agentleFS
dnlboxdnlbox/ai-protocol/.agents/skills/concept-intake/SKILL.md

concept-intake

Skill18 starsChanged 3 months agoMITView on GitHub

Capture an unstructured project idea before canonical concept documents or implementation planning exist.

The file

Show its rules and text

We split this skill into the rules it gives an agent

18 rules. About 0 are common, 12 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈12

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the user wants to think aloud about a new project.

    line 8
  2. Very specific:

    Read docs/intake/concept-intake.md when it exists.

    line 12
  3. Very specific:

    Create docs/intake/concept-intake.md when it does not exist.

    line 14
  4. Distinctive:

    Ask for clarification only when competing interpretations would materially change the concept.

    line 18
  5. Distinctive:

    Keep each round focused on one topic.

    line 22
  6. Distinctive:

    Ask at most one next question.

    line 25
  7. Distinctive:

    Ask two questions only when they cannot be separated.

    line 26
  8. Distinctive:

    Avoid administering a questionnaire.

    line 27
  9. Distinctive:

    Avoid turning rough ideas into invented requirements.

    line 28
  10. Distinctive:

    Avoid choosing implementation details.

    line 29
  11. Distinctive:

    Avoid launching research without an explicit request.

    line 30
  12. Very specific:

    Keep settled choices in Decisions.

    line 35
  13. Very specific:

    Keep unresolved matters in Unknowns.

    line 36
  14. Very specific:

    Keep tangents in Parking lot.

    line 37
  15. Distinctive:

    Update the intake before replying to a substantive answer.

    line 46
  16. Distinctive:

    Avoid storing a conversation transcript.

    line 47
  17. Distinctive:

    Remove resolved unknowns before completion.

    line 58
  18. Very specific:

    Stop before editing docs/concept/.

    line 61

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Concept intake

Use this skill when the user wants to think aloud about a new project.

Start

  • Read docs/intake/concept-intake.md when it exists.
  • Resume from the recorded current focus.
  • Create docs/intake/concept-intake.md when it does not exist.
  • Set a new intake status to In progress.
  • Preserve the user's language.
  • Interpret speech-to-text errors from context.
  • Ask for clarification only when competing interpretations would materially change the concept.

Conversation

  • Keep each round focused on one topic.
  • Reflect only new or changed meaning.
  • Challenge one material weakness when useful.
  • Ask at most one next question.
  • Ask two questions only when they cannot be separated.
  • Avoid administering a questionnaire.
  • Avoid turning rough ideas into invented requirements.
  • Avoid choosing implementation details.
  • Avoid launching research without an explicit request.

Durable intake

  • Keep Working summary compact.
  • Keep settled choices in Decisions.
  • Keep unresolved matters in Unknowns.
  • Keep tangents in Parking lot.
  • Track coverage of the user.
  • Track coverage of the problem.
  • Track coverage of the intended outcome.
  • Track coverage of the primary value loop.
  • Track coverage of material scope boundaries.
  • Track coverage of material risks.
  • Track unknowns that must reach concept shaping.
  • Record one Current focus.
  • Update the intake before replying to a substantive answer.
  • Avoid storing a conversation transcript.

Completion

  • Recommend completion when the intake covers every required area.
  • Recommend completion after two rounds add no new product pillar.
  • Allow research questions to carry into concept shaping.
  • Complete when the user accepts the recommendation.
  • Complete when the user says the intake is sufficient.
  • Complete when the user asks to begin concept shaping.
  • Reconcile contradictions before completion.
  • Remove resolved unknowns before completion.
  • Set the status to Ready for concept shaping.
  • Return a one-screen readiness summary.
  • Stop before editing docs/concept/.

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.