agentleFS
elvismuslielvismusli/business-validator/skills/market-research/SKILL.md

market-research

Skill1 starsChanged 9 months agoMITView on GitHub

Use after idea-intake to research market size, trends, and dynamics for a business idea using web search — requires run_id from idea-intake

113 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-outreach

    Draft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications for fundraising. Use when the user wants outreach to angels, VCs, strategic investors, or accelerators and needs concise, personalized, investor-facing messaging.

    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

  • tpavanipradeepSkill

    nextjs-turbopack

    Next.js 16+ and Turbopack — incremental bundling, FS caching, dev speed, and when to use Turbopack vs webpack.

    Also in 14 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

  • +1 more from Infopibe

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 99 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Read docs/business-briefs/<run_id>.md and extract:

    line 53
  2. Very specific:

    Use WebSearch with queries like:

    line 61
  3. Very specific:

    Ensure the output directory exists: mkdir -p docs/reports/<run_id>

    line 82
  4. Distinctive:

    Every numeric claim MUST have a source

    line 122
  5. Distinctive:

    Use recent data (within last 2 years when possible)

    line 123
  6. Distinctive:

    If data is scarce, state this explicitly rather than guessing

    line 125

“Common” is measured: kept by at least 6 in 10 of the 99 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

Market Research

Overview

Research the market for a business idea using WebSearch and WebFetch. Produce a structured market analysis section with TAM/SAM/SOM estimates, trends, and sources.

<HARD-GATE> You MUST have the run_id before starting. Read the business brief at `docs/business-briefs/<run_id>.md` using the exact run_id provided. Do NOT glob for files or use "most recent". If you do not have a run_id, ask the user or invoke business-validator:idea-intake first. </HARD-GATE>

Inputs

  • run_id: Provided by idea-intake or the user (format: YYYY-MM-DD-<slug>-<hhmm>)
  • Business brief: docs/business-briefs/<run_id>.md

Output

  • File: docs/reports/<run_id>/01-market-research.md

Process

digraph market_research {
    "Verify run_id exists" [shape=box];
    "Read business brief" [shape=box];
    "Search market size data" [shape=box];
    "Search industry trends" [shape=box];
    "Search regulatory landscape" [shape=box];
    "Search technology trends" [shape=box];
    "Synthesize findings" [shape=box];
    "Write 01-market-research.md" [shape=box, style=filled, fillcolor="#e8f5e9"];

    "Verify run_id exists" -> "Read business brief";
    "Read business brief" -> "Search market size data";
    "Read business brief" -> "Search industry trends";
    "Read business brief" -> "Search regulatory landscape";
    "Read business brief" -> "Search technology trends";
    "Search market size data" -> "Synthesize findings";
    "Search industry trends" -> "Synthesize findings";
    "Search regulatory landscape" -> "Synthesize findings";
    "Search technology trends" -> "Synthesize findings";
    "Synthesize findings" -> "Write 01-market-research.md";
}

Step 1: Read the Business Brief

Read docs/business-briefs/<run_id>.md and extract:

  • Industry/niche
  • Geographic focus
  • Target audience segment
  • Business model type

Step 2: Research Market Size (TAM/SAM/SOM)

Use WebSearch with queries like:

  • "[industry] market size [year]"
  • "[industry] market forecast [geographic focus]"
  • "[niche] total addressable market"

Calculate or find:

  • TAM (Total Addressable Market): The entire market for the product category
  • SAM (Serviceable Addressable Market): The segment reachable with the business model
  • SOM (Serviceable Obtainable Market): Realistic first-year capture

Step 3: Research Industry Trends

Search for:

  • Growth rate (CAGR) and direction
  • Key market drivers
  • Emerging technologies in the space
  • Consumer/buyer behavior shifts
  • Regulatory changes or risks

Step 4: Write Output

Ensure the output directory exists: mkdir -p docs/reports/<run_id>

Save to docs/reports/<run_id>/01-market-research.md:

## Market Research

**Run ID:** <run_id>

### Market Size

| Metric | Value | Source |
|--------|-------|--------|
| TAM | $X.XB | [source] |
| SAM | $X.XB | [source] |
| SOM (Year 1) | $X.XM | Estimated |

### Market Trends

| Trend | Impact | Direction |
|-------|--------|-----------|
| [trend 1] | [description] | Growing/Declining |

### Growth Dynamics
- CAGR: X.X% (YYYY-YYYY)
- Key drivers: [list]

### Regulatory Environment
[Summary of relevant regulations, if any]

### Technology Trends
[Relevant technology shifts]

### Sources
- [Source 1](url)
- [Source 2](url)

Quality Standards

  • Every numeric claim MUST have a source
  • Use recent data (within last 2 years when possible)
  • Clearly distinguish estimates from cited data
  • If data is scarce, state this explicitly rather than guessing
  • Include at least 3 different sources

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.