Researcher
researcher v1Finds the evidence a piece rests on. Reads the primary source rather than the write-up of it, pulls the numbers out of the systems that hold them, sits in the interview with a subject-matter expert and takes down what was actually said, and records where every fact came from in a form somebody else can check. The agent exists because a published claim is only as good as the source under it, and finding that source is a different job from writing the sentence.
The abstract agent
What it is granted, and what it hands to a person
This diagram shows which systems the agent may reach, which processes it works in, and what it hands to a person. Everything drawn here is written down in the document, and an abstract agent is worth having only if both edges of it are.
Holds a specialist slice in build-by-talent - the writing slice can only claim what the evidence slice found. Sits in briefings, and sits in the room with an expert as the agent that records what was said and who said it. Takes the fact pass in layered-passes, going through a finished draft claim by claim against the sources the draft cites.
The plugin
What is in the package
17 skills and the systems they need, written to version 1.1.0 of the Agent Plugins standard. Nothing in these files names a product. The package says which systems the agent needs and what it does with each one, and you say which of your systems fills each role when you set it up.
researcher · 22 files · 1.0.0
com.agentcatalog.agent/NOT.mdWhat the agent does not do, and when it asks a person.
# Where this abstract agent stops Does not write the piece and does not decide what the piece argues. It supplies what is true, and the writer and the editor decide what to make of it. Does not judge whether the piece holds together, which is the editor agent. Does not report on how the department's own work performed, which is the analytics agent reading the organization's own numbers. Does not work out what people are searching for, which is the search-optimizer agent; this agent is after what is true, and search demand is a separate question. Does not add anything to the claims register, because that register changes only through its own process, as versioned amendments. ## What always goes to a person - a fact it cannot source - it reports the fact as unsourced and never fills the gap with a sentence that merely sounds right - two credible sources that disagree, where the piece has to stand on one of them - a person picks which one - a source whose terms do not let the organization quote or reproduce it - a finding that contradicts something the organization has already published, because somebody has to decide what happens to the older piece
com.agentcatalog.agent/RECORDS.mdThe records the agent must leave behind.
# The records this abstract agent must leave
This is the contract. An agent implementing `researcher` leaves the
following behind, on every run.
A source line for every fact: what was read, where it lives, the date it
was read, and the part of it the fact came from. Every number with the
query or the report it came from, so somebody can pull it again and see
whether the answer still holds. Interview notes attributed to the person
who said it, marked with what that person agreed could be quoted.
An agent that leaves less than this does not implement `researcher`,
whatever else it does well.
com.agentcatalog.agent/SERVERS.mdThe systems the agent needs, by role rather than by product.
# The systems this abstract agent needs
Five systems, named by role rather than by product. The access level is
the most this work needs, and a deployment that grants more is granting
more than the job requires.
| Role | Access | What the access is for |
|---|---|---|
| public and licensed sources | read | Within the subscriptions and licenses the organization actually holds. |
| paid reports and data | read | Cap: what it may buy without asking, set by the adopting organization. |
| internal data sources | read | |
| the source record | write | Every fact lands with where it came from. |
| the claims register | read | |
Whoever builds an agent from this plugin writes the `mcp.json` that
points these roles at their own systems. Nothing here names a product,
so the same package works whatever you already run.
plugin.jsonThe manifest. It lists the skills and the systems the agent needs.
{
"$schema": "https://agent-plugins.org/schemas/1.1.0/plugin.schema.json",
"name": "researcher",
"version": "1.0.0",
"description": "The researcher abstract agent. Finds the evidence a piece rests on.",
"author": {
"name": "AgentCatalog",
"url": "https://agentcatalog.com"
},
"homepage": "https://agentcatalog.com/abstract-agents/researcher",
"repository": "https://github.com/jeffrschneider/agentcatalog",
"license": "CC-BY-4.0",
"keywords": [
"abstract-agent",
"reference",
"marketing",
"product-positioning",
"brief-industry-analyst",
"ideal-customer-profile",
"abstract"
],
"extensions": {
"com.agentcatalog.agent": {
"agent": "researcher",
"agentVersion": 1,
"department": "marketing",
"abstract": true,
"works": "Holds a specialist slice in build-by-talent - the writing slice can only claim what the evidence slice found. Sits in briefings, and sits in the room with an expert as the agent that records what was said and who said it. Takes the fact pass in layered-passes, going through a finished draft claim by claim against the sources the draft cites.",
"servers": [
{
"name": "public and licensed sources",
"role": "public-and-licensed-sources",
"access": "read",
"needs": "Within the subscriptions and licenses the organization actually holds."
},
{
"name": "paid reports and data",
"role": "paid-reports-and-data",
"access": "read",
"needs": "Cap: what it may buy without asking, set by the adopting organization."
},
{
"name": "internal data sources",
"role": "internal-data-sources",
"access": "read"
},
{
"name": "the source record",
"role": "source-record",
"access": "write",
"needs": "Every fact lands with where it came from."
},
{
"name": "the claims register",
"role": "claims-register",
"access": "read"
}
],
"records": [
"A source line for every fact: what was read, where it lives, the date it was read, and the part of it the fact came from.",
"Every number with the query or the report it came from, so somebody can pull it again and see whether the answer still holds.",
"Interview notes attributed to the person who said it, marked with what that person agreed could be quoted."
],
"escalates": [
"a fact it cannot source - it reports the fact as unsourced and never fills the gap with a sentence that merely sounds right",
"two credible sources that disagree, where the piece has to stand on one of them - a person picks which one",
"a source whose terms do not let the organization quote or reproduce it",
"a finding that contradicts something the organization has already published, because somebody has to decide what happens to the older piece"
],
"not": [
"Does not write the piece and does not decide what the piece argues.",
"It supplies what is true, and the writer and the editor decide what to make of it.",
"Does not judge whether the piece holds together, which is the editor agent.",
"Does not report on how the department's own work performed, which is the analytics agent reading the organization's own numbers.",
"Does not work out what people are searching for, which is the search-optimizer agent; this agent is after what is true, and search demand is a separate question.",
"Does not add anything to the claims register, because that register changes only through its own process, as versioned amendments."
