architecture-committee
Skill7 starsChanged 49 days agoNo licenceView on GitHub
Convene a debiased multi-persona committee to vet an architecture / design decision for a feature, spec, or PRD — distinct personas independently propose, steelman their pick AND its opposite, cross-examine across capped debate rounds, then converge on the approach that fits THIS spec rather than the model's default priors. Invoke when asked to "form/convene a committee", weigh architecture or technology options, or pressure-test a design choice before committing. Skip when you are auditing or detecting problems in an existing instruction file / config (use audit-instruction-file or audit-lethal-trifecta), auditing the coordination mechanics of a multi-agent system already built and running (use audit-multi-agent-orchestration), compressing a prompt (use compress-prompt), or when the decision is trivial / already made and only execution remains.
In this repository24 other files it gives its agents.
- AGENTS.mdAGENTS.md
- audit-geo-contentSkill
- audit-github-actions-securitySkill
- audit-harness-safetySkill
- audit-instruction-fileSkill
- audit-lethal-trifectaSkill
- audit-mcp-serverSkill
- audit-memory-retrieval-integritySkill
- audit-multi-agent-orchestrationSkill
- audit-observability-setupSkill
- audit-prompt-cache-hygieneSkill
- audit-prompt-hook-placementSkill
- audit-secret-exposureSkill
- audit-self-improvement-protocolSkill
- audit-skill-qualitySkill
- audit-supply-chain-sinksSkill
- audit-tool-definitionSkill
- audit-verification-gatesSkill
- compress-promptSkill
- conflicting-instruction-detectorSkill
- review-codeSkill
- write-skillSkill
- write-testsSkill
- write-tool-descriptionSkill
The file
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.