agentleFS
link7373link7373/agentic-pmo/.claude/skills/run-discovery/SKILL.md

run-discovery

Skill1 starsChanged 3 months agoMITView on GitHub

Plan and synthesize product discovery — frame hypotheses, design customer research/interviews, build personas and Jobs-To-Be-Done, and validate problems before building. Use to de-risk an idea or validate a problem/solution. Dispatches the discovery-researcher.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before committing build effort to a new idea, feature, or initiative.

    line 9

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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

/run-discovery — Validate before building

When to use

Before committing build effort to a new idea, feature, or initiative; to validate a problem/solution or understand users.

Dispatches

discovery-researcher (lead). Hand validated learnings to product-manager for PRD/prioritization.

Inputs

knowledge/product-context.md (target customer, problem), knowledge/roadmap.md.

Steps

  1. Identify the riskiest assumption (value / usability / feasibility / viability); attack it first.
  2. Frame falsifiable hypotheses with pre-stated success thresholds.
  3. Design the cheapest test that yields a real signal (interview guide, prototype test, fake-door, data).
  4. Synthesize into jobs/outcomes, personas, and an opportunity view — not feature lists.
  5. State validation strength honestly and recommend persevere / iterate / pivot.

Methods

knowledge/methods/discovery-and-validation.md, knowledge/methods/lean-product-process.md.

Output

A discovery artifact at knowledge/discovery/YYYY-MM-DD-<topic>.md — research plan, synthesized findings, personas (from templates/persona.md), validated learnings. Graduate validated learnings into knowledge/product-context.md: that file holds the conclusion, knowledge/discovery/ holds the evidence. Log validation decisions to knowledge/decision-log.md. Follow standards/document-standards.md.


Created by Colin Beck<br> LinkedIn: https://www.linkedin.com/in/beckcolin/<br> GitHub: https://github.com/link7373

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.