],
"processes": [
{
"process": "ref/mkt/account-based-play",
"activities": [
"Read the Accounts"
]
},
{
"process": "ref/mkt/advisory-board",
"activities": [
"Collect the Early Input",
"Capture What Was Said",
"Sort the Feedback"
]
},
{
"process": "ref/mkt/announce-company-news",
"activities": [
"Confirm the Facts"
]
},
{
"process": "ref/mkt/annual-marketing-plan",
"activities": [
"Gather the Outside Evidence"
]
},
{
"process": "ref/mkt/award-entry",
"activities": [
"Brief the Entry",
"Gather the Evidence"
]
},
{
"process": "ref/mkt/brand-health",
"activities": [
"Set the Competitor Set"
]
},
{
"process": "ref/mkt/brand-identity",
"activities": [
"Brief the Makers",
"Try the Directions on Outsiders",
"Clear the Candidate Marks"
]
},
{
"process": "ref/mkt/brand-positioning",
"activities": [
"Gather the Evidence",
"Test the Positions against the Evidence",
"Try the Positions on Outsiders",
"Record the Proof Behind the Promise"
]
},
{
"process": "ref/mkt/brand-voice",
"activities": [
"Gather How the Audience Talks",
"Brief the Makers",
"Put a Source Under Every Message",
"Try the Messages on Buyers"
]
},
{
"process": "ref/mkt/brief-executive-leadership",
"activities": [
"Gather the Outside Picture",
"Answer What Was Left Open"
]
},
{
"process": "ref/mkt/brief-industry-analyst",
"activities": [
"Read Where the Analyst Stands",
"Brief the Makers",
"Gather the Proof",
"File What the Cycle Requires",
"Answer What Was Left Open"
]
},
{
"process": "ref/mkt/buyer-persona",
"activities": [
"Gather What Is Already Known",
"Name the Others in the Decision"
]
},
{
"process": "ref/mkt/channel-program",
"activities": [
"Draw up the Candidate List",
"Assess the Applicants"
]
},
{
"process": "ref/mkt/competitive-battlecard",
"activities": [
"Confirm the Move",
"Gather the Proof"
]
},
{
"process": "ref/mkt/crisis-communication",
"activities": [
"Confirm the Facts",
"Update the Response"
]
},
{
"process": "ref/mkt/customer-case-study",
"activities": [
"Brief the Story",
"Verify the Customer's Results",
"Interview the Customer",
"Check the Facts"
]
},
{
"process": "ref/mkt/customer-reference",
"activities": [
"Verify the Customer's Results"
]
},
{
"process": "ref/mkt/customer-research",
"activities": [
"Check What Is Already Known",
"Brief the Study"
]
},
{
"process": "ref/mkt/customer-reviews",
"activities": [
"Read the Site Rules",
"Check the Ask against the Rules"
]
},
{
"process": "ref/mkt/develop-marketing-strategy",
"activities": [
"Map the Market and Its Segments",
"Read What the Rivals Are Doing",
"Hear from Buyers and the Field",
"Draft the Strategic Options"
]
},
{
"process": "ref/mkt/engage-marketing-agency",
"activities": [
"Build the Candidate List",
"Check the References"
]
},
{
"process": "ref/mkt/ideal-customer-profile",
"activities": [
"Gather the Outside Evidence",
"Collect the First-Hand Accounts",
"Draft the Candidate Profiles",
"Size Each Candidate Market",
"Clear the Data and the Targeting"
]
},
{
"process": "ref/mkt/influencer-campaign",
"activities": [
"Read the Disclosure Rules",
"Draw up the Candidate List"
]
},
{
"process": "ref/mkt/landing-page",
"activities": [
"Brief the Makers",
"Produce the Material"
]
},
{
"process": "ref/mkt/lead-scoring-model",
"activities": [
"Hear from the People Who Work the Leads",
"Gather the Candidate Signals",
"Clear the New Signals"
]
},
{
"process": "ref/mkt/long-form-content",
"activities": [
"Brief the Piece",
"Gather the Evidence",
"Check the Facts"
]
},
{
"process": "ref/mkt/map-buyer-journey",
"activities": [
"Collect the First-Hand Accounts",
"Draft the Stages",
"Collect the Questions"
]
},
{
"process": "ref/mkt/media-plan",
"activities": [
"Settle the Audience to Reach",
"Clear the Targeting and the Data",
"Gather the Channel Evidence"
]
},
{
"process": "ref/mkt/name-product",
"activities": [
"Read the Naming Landscape",
"Check the Name in Every Market"
]
},
{
"process": "ref/mkt/pitch-earned-media",
"activities": [
"Gather the Proof",
"Answer What Reporters Ask"
]
},
{
"process": "ref/mkt/product-positioning",
"activities": [
"Gather the Market Evidence",
"Interview the Makers",
"Name the Competing Choices",
"Test the Positions against the Evidence",
"Try the Positions on Outsiders",
"Record the Proof Behind Each Claim"
]
},
{
"process": "ref/mkt/quarterly-business-review",
"activities": [
"Read the Outside Conditions"
]
},
{
"process": "ref/mkt/refresh-content",
"activities": [
"Check Whether the Facts Still Hold"
]
},
{
"process": "ref/mkt/sales-enablement-kit",
"activities": [
"Hear the Field",
"Gather the Proof",
"Settle the Answers",
"Write the Objection Answers"
]
},
{
"process": "ref/mkt/segment-the-market",
"activities": [
"Set the Market Boundary",
"Gather the Outside Evidence",
"Choose the Dividing Traits",
"Size Each Segment",
"Clear the Data and the Traits"
]
},
{
"process": "ref/mkt/select-marketing-technology",
"activities": [
"Brief the Selection",
"Search the Market"
]
},
{
"process": "ref/mkt/size-market-opportunity",
"activities": [
"Draw the Market Boundary",
"Gather the Outside Evidence",
"Count the Buyers",
"Check the Method",
"Clear the Sources"
]
},
{
"process": "ref/mkt/speaking-engagement",
"activities": [
"Take in the Call",
"Shape the Talk"
]
},
{
"process": "ref/mkt/user-conference",
"activities": [
"Capture the Sessions"
]
},
{
"process": "ref/mkt/website-content-update",
"activities": [
"Write the Change"
]
}
]
}
}
}
README.mdWhat the package is, and why it carries no mcp.json.
# researcher This is an abstract agent, published as an Agent Plugin. An abstract agent is a job description rather than an implementation. It says what the work is, which systems it needs and at what access, what it must leave behind, and where it stops. Any agent that leaves the records can implement it. The plugin carries seventeen skills, no `mcp.json`, and everything the abstract agent owes under `com.agentcatalog.agent/`. ## Why there is no mcp.json A conformant server entry in `mcp.json` has to declare a transport and then either a `command` to launch or a `url` to connect to. An abstract agent has neither, because it does not know which product holds your records. Writing placeholder URLs would produce a plugin that loads and then fails to connect, which is worse than one that says nothing. Section 6.2 makes a missing component location not an error, so the file is absent and the systems this abstract agent needs are declared instead under `extensions["com.agentcatalog.agent"].servers`, as a role, an access level and what the access is for. Whoever builds an agent from this plugin writes the `mcp.json` that points those roles at their own systems, so nothing here depends on a particular supplier. ## Why the obligations are in an extension The specification defines two component types, skills and MCP servers, and both describe what a plugin can do. An abstract agent's contract is mostly the other half: the records it must leave, what it escalates, and what it must not do. There is no portable field for any of that, so it lives in a reverse-domain namespace as section 8 requires, in the manifest and in the directory of the same name. ## Where this abstract agent is used `ref/mkt/account-based-play`, `ref/mkt/advisory-board`, `ref/mkt/announce-company-news`, `ref/mkt/annual-marketing-plan`, `ref/mkt/award-entry`, `ref/mkt/brand-health`, and 34 more. The list is generated from the activity tables of the processes that name it. https://agentcatalog.com/abstract-agents/researcher
skills/answer-a-question-left-open/SKILL.mdGoes back after a meeting or a conversation and settles the questions nobody could answer at the time. Use it when running `ref/mkt/brief-executive-leadership`, `ref/mkt/brief-industry-analyst` and `ref/mkt/pitch-earned-media`.
--- name: answer-a-question-left-open description: Goes back after a meeting or a conversation and settles the questions nobody could answer at the time. Use it when running `ref/mkt/brief-executive-leadership`, `ref/mkt/brief-industry-analyst` and `ref/mkt/pitch-earned-media`. license: CC-BY-4.0 metadata: agent: researcher agent-version: "1" --- # Answer a question left open ## What it does Goes back after a meeting or a conversation and settles the questions nobody could answer at the time. It finds the extra data, runs the fact check, or arranges the further interview, and returns the answer with its source. ## Where it happens The agent does this in two activities across three reference processes. Each one names the activity as that process words it. - **Answer What Reporters Ask** - `ref/mkt/pitch-earned-media`, activity 13 - [Pitch Earned Media](../../../../processes/marketing/pitch-earned-media.md) - **Answer What Was Left Open** - `ref/mkt/brief-executive-leadership`, activity 18 - [Brief Executive Leadership](../../../../processes/marketing/brief-executive-leadership.md) - `ref/mkt/brief-industry-analyst`, activity 13 - [Brief Industry Analyst](../../../../processes/marketing/brief-industry-analyst.md) ## What to record A source line for every fact: what was read, where it lives, the date it was read, and the part of it the fact came from. Every number with the query or the report it came from, so somebody can pull it again and see whether the answer still holds. Interview notes attributed to the person who said it, marked with what that person agreed could be quoted. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
skills/brief-everyone-on-the-request/SKILL.mdPuts the request, the evidence behind it and the dates in front of everyone who has to act on it at the same time, so that nobody works from a different version of what was asked. Use it when running `ref/mkt/award-entry` and 8 other reference processes.
