agentleFS
rikilamadridrikilamadrid/pathfinder/skills/to-specs/SKILL.md

to-specs

Skill1 starsChanged 44 days agoMITView on GitHub

Turn approved direction into small, clear Feature specs.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. About 0 are common, 9 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the approved project context and relevant existing Features.

    line 18
  2. Very specific:

    Stop if a required human decision is still TBD.

    line 19
  3. Very specific:

    Create context/features/ if it does not exist.

    line 21
  4. Very specific:

    Create each Feature from templates/feature-spec.template.md, named NN-feature-name.md — see Naming below.

    line 22
  5. Very specific:

    Do not consult or write the ticket store.

    line 28
  6. Distinctive:

    Prefer one Feature when the work is coherent.

    line 47
  7. Distinctive:

    Prefer fewer Features and fewer artifacts.

    line 56
  8. Distinctive:

    Do not invent unresolved decisions.

    line 64
  9. Distinctive:

    Do not plan beyond the approved direction.

    line 65
  10. Distinctive:

    Do not add workflow metadata that the Feature template does not require.

    line 66
  11. Distinctive:

    Do not create tickets, tracker items, or extra planning files by default.

    line 67
  12. Distinctive:

    Do not scan unrelated repository areas.

    line 68
  13. Distinctive:

    When implementation details are unclear, inspect only enough source code to write an accurate Feature.

    line 70

≈ “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

To Specs

Turn approved direction into the minimum Feature specs needed to implement it.

Assumed role

Unless the human explicitly activated a role, assume planner for this invocation: read roles/planner.md and follow it. An explicit role overrides this default. A role narrows responsibility and never grants human authority.

Process

  1. Read the approved project context and relevant existing Features.
  2. Stop if a required human decision is still TBD.
  3. Decide whether the work is one Feature or needs a small number of Features.
  4. Create context/features/ if it does not exist.
  5. Create each Feature from templates/feature-spec.template.md, named NN-feature-name.md — see Naming below.
  6. Fill only information that materially helps implementation and review.
  7. Present the created Features and recommend which one to start first. Recommend to-tickets on that Feature as the next action: a Feature is planned work, and tickets are what a session executes.
  8. Do not consult or write the ticket store. Feature specs stay in the repository; to-tickets owns creating their executable tickets wherever the project keeps them.

Naming

A Feature spec is named NN-feature-name.md in the spec source, for example context/features/27-export-saved-searches.md.

NN is the Feature number: the next unused number in the spec source, counting every spec already there whatever its status. Numbers are never reused and never renumbered, because every ticket of that Feature carries the number in its own key — NN.TT — and renumbering would orphan all of them.

The number lives in the filename and nowhere else. The Feature template carries no number field, and nothing else in the spec records one.

Sizing

Prefer one Feature when the work is coherent.

Split only when separate outcomes:

  • can be implemented or reviewed independently
  • depend on meaningfully different context
  • have a real dependency between them
  • would make one Feature unnecessarily difficult to understand

Prefer fewer Features and fewer artifacts.

A Feature that is coherent but large is not two Features. It is one Feature that to-tickets will slice into several tickets.

Rules

  • Do not implement.
  • Do not invent unresolved decisions.
  • Do not plan beyond the approved direction.
  • Do not add workflow metadata that the Feature template does not require.
  • Do not create tickets, tracker items, or extra planning files by default.
  • Do not scan unrelated repository areas.

When implementation details are unclear, inspect only enough source code to write an accurate Feature.

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.