research-market
Skill1 starsChanged 3 months agoMITView on GitHub
Research who the customer is, the smallest viable market to win first, customer language, competitors, and where the audience lives online. Run after setup and before offer/positioning work; rerun when entering a new segment.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- athina-ai/goose-skillstheir own version, first seen Nov 9, 2026
- gooseworks-ai/goose-skillstheir own version, first seen Nov 1, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- athina-ai/goose-skills★ 1.3ksame name
- gooseworks-ai/goose-skills★ 1.3ksame 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 repository22 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- build-funnelSkill
- close-dealSkill
- connect-toolsSkill
- create-contentSkill
- define-positioningSkill
- design-offerSkill
- experimentSkill
- grow-referralsSkill
- grow-seoSkill
- health-checkSkill
- launch-campaignSkill
- launch-productSkill
- manage-pipelineSkill
- measureSkill
- plan-strategySkill
- review-monthlySkill
- run-adsSkill
- run-outboundSkill
- run-partnershipsSkill
- setup-teamSkill
- tune-revopsSkill
The file
Files
/research-market — Know the Buyer Before Anything Else
Inputs: knowledge/business-context.md, open questions from setup.
Agents: market-researcher leads.
Method: knowledge/methods/positioning-and-audience.md (audience sections), knowledge/methods/digital-channel-strategy.md (channel research).
Steps
- Frame the questions. From business context, list what must be learned: who exactly buys, what words they use, what they compare us to, where they gather, what triggers purchase. Confirm scope with the operator only if the product itself is ambiguous.
- Draft candidate segments. 2–4 hypotheses for the smallest viable market — narrow enough that members recognize each other. For each: who, the burning problem, why we could be their obvious choice.
- Mine real language. For the strongest segments, collect verbatim customer phrases from reviews of competing products, community threads, marketplace Q&As, and forums. Tag phrases as problem / desired outcome / objection. This corpus feeds all future copy — collect generously.
- Map competitors. Direct, indirect, and "do nothing / DIY". For each: positioning, price, visible strengths, complaint patterns (their bad reviews are our opportunity list). Identify credible open space.
- Locate the audience. Rank channels by reachability for this budget: search terms and volumes where discoverable, marketplaces and their search behavior, communities, platforms. B2B: add ICP detail (industry/size/role/trigger events) and ethical list-building sources. B2C: add identity dimension of the purchase.
- Recommend the beachhead. One segment to win first, with rationale and the riskiest untested assumption. Present to the operator with the evidence trail; capture their business-knowledge reactions — they know things research can't find.
- Record. Profiles via
templates/audience-profile.md.
Before you start
- Required inputs:
knowledge/business-context.mdat statusseededor better — ifstub, offer to run/setup-teamfirst. - Scan
knowledge/decision-log.mdfor tagsaudience,channel— honor prior segment decisions or explicitly supersede them with new evidence. - Gate check: none — research is internal. Web research uses read-only tools (WebSearch, Bright Data
search/scrape, Similarweb if authorized).
If things go wrong
- Web research tools unavailable/unauthorized → use WebSearch/WebFetch; note in the output which findings are thinner as a result.
- Too little public signal to validate any segment → say so honestly; recommend the cheapest real-world test (5 conversations, a smoke-test post) instead of inventing confidence.
- Operator unavailable for the beachhead confirmation → record the recommendation in
knowledge/pending.mdand stop before writing the segment decision.
Outputs
knowledge/audience-profiles.md (beachhead + secondary segments), knowledge/research/competitors.md, knowledge/research/customer-language.md, raw notes in knowledge/research/. Seed knowledge/competitors.md (the living intel file) from the competitor map. Close with the report per templates/skill-report.md.
Writeback
Above files; segment decision (tag: audience) to knowledge/decision-log.md; unresolved unknowns flagged for /experiment or early sales conversations.
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.