--- name: brief-everyone-on-the-request description: Puts the request, the evidence behind it and the dates in front of everyone who has to act on it at the same time, so that nobody works from a different version of what was asked. Use it when running `ref/mkt/award-entry` and 8 other reference processes. license: CC-BY-4.0 metadata: agent: researcher agent-version: "1" --- # Brief everyone on the request ## What it does Puts the request, the evidence behind it and the dates in front of everyone who has to act on it at the same time, so that nobody works from a different version of what was asked. ## Where it happens The agent does this in six activities across nine reference processes. Each one names the activity as that process words it. - **Brief the Entry** - `ref/mkt/award-entry`, activity 5 - [Submit Award Entry](../../../../processes/marketing/award-entry.md) - **Brief the Makers** - `ref/mkt/brand-identity`, activity 4 - [Develop Brand Identity](../../../../processes/marketing/brand-identity.md) - `ref/mkt/brand-voice`, activity 4 - [Define Brand Voice and Messaging](../../../../processes/marketing/brand-voice.md) - `ref/mkt/brief-industry-analyst`, activity 4 - [Brief Industry Analyst](../../../../processes/marketing/brief-industry-analyst.md) - `ref/mkt/landing-page`, activity 4 - [Publish Landing Page](../../../../processes/marketing/landing-page.md) - **Brief the Piece** - `ref/mkt/long-form-content`, activity 3 - [Produce Long-Form Content](../../../../processes/marketing/long-form-content.md) - **Brief the Selection** - `ref/mkt/select-marketing-technology`, activity 5 - [Select Marketing Technology](../../../../processes/marketing/select-marketing-technology.md) - **Brief the Story** - `ref/mkt/customer-case-study`, activity 6 - [Produce Customer Case Study](../../../../processes/marketing/customer-case-study.md) - **Brief the Study** - `ref/mkt/customer-research`, activity 4 - [Conduct Customer Research](../../../../processes/marketing/customer-research.md) ## What to record A source line for every fact: what was read, where it lives, the date it was read, and the part of it the fact came from. Every number with the query or the report it came from, so somebody can pull it again and see whether the answer still holds. Interview notes attributed to the person who said it, marked with what that person agreed could be quoted. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
skills/check-claims-against-their-sources/SKILL.mdTakes a claim somebody wants to publish, finds the source under it, and says whether that source actually carries the claim. Use it when running `ref/mkt/announce-company-news` and 9 other reference processes.
--- name: check-claims-against-their-sources description: Takes a claim somebody wants to publish, finds the source under it, and says whether that source actually carries the claim. Use it when running `ref/mkt/announce-company-news` and 9 other reference processes. license: CC-BY-4.0 metadata: agent: researcher agent-version: "1" --- # Check claims against their sources ## What it does Takes a claim somebody wants to publish, finds the source under it, and says whether that source actually carries the claim. It redoes the arithmetic behind a figure, reads a number straight out of the system that holds it, and records the source beside every claim so that the next person can check the same thing. ## Where it happens The agent does this in nine activities across ten reference processes. Each one names the activity as that process words it. - **Check Whether the Facts Still Hold** - `ref/mkt/refresh-content`, activity 6 - [Refresh Published Content](../../../../processes/marketing/refresh-content.md) - **Check the Facts** - `ref/mkt/customer-case-study`, activity 12 - [Produce Customer Case Study](../../../../processes/marketing/customer-case-study.md) - `ref/mkt/long-form-content`, activity 8 - [Produce Long-Form Content](../../../../processes/marketing/long-form-content.md) - **Check the Method** - `ref/mkt/size-market-opportunity`, activity 10 - [Size Market Opportunity](../../../../processes/marketing/size-market-opportunity.md) - **Confirm the Facts** - `ref/mkt/announce-company-news`, activity 3 - [Announce Company News](../../../../processes/marketing/announce-company-news.md) - `ref/mkt/crisis-communication`, activity 2 - [Manage Crisis Communication](../../../../processes/marketing/crisis-communication.md) - **Put a Source Under Every Message** - `ref/mkt/brand-voice`, activity 8 - [Define Brand Voice and Messaging](../../../../processes/marketing/brand-voice.md) - **Record the Proof Behind Each Claim** - `ref/mkt/product-positioning`, activity 13 - [Develop Product Positioning](../../../../processes/marketing/product-positioning.md) - **Record the Proof Behind the Promise** - `ref/mkt/brand-positioning`, activity 11 - [Define Brand Positioning](../../../../processes/marketing/brand-positioning.md) - **Test the Positions against the Evidence** - `ref/mkt/brand-positioning`, activity 7 - [Define Brand Positioning](../../../../processes/marketing/brand-positioning.md) - `ref/mkt/product-positioning`, activity 9 - [Develop Product Positioning](../../../../processes/marketing/product-positioning.md) - **Verify the Customer's Results** - `ref/mkt/customer-case-study`, activity 7 - [Produce Customer Case Study](../../../../processes/marketing/customer-case-study.md) - `ref/mkt/customer-reference`, activity 5 - [Recruit Customer Reference](../../../../processes/marketing/customer-reference.md) ## What to record A source line for every fact: what was read, where it lives, the date it was read, and the part of it the fact came from. Every number with the query or the report it came from, so somebody can pull it again and see whether the answer still holds. Interview notes attributed to the person who said it, marked with what that person agreed could be quoted. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
skills/check-what-the-terms-allow/SKILL.mdReads the terms attached to a data source, a site or a market and says what may actually be used, targeted, scored on, offered or published. Use it when running `ref/mkt/customer-reviews` and 6 other reference processes.
--- name: check-what-the-terms-allow description: Reads the terms attached to a data source, a site or a market and says what may actually be used, targeted, scored on, offered or published. Use it when running `ref/mkt/customer-reviews` and 6 other reference processes. license: CC-BY-4.0 metadata: agent: researcher agent-version: "1" --- # Check what the terms allow ## What it does Reads the terms attached to a data source, a site or a market and says what may actually be used, targeted, scored on, offered or published. Every answer names the term or the rule it rests on, so an agent planning around it knows where the line is. ## Where it happens The agent does this in eight activities across seven reference processes. Each one names the activity as that process words it. - **Check the Ask against the Rules** - `ref/mkt/customer-reviews`, activity 7 - [Solicit Customer Reviews](../../../../processes/marketing/customer-reviews.md) - **Clear the Data and the Targeting** - `ref/mkt/ideal-customer-profile`, activity 11 - [Define Ideal Customer Profile](../../../../processes/marketing/ideal-customer-profile.md) - **Clear the Data and the Traits** - `ref/mkt/segment-the-market`, activity 11 - [Segment the Market](../../../../processes/marketing/segment-the-market.md) - **Clear the New Signals** - `ref/mkt/lead-scoring-model`, activity 6 - [Maintain Lead Scoring Model](../../../../processes/marketing/lead-scoring-model.md) - **Clear the Sources** - `ref/mkt/size-market-opportunity`, activity 11 - [Size Market Opportunity](../../../../processes/marketing/size-market-opportunity.md) - **Clear the Targeting and the Data** - `ref/mkt/media-plan`, activity 4 - [Develop Media Plan](../../../../processes/marketing/media-plan.md) - **Read the Disclosure Rules** - `ref/mkt/influencer-campaign`, activity 3 - [Run Influencer Campaign](../../../../processes/marketing/influencer-campaign.md) - **Read the Site Rules** - `ref/mkt/customer-reviews`, activity 2 - [Solicit Customer Reviews](../../../../processes/marketing/customer-reviews.md) ## What to record A source line for every fact: what was read, where it lives, the date it was read, and the part of it the fact came from. Every number with the query or the report it came from, so somebody can pull it again and see whether the answer still holds. Interview notes attributed to the person who said it, marked with what that person agreed could be quoted. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
skills/clear-a-candidate-name/SKILL.mdChecks a candidate name before anybody commits to it. Use it when running `ref/mkt/brand-identity` and `ref/mkt/name-product`.
