specdriven-skills
CLAUDE.md1 starsChanged 5 months agoMITView on GitHub
A Claude Code skill suite for spec-driven development. Each skill lives in skills/<skill-name>/SKILL.md. There are six skills: spec:core, spec:bootstrap, spec:maintain, spec:capture, spec:infer, spec:validate. Use superpowers:writing-skills for every addition or modification. The full RED-GREEN-REFACTOR cycle is mandatory: 1. RED — write a pressure scenario and run it WITHOUT the skill. Document exact agent failures and rationalizations verbatim. 2. GREEN — write the skill addressing those specific failures. Run the same scenario WITH the skill. Verify the agent complies. 3. REFACTOR —…
In this repository6 other files it gives its agents.
- spec-bootstrapSkill
- spec-captureSkill
- spec-coreSkill
- spec-inferSkill
- spec-maintainSkill
- spec-validateSkill
The file
We split this CLAUDE.md into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 12
Use superpowers:writing-skills for every addition or modification.
≈ “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.
Files
specdriven-skills — Contributor Guidelines
What this repo is
A Claude Code skill suite for spec-driven development. Each skill lives in
skills/<skill-name>/SKILL.md. There are six skills: spec:core,
spec:bootstrap, spec:maintain, spec:capture, spec:infer,
spec:validate.
Adding or modifying skills
Use superpowers:writing-skills for every addition or modification. The
full RED-GREEN-REFACTOR cycle is mandatory:
- RED — write a pressure scenario and run it WITHOUT the skill. Document exact agent failures and rationalizations verbatim.
- GREEN — write the skill addressing those specific failures. Run the same scenario WITH the skill. Verify the agent complies.
- REFACTOR — run at least one harder scenario (loophole pressure). Close any new rationalizations. Re-verify.
No skill without a failing test first. This applies to new skills and to edits of existing skills. No exceptions.
Before committing
Show every new or modified skill to the user for review before committing. One skill per commit.
What not to commit
Any files generated during testing (e.g. spec files created in /tmp).
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
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.