market-map
Skill2 starsChanged 56 days agoMITView on GitHub
Cartographer — chooses which slice of the market to work, writes down how to recognise a buyer in it, and turns that into Pastel ICP definitions and agents. Use for "who should we target", a new market or segment, a brief made only of a website, an empty lead list, or when what-works says the aim is off.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- corebits-io/deal-origination-playbooktheir own version, first seen Oct 13, 2026
- saberapp/skillstheir own version, first seen May 5, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- saberapp/skills★ 4same name
- corebits-io/deal-origination-playbook★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository20 other files it gives its agents.
- AGENTS.mdAGENTS.md
- buying-committeeSkill
- call-readySkill
- campaign-launchSkill
- command-centerSkill
- competitor-watchSkill
- fit-checkSkill
- human-voiceSkill
- intent-radarSkill
- message-writerSkill
- morning-briefSkill
- nudgeSkill
- outbound-briefSkill
- post-studioSkill
- priority-rankSkill
- reach-checkSkill
- reply-deskSkill
- social-warmupSkill
- what-worksSkill
- why-nowSkill
The file
Files
Market map — Cartographer
House rules: ../command-center/shared/house-rules.md · Pastel tools: ../command-center/shared/pastel-tools.md
Pastel's agents only bring back what they're told to watch. A market map is that instruction: which accounts, which people, which moments, which sources.
Steps
- See what exists.
outbound-brief.md,pastel_get_workspace_context,pastel_list_icp_definitions,pastel_list_agents(include_stats=true), pluspastel_aggregate_leadsbyindustryand bycompany_sizeto see where leads already cluster. Read the latestwhat-worksreport if there is one. - Draw up to three segments, each written as one sentence a salesperson could repeat: "Series A–B SaaS in France, 20–150 people, selling to mid-market." Name the most promising one first and say why.
- For each segment, three recognisers:
- the account — sector, headcount, country, how they make money;
- the person — the role that feels the pain, and whether they can sign;
- the moment — what they do in public right before they buy (ask their network for a tool, react to a competitor's launch, post about the problem, open a role in the team we'd equip).
- Exclusions: the off-limits list from the brief, plus any segment
what-worksshows produced no hot replies over at least 50 people. - Compare with Pastel: which segments already have an agent, which agents produce leads (stats), which drift outside the map.
- Write the Pastel changes —
create_icp_definition,update_icp_definition,create_agent,update_agent— each with its exact params and a one-line reason. After approval, request them and confirm withpastel_list_agents.
Output
# Market map — [date]
Segment 1 (start here): [one sentence]
Account:
Person:
Moment:
Segment 2 / 3: …
Exclusions:
Pastel changes: action · params · reason
First batch: how many leads, which segment, which moment
Open questions:Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

