improving-skill-definition
Skill3 starsChanged 12 days agoNo licenceView on GitHub
Adversarially audits and improves existing first-party agent-skill packages through approval-gated edits, focused subagent reports, baseline diff validation, and outcome-dependent evidence preservation. Use when improving, hardening, or repairing a skill definition, subagent architecture, flow diagram, package hygiene, or prompt sufficiency.
In this repository59 other files it gives its agents.
- AGENTS.mdAGENTS.md
- evals/AGENTS.mdAGENTS.md
- api-security-best-practicesSkill
- architecture-patternsSkill
- clean-codeSkill
- code-review-excellenceSkill
- committing-scoped-changesSkill
- council-of-advisorsSkill
- diagnosing-root-causesSkill
- domain-modelingSkill
- executing-plansSkill
- generate-flow-diagramSkill
- improving-test-suitesSkill
- interview-meSkill
- planning-codebase-restructuringSkill
- pr-creatorSkill
- prompt-structurerSkill
- receiving-code-reviewSkill
- recency-guardSkill
- refactoring-codeSkill
- reporting-skill-issuesSkill
- responding-to-pr-review-commentsSkill
- review-pull-requestSkill
- rewriting-code-strictlySkill
- stop-slopSkill
- subagent-driven-developmentSkill
- test-driven-developmentSkill
- unslopSkill
- validate-implementation-planSkill
- vitestSkill
- workflow-skill-architectSkill
- writing-plansSkill
- analyzing-recent-project-stateSkill
- clarifying-assumptionsSkill
- committing-scoped-changesSkill
- council-of-advisorsSkill
- creating-work-item-childrenSkill
- diagnosing-root-causesSkill
- executing-work-item-taskSkill
- fetching-work-itemSkill
- generate-flow-diagramSkill
- generate-handoff-documentSkill
- improving-test-suitesSkill
- orchestrating-workflowSkill
- planning-codebase-restructuringSkill
- planning-task-executionSkill
- planning-work-item-tasksSkill
- pr-creatorSkill
- prompt-structurerSkill
- recency-guardSkill
- refactoring-codeSkill
- refine-taskSkill
- reporting-skill-issuesSkill
- responding-to-pr-review-commentsSkill
- review-pull-requestSkill
- review-software-engineer-cvSkill
- rewriting-code-strictlySkill
- validate-implementation-planSkill
- workflow-skill-architectSkill
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.