--- name: clear-a-candidate-name description: Checks a candidate name before anybody commits to it. Use it when running `ref/mkt/brand-identity` and `ref/mkt/name-product`. license: CC-BY-4.0 metadata: agent: researcher agent-version: "1" --- # Clear a candidate name ## What it does Checks a candidate name before anybody commits to it. It searches the registers for marks already in use, and finds out what the name means and how it sounds in every market where it will be used. ## Where it happens The agent does this in two activities across two reference processes. Each one names the activity as that process words it. - **Check the Name in Every Market** - `ref/mkt/name-product`, activity 7 - [Name Product or Company](../../../../processes/marketing/name-product.md) - **Clear the Candidate Marks** - `ref/mkt/brand-identity`, activity 8 - [Develop Brand Identity](../../../../processes/marketing/brand-identity.md) ## What to record A source line for every fact: what was read, where it lives, the date it was read, and the part of it the fact came from. Every number with the query or the report it came from, so somebody can pull it again and see whether the answer still holds. Interview notes attributed to the person who said it, marked with what that person agreed could be quoted. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
skills/define-the-market-and-how-it-divides/SKILL.mdSettles what counts as inside a market and what falls outside it, and picks the traits the market gets divided on. Use it when running `ref/mkt/segment-the-market` and `ref/mkt/size-market-opportunity`.
--- name: define-the-market-and-how-it-divides description: Settles what counts as inside a market and what falls outside it, and picks the traits the market gets divided on. Use it when running `ref/mkt/segment-the-market` and `ref/mkt/size-market-opportunity`. license: CC-BY-4.0 metadata: agent: researcher agent-version: "1" --- # Define the market and how it divides ## What it does Settles what counts as inside a market and what falls outside it, and picks the traits the market gets divided on. It writes down the reason behind every line it draws. ## Where it happens The agent does this in three activities across two reference processes. Each one names the activity as that process words it. - **Choose the Dividing Traits** - `ref/mkt/segment-the-market`, activity 6 - [Segment the Market](../../../../processes/marketing/segment-the-market.md) - **Draw the Market Boundary** - `ref/mkt/size-market-opportunity`, activity 2 - [Size Market Opportunity](../../../../processes/marketing/size-market-opportunity.md) - **Set the Market Boundary** - `ref/mkt/segment-the-market`, activity 2 - [Segment the Market](../../../../processes/marketing/segment-the-market.md) ## What to record A source line for every fact: what was read, where it lives, the date it was read, and the part of it the fact came from. Every number with the query or the report it came from, so somebody can pull it again and see whether the answer still holds. Interview notes attributed to the person who said it, marked with what that person agreed could be quoted. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
skills/draft-what-the-evidence-supports/SKILL.mdTurns gathered evidence into a small number of drafts people can argue with, such as two or three shapes of buyer, the stages a buyer moves through, the other people who have to agree, or the ways the organization could compete. Use it when running `ref/mkt/buyer-persona` and 3 other reference processes.
--- name: draft-what-the-evidence-supports description: Turns gathered evidence into a small number of drafts people can argue with, such as two or three shapes of buyer, the stages a buyer moves through, the other people who have to agree, or the ways the organization could compete. Use it when running `ref/mkt/buyer-persona` and 3 other reference processes. license: CC-BY-4.0 metadata: agent: researcher agent-version: "1" --- # Draft what the evidence supports ## What it does Turns gathered evidence into a small number of drafts people can argue with, such as two or three shapes of buyer, the stages a buyer moves through, the other people who have to agree, or the ways the organization could compete. Each draft carries the evidence it rests on. ## Where it happens The agent does this in four activities across four reference processes. Each one names the activity as that process words it. - **Draft the Candidate Profiles** - `ref/mkt/ideal-customer-profile`, activity 6 - [Define Ideal Customer Profile](../../../../processes/marketing/ideal-customer-profile.md) - **Draft the Stages** - `ref/mkt/map-buyer-journey`, activity 8 - [Map Buyer Journey](../../../../processes/marketing/map-buyer-journey.md) - **Draft the Strategic Options** - `ref/mkt/develop-marketing-strategy`, activity 6 - [Develop Marketing Strategy](../../../../processes/marketing/develop-marketing-strategy.md) - **Name the Others in the Decision** - `ref/mkt/buyer-persona`, activity 12 - [Develop Buyer Persona](../../../../processes/marketing/buyer-persona.md) ## What to record A source line for every fact: what was read, where it lives, the date it was read, and the part of it the fact came from. Every number with the query or the report it came from, so somebody can pull it again and see whether the answer still holds. Interview notes attributed to the person who said it, marked with what that person agreed could be quoted. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
skills/find-and-assess-outside-candidates/SKILL.mdSearches for every outside organization that could do a piece of work or join a program, then reads each one against the stated profile and terms. Use it when running `ref/mkt/channel-program` and 3 other reference processes.
--- name: find-and-assess-outside-candidates description: Searches for every outside organization that could do a piece of work or join a program, then reads each one against the stated profile and terms. Use it when running `ref/mkt/channel-program` and 3 other reference processes. license: CC-BY-4.0 metadata: agent: researcher agent-version: "1" --- # Find and assess outside candidates ## What it does Searches for every outside organization that could do a piece of work or join a program, then reads each one against the stated profile and terms. It talks to their existing clients and reports where each candidate stands. ## Where it happens The agent does this in five activities across four reference processes. Each one names the activity as that process words it. - **Assess the Applicants** - `ref/mkt/channel-program`, activity 12 - [Launch Channel Program](../../../../processes/marketing/channel-program.md) - **Build the Candidate List** - `ref/mkt/engage-marketing-agency`, activity 7 - [Engage Marketing Agency](../../../../processes/marketing/engage-marketing-agency.md) - **Check the References** - `ref/mkt/engage-marketing-agency`, activity 11 - [Engage Marketing Agency](../../../../processes/marketing/engage-marketing-agency.md) - **Draw up the Candidate List** - `ref/mkt/channel-program`, activity 5 - [Launch Channel Program](../../../../processes/marketing/channel-program.md) - `ref/mkt/influencer-campaign`, activity 4 - [Run Influencer Campaign](../../../../processes/marketing/influencer-campaign.md) - **Search the Market** - `ref/mkt/select-marketing-technology`, activity 8 - [Select Marketing Technology](../../../../processes/marketing/select-marketing-technology.md) ## What to record A source line for every fact: what was read, where it lives, the date it was read, and the part of it the fact came from. Every number with the query or the report it came from, so somebody can pull it again and see whether the answer still holds. Interview notes attributed to the person who said it, marked with what that person agreed could be quoted. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
skills/gather-published-evidence/SKILL.mdPulls together what has already been published on a subject and reads the primary source rather than somebody's write-up of it. Use it when running `ref/mkt/annual-marketing-plan` and 16 other reference processes.
