agentleFS
alsy99alsy99/agent-enterprise-os/skills/market-research/SKILL.md

market-research

Skill0 starsChanged 2 months agoMITView on GitHub

Build an ICP/competitor/opportunity research pack with dated sources and explicit unknowns. Use when researching a segment, lead company, or market before outbound. Trigger on market research, ICP, competitor, or research pack.

118 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use everything-claude-code, everything-claude-code-conventions and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • InfopibeSkill

    everything-claude-code

    Also in 9 projects that use this

  • mryeastcodeSkill

    everything-claude-code-conventions

    Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

    Also in 8 projects that use this

  • InfopibeSkill

    investor-materials

    Create and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and fundraising materials. Use when the user needs investor-facing documents, projections, use-of-funds tables, milestone plans, or materials that must stay internally consistent across multiple fundraising assets.

    Also in 22 projects that use this

  • shawnpangSkill

    competitor-monitoring

    When the user wants to set up ongoing tracking of competitor activity — pricing changes, feature launches, hiring signals, content, or public mentions. Also use when the user mentions "track competitors", "what are competitors doing", "competitor alerts", or "market watch".

    Also in 3 projects that use this

  • niloykumarbarmanSkill

    agent-sort

    Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

    Also in 7 projects that use this

  • CodeWithBehnamSkill

    dmux-workflows

    Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.

    Also in 15 projects that use this

  • +1 more from Infopibe

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 104 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read wiki/market/ if pages exist.

    line 26
  2. Very specific:

    Write or update a page under wiki/market/ (or wiki/sales/leads/<slug>.md for a single lead).

    line 27
  3. Very specific:

    Do not draft email here — hand off to sales-outbound.

    line 34
  4. Distinctive:

    Run verifier on claims (no invented TAM/quotes) and confirm the checklist is present for leads.

    line 35
  5. Very specific:

    Do not invent headcount, ARR, or shipping status to avoid Unknown.

    line 56
  6. Distinctive:

    No email, no CRM write

    line 63
  7. Very specific:

    Every number/claim sourced or marked Unknown

    line 69

“Common” is measured: kept by at least 6 in 10 of the 104 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

When to use

  • Before first-touch outbound
  • New segment or lead company needs a wiki pack

Models

  • Actor: planner (Gemini Flash — long context + browse)
  • Verifier: thinker or verifier (GLM-4.7-Flash / Groq gpt-oss — different family)
  • Resolve: ./scripts/resolve-model.sh market-research

Steps

  1. Restate the research question in one sentence.
  2. Read wiki/market/ if pages exist; note Updated: dates.
  3. Write or update a page under wiki/market/ (or wiki/sales/leads/<slug>.md for a single lead).
  4. Produce exactly:
    • ICP or account hypothesis
    • 3 evidence bullets (sourced or Unknown)
    • Competitors / alternatives (known vs unknown)
    • Opportunity one-liner + next skill (sales-outbound)
  5. If the page is a lead (wiki/sales/leads/<slug>.md): complete the Required Unknown checklist below. Every row must appear. A row’s value is either a sourced fact or the literal word Unknown. Omitting a row = incomplete — do not hand off to sales-outbound.
  6. Do not draft email here — hand off to sales-outbound.
  7. Run verifier on claims (no invented TAM/quotes) and confirm the checklist is present for leads.

Required Unknown checklist (lead pages)

Copy this block into every lead page (values filled):

## Unknown checklist

| Field | Value |
|---|---|
| Headcount / team size (ICP 1–5?) | <sourced fact or Unknown> |
| Shipping status of cited features (GA / beta / coming soon) | <sourced fact or Unknown> |
| Decision-maker path | <sourced fact or Unknown> |
| Timeline ≤90 days | <sourced fact or Unknown> |
| Willingness to talk / design-partner interest | Unknown |

Notes:

  • “Headcount” may be “appears solo (first-person site)” with a URL — still cite the source. If not evidenced, write Unknown.
  • Do not invent headcount, ARR, or shipping status to avoid Unknown.
  • Willingness… stays Unknown until a human confirms a reply or meeting.

Tools allowed

  • Browser (read-only)
  • Wiki read/write under wiki/
  • No email, no CRM write

Definition of done

  • Wiki page path recorded
  • 3 evidence bullets present
  • Every number/claim sourced or marked Unknown
  • Lead pages include the full Unknown checklist (all five rows)
  • Next step named: sales-outbound
  • Verifier pass (or human escalate)

Never do

  • Invent TAM/SAM, quotes, or pricing
  • Skip checklist rows on lead pages
  • Hand off to sales-outbound with missing checklist
  • Send outreach

Escalation

  • Conflicting sources → SOP_GAP: conflict + ask human

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.