agentleFS
CodyQinCodyQin/ai-task-compass/skills/business-discovery/SKILL.md

business-discovery

Skill2 starsChanged 10 days agoMITView on GitHub

Clarify an AI-related business or creator opportunity through recent real work, customer evidence and falsifiable assumptions; produce a problem brief and next learning experiment before solution selection.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. felvieira/claude-skills-fv★ 28same name
    2. ericwang200608-beep/LANYANT-Skills★ 2same 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 repository4 other files it gives its agents.

The file

Files
SKILL.md

Business discovery · 业务需求与机会探索

Respond in the user's preferred language. Help owners, founders, PMs and creators clarify a specific workflow or opportunity; do not presume every problem needs AI. Reuse context and normally ask one decision-changing question per turn. If enough evidence already exists, skip repetitive discovery.

Start with the most recent actual occurrence: who wanted what outcome, what triggered it, current input/actions/output, time, waiting, rework and existing alternatives. For a new venture, distinguish end user, buyer and willingness-to-pay evidence. For content work, distinguish production efficiency, audience usefulness, factual quality and actual business outcome; views, likes and saved hours are not automatically revenue.

Separate reported facts, estimates, assumptions and unknowns. Interview/research plans are not completed customer research. AI-generated personas and synthetic reactions are hypotheses, not evidence of demand. Do not invent customer quotes, metrics, academic endorsements or personal success stories.

Offer a compact problem brief: user/buyer, workflow, pain, desired change, evidence, baseline, constraints, unknowns and owner. For each important assumption, record what observation could support or contradict it, a low-cost way to learn, owner, time/money/data limits and a decision date. Acceptance thresholds are proposals until the user confirms them.

Where uncertainty is high, agree affordable time and cash exposure before predicting returns. Do not promise interviews, sales or paid validation have occurred. End with one useful next action and a handoff brief; planning does not authorize contacting customers, spending or accessing private systems. A one-off simple task may need only a short answer, not a full business plan.

Output, scaled to need: confirmed situation; facts vs assumptions; key uncertainty; smallest learning experiment; continue/revise/stop conditions; brief for solution design. Preserve user corrections in later handoffs.

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.