agentleFS
Sign inStart free
alabenkhlifaalabenkhlifa/Specs-Driven-Development-Skills-Templates/CLAUDE.md

Specs-Driven-Development-Skills-Templates

CLAUDE.md0 starsChanged 4 months agoMITView on GitHub

This repository publishes reusable Spec-Driven Development templates and agent workflows. The four supported workflows are add-spec, update-spec, implement-spec, and review-spec. Validate every changed canonical skill with the active skill-authoring environment. Do not commit while validation is failing.

The file

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

9 rules. About 0 are common, 4 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Treat skills/ as the canonical workflow source.

    line 7
  2. Very specific:

    Keep each commands/<name>.md file identical to its matching skills/<name>/SKILL.md.

    line 8
  3. Very specific:

    Keep .claude/skills/ linked to the canonical skill folders.

    line 9
  4. Very specific:

    Keep .claude/commands/ synchronized with the four command contracts.

    line 10
  5. Very specific:

    Keep skills/add-spec/assets/ identical to templates/feature-spec/.

    line 11
  6. Distinctive:

    Keep AGENTS.md and CLAUDE.md identical.

    line 12
  7. Distinctive:

    Do not add private URLs, credentials, customer names, or internal project details.

    line 21
  8. Distinctive:

    Do not weaken scope, task-size, ownership, traceability, proof, or verification gates to make a workflow appear complete.

    line 22
  9. Distinctive:

    Keep the example small and anonymized.

    line 23

≈ “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

Repository Instructions

This repository publishes reusable Spec-Driven Development templates and agent workflows.

Canonical Resources

  • Treat skills/ as the canonical workflow source.
  • Keep each commands/<name>.md file identical to its matching skills/<name>/SKILL.md.
  • Keep .claude/skills/ linked to the canonical skill folders.
  • Keep .claude/commands/ synchronized with the four command contracts.
  • Keep skills/add-spec/assets/ identical to templates/feature-spec/.
  • Keep AGENTS.md and CLAUDE.md identical.
  • Keep templates/AGENTS.md and templates/CLAUDE.md identical.

The four supported workflows are add-spec, update-spec, implement-spec, and review-spec.

Change Boundaries

  • Inspect the working tree before editing and preserve unrelated changes.
  • Preserve tool-neutral workflow rules unless a file is explicitly an adapter.
  • Do not add private URLs, credentials, customer names, or internal project details.
  • Do not weaken scope, task-size, ownership, traceability, proof, or verification gates to make a workflow appear complete.
  • Keep the example small and anonymized.

Verification

Run:

python3 scripts/test_validate_spec.py
python3 scripts/test_run_proof.py
python3 scripts/test_capability_index.py
python3 scripts/test_split_progress_log.py
python3 scripts/split_progress_log.py --check examples
python3 scripts/validate_spec.py --all examples
python3 scripts/validate_repo.py
git diff --check

Validate every changed canonical skill with the active skill-authoring environment. Do not commit while validation is failing.

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