--- name: gather-published-evidence description: Pulls together what has already been published on a subject and reads the primary source rather than somebody's write-up of it. Use it when running `ref/mkt/annual-marketing-plan` and 16 other reference processes. license: CC-BY-4.0 metadata: agent: researcher agent-version: "1" --- # Gather published evidence ## What it does Pulls together what has already been published on a subject and reads the primary source rather than somebody's write-up of it. It comes back with the market picture, the figures and the quotations that answer the question, each carrying the source it came from and the date it was pulled. It checks first whether the organization's own record already answers the question. ## Where it happens The agent does this in nine activities across seventeen reference processes. Each one names the activity as that process words it. - **Check What Is Already Known** - `ref/mkt/customer-research`, activity 2 - [Conduct Customer Research](../../../../processes/marketing/customer-research.md) - **Gather How the Audience Talks** - `ref/mkt/brand-voice`, activity 3 - [Define Brand Voice and Messaging](../../../../processes/marketing/brand-voice.md) - **Gather What Is Already Known** - `ref/mkt/buyer-persona`, activity 3 - [Develop Buyer Persona](../../../../processes/marketing/buyer-persona.md) - **Gather the Evidence** - `ref/mkt/award-entry`, activity 6 - [Submit Award Entry](../../../../processes/marketing/award-entry.md) - `ref/mkt/brand-positioning`, activity 2 - [Define Brand Positioning](../../../../processes/marketing/brand-positioning.md) - `ref/mkt/long-form-content`, activity 4 - [Produce Long-Form Content](../../../../processes/marketing/long-form-content.md) - **Gather the Market Evidence** - `ref/mkt/product-positioning`, activity 3 - [Develop Product Positioning](../../../../processes/marketing/product-positioning.md) - **Gather the Outside Evidence** - `ref/mkt/annual-marketing-plan`, activity 4 - [Build Annual Marketing Plan](../../../../processes/marketing/annual-marketing-plan.md) - `ref/mkt/ideal-customer-profile`, activity 3 - [Define Ideal Customer Profile](../../../../processes/marketing/ideal-customer-profile.md) - `ref/mkt/segment-the-market`, activity 4 - [Segment the Market](../../../../processes/marketing/segment-the-market.md) - `ref/mkt/size-market-opportunity`, activity 4 - [Size Market Opportunity](../../../../processes/marketing/size-market-opportunity.md) - **Gather the Outside Picture** - `ref/mkt/brief-executive-leadership`, activity 8 - [Brief Executive Leadership](../../../../processes/marketing/brief-executive-leadership.md) - **Gather the Proof** - `ref/mkt/brief-industry-analyst`, activity 5 - [Brief Industry Analyst](../../../../processes/marketing/brief-industry-analyst.md) - `ref/mkt/competitive-battlecard`, activity 5 - [Refresh Competitive Battlecard](../../../../processes/marketing/competitive-battlecard.md) - `ref/mkt/pitch-earned-media`, activity 3 - [Pitch Earned Media](../../../../processes/marketing/pitch-earned-media.md) - `ref/mkt/sales-enablement-kit`, activity 4 - [Produce Sales Enablement Kit](../../../../processes/marketing/sales-enablement-kit.md) - **Read the Outside Conditions** - `ref/mkt/quarterly-business-review`, activity 5 - [Conduct Quarterly Business Review](../../../../processes/marketing/quarterly-business-review.md) ## What to record A source line for every fact: what was read, where it lives, the date it was read, and the part of it the fact came from. Every number with the query or the report it came from, so somebody can pull it again and see whether the answer still holds. Interview notes attributed to the person who said it, marked with what that person agreed could be quoted. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
skills/interview-people/SKILL.mdSits down with customers, buyers, sellers and the people who build the product, asks them what happened, and takes down what they said in their own words. Use it when running `ref/mkt/advisory-board` and 7 other reference processes.
--- name: interview-people description: Sits down with customers, buyers, sellers and the people who build the product, asks them what happened, and takes down what they said in their own words. Use it when running `ref/mkt/advisory-board` and 7 other reference processes. license: CC-BY-4.0 metadata: agent: researcher agent-version: "1" --- # Interview people ## What it does Sits down with customers, buyers, sellers and the people who build the product, asks them what happened, and takes down what they said in their own words. The answers come back attributed, so a later reader can tell who said what. ## Where it happens The agent does this in eight activities across eight reference processes. Each one names the activity as that process words it. - **Collect the Early Input** - `ref/mkt/advisory-board`, activity 10 - [Convene Customer Advisory Board](../../../../processes/marketing/advisory-board.md) - **Collect the First-Hand Accounts** - `ref/mkt/ideal-customer-profile`, activity 4 - [Define Ideal Customer Profile](../../../../processes/marketing/ideal-customer-profile.md) - `ref/mkt/map-buyer-journey`, activity 7 - [Map Buyer Journey](../../../../processes/marketing/map-buyer-journey.md) - **Collect the Questions** - `ref/mkt/map-buyer-journey`, activity 10 - [Map Buyer Journey](../../../../processes/marketing/map-buyer-journey.md) - **Hear from Buyers and the Field** - `ref/mkt/develop-marketing-strategy`, activity 5 - [Develop Marketing Strategy](../../../../processes/marketing/develop-marketing-strategy.md) - **Hear from the People Who Work the Leads** - `ref/mkt/lead-scoring-model`, activity 4 - [Maintain Lead Scoring Model](../../../../processes/marketing/lead-scoring-model.md) - **Hear the Field** - `ref/mkt/sales-enablement-kit`, activity 3 - [Produce Sales Enablement Kit](../../../../processes/marketing/sales-enablement-kit.md) - **Interview the Customer** - `ref/mkt/customer-case-study`, activity 8 - [Produce Customer Case Study](../../../../processes/marketing/customer-case-study.md) - **Interview the Makers** - `ref/mkt/product-positioning`, activity 6 - [Develop Product Positioning](../../../../processes/marketing/product-positioning.md) ## What to record A source line for every fact: what was read, where it lives, the date it was read, and the part of it the fact came from. Every number with the query or the report it came from, so somebody can pull it again and see whether the answer still holds. Interview notes attributed to the person who said it, marked with what that person agreed could be quoted. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
skills/pull-the-numbers-from-the-systems/SKILL.mdReads the organization's own records to answer a question about accounts, channels or signals. Use it when running `ref/mkt/account-based-play`, `ref/mkt/lead-scoring-model` and `ref/mkt/media-plan`.
--- name: pull-the-numbers-from-the-systems description: Reads the organization's own records to answer a question about accounts, channels or signals. Use it when running `ref/mkt/account-based-play`, `ref/mkt/lead-scoring-model` and `ref/mkt/media-plan`. license: CC-BY-4.0 metadata: agent: researcher agent-version: "1" --- # Pull the numbers from the systems ## What it does Reads the organization's own records to answer a question about accounts, channels or signals. It comes back with what each account or channel has actually done, and names the system and the date every figure came from. ## Where it happens The agent does this in three activities across three reference processes. Each one names the activity as that process words it. - **Gather the Candidate Signals** - `ref/mkt/lead-scoring-model`, activity 5 - [Maintain Lead Scoring Model](../../../../processes/marketing/lead-scoring-model.md) - **Gather the Channel Evidence** - `ref/mkt/media-plan`, activity 5 - [Develop Media Plan](../../../../processes/marketing/media-plan.md) - **Read the Accounts** - `ref/mkt/account-based-play`, activity 2 - [Run Account-Based Play](../../../../processes/marketing/account-based-play.md) ## What to record A source line for every fact: what was read, where it lives, the date it was read, and the part of it the fact came from. Every number with the query or the report it came from, so somebody can pull it again and see whether the answer still holds. Interview notes attributed to the person who said it, marked with what that person agreed could be quoted. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
skills/read-the-competitive-landscape/SKILL.mdReads what other companies in the market have published about themselves and what an outside firm has published about this one. Use it when running `ref/mkt/brand-health` and 5 other reference processes.
