Agent Skills: agentsmd-optimize
Audit and organize AI coding-agent instructions, including AGENTS.md, CLAUDE.md, skills, and agent definitions. Use when the user asks to diagnose conflicting instructions, excessive approval pauses, broad skill triggers, duplicate guidance, or broken instruction references, or to clean up that instruction set. Ordinary code review, Markdown editing, or application debugging alone does not trigger this workflow. Inspection stays read-only; apply changes when authorized.
ID: majiayu000/claude-arsenal/agentsmd-optimize
28026
Install this agent skill to your local
Skill Files
The files that make up agentsmd-optimize.
More agent skills
- heterogeneous-agentUse for Claude Code/Codex external-agent adapters, IPC, event mapping, sessions, persistence and tool-call chains.
- node-redEdit, analyze, and create Node-RED flows by working with flows.json files,
- python-testsWrite regression tests for FastMCP changes using its pytest fixtures, in-memory clients, and protocol boundaries.
- nip85-trusted-assertionsThe NIP-85 trusted-assertions model in Quartz (`nip85TrustedAssertions/`) — kind 10040 trust-provider lists, kind 30382 contact cards / user assertions, 30383 event assertions, 30384 addressable assertions, 30385 external-id assertions. Use when building or parsing these events, working with the typed tags (RankTag, HopsTag, FollowerCountTag, ServiceProviderTag/ServiceType, …), wiring a consumer that resolves a 10040 provider entry to the 30382s it signs, ranking on assertion values, or touching the GrapeRank publisher, contact-card nicknames, or the trust projection of an external store.
- skillifyTurn a repeatable workflow from the current session into a reusable OMC skill draft
- interpolationProblem-solving strategies for interpolation in numerical methods