agentleFS
Sign inStart free
dayvisonassisdayvisonassis/sdd-skills/CLAUDE.md

sdd-skills

CLAUDE.md3 starsChanged 32 days agoMITView on GitHub

A public package of Claude Code skills for spec-driven development. The skills live in skills/<name>/; docs/ holds the guide and the rationale and is not installed with them. Read docs/ARQUITETURA_DAS_SKILLS.md. It is the single source for how the skills call each other, the signals and files they exchange, where each shared definition lives, which files read which, and what to touch for each kind of change. Do not re-derive that from the SKILL.md files. - Skills are generic. No path,…

The file

We split this CLAUDE.md into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    Read docs/ARQUITETURA_DAS_SKILLS.md.

    line 8
  2. Distinctive:

    Update the architecture doc in the same commit as the change it describes.

    line 14

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md 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
CLAUDE.md

sdd-skills

A public package of Claude Code skills for spec-driven development. The skills live in skills/<name>/; docs/ holds the guide and the rationale and is not installed with them.

Before creating or changing a skill

Read docs/ARQUITETURA_DAS_SKILLS.md. It is the single source for how the skills call each other, the signals and files they exchange, where each shared definition lives, which files read which, and what to touch for each kind of change. Do not re-derive that from the SKILL.md files.

  • A SKILL.md is what runs. When it and the architecture doc disagree, the doc is wrong: fix it.
  • Update the architecture doc in the same commit as the change it describes.
  • Work in progress and its status: docs/PLANO_TESTES_MULTILINGUAGEM.md.

Rules of this repository

  • Skills are generic. No path, runner, mocking rule, data policy or name of a particular project goes into a skill; project facts are read from the project's GATES.md.
  • SKILL.md and references/ are written in English; docs/ in Portuguese.
  • A concept more than one skill uses has one home; the others point to it.
  • A skill is validated by running it in a fresh context, one subagent at a time, with each result saved to disk before the next starts.
  • coupling-map is the only skill with executable code: node --test "skills/**/test/*.test.mjs".

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.

Check your setup, free