--- name: read-the-competitive-landscape description: Reads what other companies in the market have published about themselves and what an outside firm has published about this one. Use it when running `ref/mkt/brand-health` and 5 other reference processes. license: CC-BY-4.0 metadata: agent: researcher agent-version: "1" --- # Read the competitive landscape ## What it does Reads what other companies in the market have published about themselves and what an outside firm has published about this one. It says which rivals are the relevant ones, what each of them sells and claims, what the category sounds like, and what a buyer would choose instead. ## Where it happens The agent does this in six activities across six reference processes. Each one names the activity as that process words it. - **Confirm the Move** - `ref/mkt/competitive-battlecard`, activity 2 - [Refresh Competitive Battlecard](../../../../processes/marketing/competitive-battlecard.md) - **Name the Competing Choices** - `ref/mkt/product-positioning`, activity 7 - [Develop Product Positioning](../../../../processes/marketing/product-positioning.md) - **Read What the Rivals Are Doing** - `ref/mkt/develop-marketing-strategy`, activity 4 - [Develop Marketing Strategy](../../../../processes/marketing/develop-marketing-strategy.md) - **Read Where the Analyst Stands** - `ref/mkt/brief-industry-analyst`, activity 2 - [Brief Industry Analyst](../../../../processes/marketing/brief-industry-analyst.md) - **Read the Naming Landscape** - `ref/mkt/name-product`, activity 3 - [Name Product or Company](../../../../processes/marketing/name-product.md) - **Set the Competitor Set** - `ref/mkt/brand-health`, activity 4 - [Measure Brand Health](../../../../processes/marketing/brand-health.md) ## What to record A source line for every fact: what was read, where it lives, the date it was read, and the part of it the fact came from. Every number with the query or the report it came from, so somebody can pull it again and see whether the answer still holds. Interview notes attributed to the person who said it, marked with what that person agreed could be quoted. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
skills/record-what-was-said/SKILL.mdCaptures a session while it happens, which means the recording, the notes, the photographs and the quotations, and marks what may be repeated outside the room. Use it when running `ref/mkt/advisory-board` and `ref/mkt/user-conference`.
--- name: record-what-was-said description: Captures a session while it happens, which means the recording, the notes, the photographs and the quotations, and marks what may be repeated outside the room. Use it when running `ref/mkt/advisory-board` and `ref/mkt/user-conference`. license: CC-BY-4.0 metadata: agent: researcher agent-version: "1" --- # Record what was said ## What it does Captures a session while it happens, which means the recording, the notes, the photographs and the quotations, and marks what may be repeated outside the room. It then groups what was said into themes and keeps the quotations under each theme. ## Where it happens The agent does this in three activities across two reference processes. Each one names the activity as that process words it. - **Capture What Was Said** - `ref/mkt/advisory-board`, activity 12 - [Convene Customer Advisory Board](../../../../processes/marketing/advisory-board.md) - **Capture the Sessions** - `ref/mkt/user-conference`, activity 14 - [Host User Conference](../../../../processes/marketing/user-conference.md) - **Sort the Feedback** - `ref/mkt/advisory-board`, activity 13 - [Convene Customer Advisory Board](../../../../processes/marketing/advisory-board.md) ## What to record A source line for every fact: what was read, where it lives, the date it was read, and the part of it the fact came from. Every number with the query or the report it came from, so somebody can pull it again and see whether the answer still holds. Interview notes attributed to the person who said it, marked with what that person agreed could be quoted. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
skills/size-a-market-or-an-audience/SKILL.mdCounts how many buyers or accounts of a given shape actually exist and how much money sits with them, and describes how buyers buy in each part. Use it when running `ref/mkt/develop-marketing-strategy` and 4 other reference processes.
--- name: size-a-market-or-an-audience description: Counts how many buyers or accounts of a given shape actually exist and how much money sits with them, and describes how buyers buy in each part. Use it when running `ref/mkt/develop-marketing-strategy` and 4 other reference processes. license: CC-BY-4.0 metadata: agent: researcher agent-version: "1" --- # Size a market or an audience ## What it does Counts how many buyers or accounts of a given shape actually exist and how much money sits with them, and describes how buyers buy in each part. It reports the count with the source and the method behind it, so somebody else can redo the sum. ## Where it happens The agent does this in five activities across five reference processes. Each one names the activity as that process words it. - **Count the Buyers** - `ref/mkt/size-market-opportunity`, activity 5 - [Size Market Opportunity](../../../../processes/marketing/size-market-opportunity.md) - **Map the Market and Its Segments** - `ref/mkt/develop-marketing-strategy`, activity 3 - [Develop Marketing Strategy](../../../../processes/marketing/develop-marketing-strategy.md) - **Settle the Audience to Reach** - `ref/mkt/media-plan`, activity 3 - [Develop Media Plan](../../../../processes/marketing/media-plan.md) - **Size Each Candidate Market** - `ref/mkt/ideal-customer-profile`, activity 10 - [Define Ideal Customer Profile](../../../../processes/marketing/ideal-customer-profile.md) - **Size Each Segment** - `ref/mkt/segment-the-market`, activity 9 - [Segment the Market](../../../../processes/marketing/segment-the-market.md) ## What to record A source line for every fact: what was read, where it lives, the date it was read, and the part of it the fact came from. Every number with the query or the report it came from, so somebody can pull it again and see whether the answer still holds. Interview notes attributed to the person who said it, marked with what that person agreed could be quoted. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
skills/take-in-a-call-for-speakers/SKILL.mdReads a published call for speakers and works out what it is asking for, which is what the event is, who attends, and when it closes. Use it when running `ref/mkt/speaking-engagement`.
--- name: take-in-a-call-for-speakers description: Reads a published call for speakers and works out what it is asking for, which is what the event is, who attends, and when it closes. Use it when running `ref/mkt/speaking-engagement`. license: CC-BY-4.0 metadata: agent: researcher agent-version: "1" --- # Take in a call for speakers ## What it does Reads a published call for speakers and works out what it is asking for, which is what the event is, who attends, and when it closes. ## Where it happens The agent does this in one activity across one reference process. Each one names the activity as that process words it. - **Take in the Call** - `ref/mkt/speaking-engagement`, activity 1 - [Secure Speaking Engagement](../../../../processes/marketing/speaking-engagement.md) ## What to record A source line for every fact: what was read, where it lives, the date it was read, and the part of it the fact came from. Every number with the query or the report it came from, so somebody can pull it again and see whether the answer still holds. Interview notes attributed to the person who said it, marked with what that person agreed could be quoted. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
skills/test-material-on-outsiders/SKILL.mdPuts a draft direction, message or position in front of people outside the company and reports how they read it. Use it when running `ref/mkt/brand-identity` and 3 other reference processes.
