generate-agent
Skill1 starsChanged 4 months agoNo licenceView on GitHub
Generates and modifies optimized Claude Code agents (subagent .md files) through a strict TDD pipeline — deep need investigation via AskUserQuestion, official-docs grounding, invocation evals written before the agent, structural validation. Use when the user asks to create a new agent or subagent, fix an existing agent's description or delegation routing, tighten an agent's tool scope or model choice, or backfill invocation evals for an existing agent. Do NOT use for authoring skills (use `generate-skill`), for designing multi-component agentic architectures (use `generate-workflow`), for invoking an existing agent on a task (use the Agent tool directly), or for hooks and settings changes (use `update-config`).
In this repository10 other files it gives its agents.
- audit-my-designSkill
- deep-testSkill
- diagnoseSkill
- generate-skillSkill
- generate-workflowSkill
- grillingSkill
- grill-with-docsSkill
- improve-codebase-architectureSkill
- markdown-styleSkill
- ultrabrainSkill
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.