--- name: test-material-on-outsiders description: Puts a draft direction, message or position in front of people outside the company and reports how they read it. Use it when running `ref/mkt/brand-identity` and 3 other reference processes. license: CC-BY-4.0 metadata: agent: researcher agent-version: "1" --- # Test material on outsiders ## What it does Puts a draft direction, message or position in front of people outside the company and reports how they read it. It says what each person understood and where that differed from what the material intended. ## Where it happens The agent does this in three activities across four reference processes. Each one names the activity as that process words it. - **Try the Directions on Outsiders** - `ref/mkt/brand-identity`, activity 7 - [Develop Brand Identity](../../../../processes/marketing/brand-identity.md) - **Try the Messages on Buyers** - `ref/mkt/brand-voice`, activity 13 - [Define Brand Voice and Messaging](../../../../processes/marketing/brand-voice.md) - **Try the Positions on Outsiders** - `ref/mkt/brand-positioning`, activity 8 - [Define Brand Positioning](../../../../processes/marketing/brand-positioning.md) - `ref/mkt/product-positioning`, activity 10 - [Develop Product Positioning](../../../../processes/marketing/product-positioning.md) ## What to record A source line for every fact: what was read, where it lives, the date it was read, and the part of it the fact came from. Every number with the query or the report it came from, so somebody can pull it again and see whether the answer still holds. Interview notes attributed to the person who said it, marked with what that person agreed could be quoted. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
skills/write-with-the-sources-attached/SKILL.mdWrites material whose argument has to hold up under checking, such as an answer to an objection, a change to a published page, a talk, a statement reissued on new facts, or a response in a form somebody else set. Use it when running `ref/mkt/brief-industry-analyst` and 5 other reference processes.
--- name: write-with-the-sources-attached description: Writes material whose argument has to hold up under checking, such as an answer to an objection, a change to a published page, a talk, a statement reissued on new facts, or a response in a form somebody else set. Use it when running `ref/mkt/brief-industry-analyst` and 5 other reference processes. license: CC-BY-4.0 metadata: agent: researcher agent-version: "1" --- # Write with the sources attached ## What it does Writes material whose argument has to hold up under checking, such as an answer to an objection, a change to a published page, a talk, a statement reissued on new facts, or a response in a form somebody else set. Every claim in it carries the source underneath. ## Where it happens The agent does this in seven activities across six reference processes. Each one names the activity as that process words it. - **File What the Cycle Requires** - `ref/mkt/brief-industry-analyst`, activity 9 - [Brief Industry Analyst](../../../../processes/marketing/brief-industry-analyst.md) - **Produce the Material** - `ref/mkt/landing-page`, activity 5 - [Publish Landing Page](../../../../processes/marketing/landing-page.md) - **Settle the Answers** - `ref/mkt/sales-enablement-kit`, activity 5 - [Produce Sales Enablement Kit](../../../../processes/marketing/sales-enablement-kit.md) - **Shape the Talk** - `ref/mkt/speaking-engagement`, activity 7 - [Secure Speaking Engagement](../../../../processes/marketing/speaking-engagement.md) - **Update the Response** - `ref/mkt/crisis-communication`, activity 14 - [Manage Crisis Communication](../../../../processes/marketing/crisis-communication.md) - **Write the Change** - `ref/mkt/website-content-update`, activity 4 - [Update Website Content](../../../../processes/marketing/website-content-update.md) - **Write the Objection Answers** - `ref/mkt/sales-enablement-kit`, activity 9 - [Produce Sales Enablement Kit](../../../../processes/marketing/sales-enablement-kit.md) ## What to record A source line for every fact: what was read, where it lives, the date it was read, and the part of it the fact came from. Every number with the query or the report it came from, so somebody can pull it again and see whether the answer still holds. Interview notes attributed to the person who said it, marked with what that person agreed could be quoted. That contract covers every activity this abstract agent takes on, and it is repeated in `com.agentcatalog.agent/RECORDS.md`. What the abstract agent does not do is in `com.agentcatalog.agent/NOT.md`.
mcp.jsonNot in the package.
Every server entry in an mcp.json needs either a command to run or a url to connect to, and the package cannot know either of those until somebody points it at their own systems. So the file is left out, the systems the agent needs are named by role in plugin.json, and you write the mcp.json when you set it up.
Setting it up
Point it at your systems
To run an agent built from this package, write an mcp.json that says which of your systems fills each role. The package names these 5 roles, and the access level beside each one is the most the work needs.
public-and-licensed-sources · readpaid-reports-and-data · readinternal-data-sources · readsource-record · writeclaims-register · read
mcp.json
You write this file. It is not part of the package.
{
"$schema": "https://agent-plugins.org/schemas/1.1.0/mcp.schema.json",
"mcpServers": {
"public-and-licensed-sources": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/public-and-licensed-sources"
},
"paid-reports-and-data": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/paid-reports-and-data"
},
"internal-data-sources": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/internal-data-sources"
},
"source-record": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/source-record"
},
"claims-register": {
"type": "streamable-http",
"url": "https://mcp.yourcompany.com/claims-register"
}
}
}
The hostnames here are a placeholder for your own. Whichever product holds each of these systems, the agent you build is yours and nobody else has to be involved in running it.
Where it works
61 processes, 140 activities
The highlighted activities are the ones this abstract agent does. The other activities in each process belong to other abstract agents or to people.
Run Account-Based Playref/mkt/account-based-play · 19 activities
Read the Accounts
Convene Customer Advisory Boardref/mkt/advisory-board · 16 activities
Collect the Early Input · Capture What Was Said · Sort the Feedback
Announce Company Newsref/mkt/announce-company-news · 17 activities
Confirm the Facts
Build Annual Marketing Planref/mkt/annual-marketing-plan · 16 activities
Gather the Outside Evidence
Submit Award Entryref/mkt/award-entry · 16 activities
Brief the Entry · Gather the Evidence
Measure Brand Healthref/mkt/brand-health · 23 activities
Set the Competitor Set
Develop Brand Identityref/mkt/brand-identity · 16 activities
Brief the Makers · Try the Directions on Outsiders · Clear the Candidate Marks
Define Brand Positioningref/mkt/brand-positioning · 16 activities
Gather the Evidence · Test the Positions against the Evidence · Try the Positions on Outsiders · Record the Proof Behind the Promise
Define Brand Voice and Messagingref/mkt/brand-voice · 19 activities
Gather How the Audience Talks · Brief the Makers · Put a Source Under Every Message · Try the Messages on Buyers
Brief Executive Leadershipref/mkt/brief-executive-leadership · 20 activities
Gather the Outside Picture · Answer What Was Left Open
Brief Industry Analystref/mkt/brief-industry-analyst · 17 activities
Read Where the Analyst Stands · Brief the Makers · Gather the Proof · File What the Cycle Requires · Answer What Was Left Open
Develop Buyer Personaref/mkt/buyer-persona · 20 activities
Gather What Is Already Known · Name the Others in the Decision
Launch Channel Programref/mkt/channel-program · 17 activities
Draw up the Candidate List · Assess the Applicants
Refresh Competitive Battlecardref/mkt/competitive-battlecard · 16 activities
Confirm the Move · Gather the Proof
Manage Crisis Communicationref/mkt/crisis-communication · 16 activities
Confirm the Facts · Update the Response
Produce Customer Case Studyref/mkt/customer-case-study · 21 activities
Brief the Story · Verify the Customer's Results · Interview the Customer · Check the Facts
Recruit Customer Referenceref/mkt/customer-reference · 15 activities
Verify the Customer's Results
Conduct Customer Researchref/mkt/customer-research · 20 activities
Check What Is Already Known · Brief the Study
Solicit Customer Reviewsref/mkt/customer-reviews · 16 activities
Read the Site Rules · Check the Ask against the Rules
Develop Marketing Strategyref/mkt/develop-marketing-strategy · 17 activities
Map the Market and Its Segments · Read What the Rivals Are Doing · Hear from Buyers and the Field · Draft the Strategic Options
Engage Marketing Agencyref/mkt/engage-marketing-agency · 16 activities
Build the Candidate List · Check the References
Define Ideal Customer Profileref/mkt/ideal-customer-profile · 17 activities
Gather the Outside Evidence · Collect the First-Hand Accounts · Draft the Candidate Profiles · Size Each Candidate Market · Clear the Data and the Targeting
Run Influencer Campaignref/mkt/influencer-campaign · 16 activities
Read the Disclosure Rules · Draw up the Candidate List
Publish Landing Pageref/mkt/landing-page · 15 activities
Brief the Makers · Produce the Material
Maintain Lead Scoring Modelref/mkt/lead-scoring-model · 18 activities
Hear from the People Who Work the Leads · Gather the Candidate Signals · Clear the New Signals
Produce Long-Form Contentref/mkt/long-form-content · 18 activities
Brief the Piece · Gather the Evidence · Check the Facts
Map Buyer Journeyref/mkt/map-buyer-journey · 19 activities
Collect the First-Hand Accounts · Draft the Stages · Collect the Questions
Develop Media Planref/mkt/media-plan · 14 activities
Settle the Audience to Reach · Clear the Targeting and the Data · Gather the Channel Evidence
Name Product or Companyref/mkt/name-product · 16 activities
Read the Naming Landscape · Check the Name in Every Market
Pitch Earned Mediaref/mkt/pitch-earned-media · 15 activities
Gather the Proof · Answer What Reporters Ask
Develop Product Positioningref/mkt/product-positioning · 17 activities
Gather the Market Evidence · Interview the Makers · Name the Competing Choices · Test the Positions against the Evidence · Try the Positions on Outsiders · Record the Proof Behind Each Claim
Conduct Quarterly Business Reviewref/mkt/quarterly-business-review · 16 activities
Read the Outside Conditions
Refresh Published Contentref/mkt/refresh-content · 22 activities
Check Whether the Facts Still Hold
Produce Sales Enablement Kitref/mkt/sales-enablement-kit · 16 activities
Hear the Field · Gather the Proof · Settle the Answers · Write the Objection Answers
Segment the Marketref/mkt/segment-the-market · 18 activities
Set the Market Boundary · Gather the Outside Evidence · Choose the Dividing Traits · Size Each Segment · Clear the Data and the Traits
Select Marketing Technologyref/mkt/select-marketing-technology · 21 activities
Brief the Selection · Search the Market
Size Market Opportunityref/mkt/size-market-opportunity · 16 activities
Draw the Market Boundary · Gather the Outside Evidence · Count the Buyers · Check the Method · Clear the Sources
Secure Speaking Engagementref/mkt/speaking-engagement · 16 activities
Take in the Call · Shape the Talk
Host User Conferenceref/mkt/user-conference · 17 activities
Capture the Sessions
Update Website Contentref/mkt/website-content-update · 12 activities
Write the Change
Explore an Allianceref/prt/explore-an-alliance · 16 activities
Scan the Field · Read the Candidates · Test the Thesis with Customers
Find a Partnerref/prt/find-a-partner · 16 activities
Read Each Candidate · Score the Candidates
Plan the Integrationref/prt/plan-the-integration · 16 activities
Define the Joint Offer
Qualify a Partnerref/prt/qualify-a-partner · 17 activities
Collect What the Candidate Claims · Check the Delivery Record · Check the People and the Skills
Run Alliance Diligenceref/prt/run-alliance-diligence · 17 activities
Ask Their Customers · Check the People and the Roadmap
Choose a Toolref/rev/choose-a-tool · 18 activities
Brief the Evaluation · Search the Market
Answer an Inbound Inquiryref/sls/answer-an-inbound-inquiry · 14 activities
Read the Company
Book the Meetingref/sls/book-the-meeting · 16 activities
Read What They Asked For · Brief the Attendees
Build a Prospect Listref/sls/build-a-prospect-list · 14 activities
Read Each Account · Find the People
Map the People at an Accountref/sls/map-the-account-people · 14 activities
Find the People We Do Not Hold · Read the Reporting Lines
Provide a Referenceref/sls/provide-a-reference · 15 activities
Check the Account Is Healthy
Qualify an Opportunityref/sls/qualify-an-opportunity · 16 activities
Read the Company · Ask About the Alternatives
Record the Requirementsref/sls/record-the-requirements · 14 activities
Check the Hard Constraints
Research an Accountref/sls/research-an-account · 15 activities
Read What the Account Publishes · Read What Others Say · Work out What the Account Wants · Map What the Account Already Owns · Work out Where the Money Goes
Return a Lead to Nurtureref/sls/return-a-lead-to-nurture · 13 activities
Look Again on the Date
Review the Account Plansref/sls/review-the-account-plans · 14 activities
Test the Assumptions Again
Run a Discovery Callref/sls/run-a-discovery-call · 14 activities
Read the Account First
Run an Outbound Sequenceref/sls/run-an-outbound-sequence · 17 activities
Write the Touches
Shape the Solutionref/sls/shape-the-solution · 15 activities
Read What Was Shaped Before
Work a Referralref/sls/work-a-referral · 14 activities
Read the Person and the Account
Write an Account Planref/sls/write-an-account-plan · 16 activities
Test Each Opportunity Against the Read · Name the Risks and What Would Kill It
The records it leaves
What it writes down
A source line for every fact: what was read, where it lives, the date it was read, and the part of it the fact came from. Every number with the query or the report it came from, so somebody can pull it again and see whether the answer still holds. Interview notes attributed to the person who said it, marked with what that person agreed could be quoted.
Where it stops
What it will not do
Does not write the piece and does not decide what the piece argues. It supplies what is true, and the writer and the editor decide what to make of it. Does not judge whether the piece holds together, which is the editor agent. Does not report on how the department's own work performed, which is the analytics agent reading the organization's own numbers. Does not work out what people are searching for, which is the search-optimizer agent; this agent is after what is true, and search demand is a separate question. Does not add anything to the claims register, because that register changes only through its own process, as versioned amendments.
These limits are written into the job on purpose, so that everyone adopting the process knows which decisions stay with a person.
Agents built from this plugin
Who has built one, and how far each one got
Nobody has built one yet. The catalog says so rather than leaving the section off, because an empty list is a fact about the document.
declare it
implements: researcher v1
One line in your agent's manifest. The catalog checks it against the records your runs actually leave.
A guess, not a claim
The closest things in the catalog, by description
Nobody above has claimed any of these. This is the nearest match by wording between the job written above and what publishers wrote about their own listings, closest first, and wording is not evidence: some of these will be wrong, and a job with nothing suitable still gets whatever was nearest. The publishers have never heard of this abstract agent and have promised nothing about it. What a claim looks like is in the table above, and it is signed.
Might do the job
Things that could be the worker: an agent, a packaged product, a plugin.
- The Website Specification — A2A agent Agent · specification.website Read-only A2A agent that answers natural-language questions about The Website Specification and returns matching topics with status, canonical URL,…
Might be reached for
Not workers. These are capability that whatever does the job would use, which is a different relationship and kept in its own column for that reason.
- Tru8 Evidence Research MCP server · samyatessmith.github.io · hosted · run it yourself · mirrored from the MCP registry Source-traced evidence research for AI agents. We organise the evidence; you decide.
- Secant Agent Research Pack MCP server · jnilrac.github.io · hosted · mirrored from the MCP registry Paid MCP web research for agents: search, extraction, citations, and x402 payment discovery.
- research MCP server · ilo415.github.io · run it yourself · mirrored from the MCP registry AI research for agents. Company intel, competitor analysis, web scraping, topic dives. Pay via MPP.