byflorianbruniaux· 106 skills
Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when onboarding to a project with existing agents, after adding new agents to a fleet, or when an orchestrator consistently selects the wrong agent.
$npx -y skills add florianbruniaux/claude-code-plugins --skill eval-agentsInstalls into the current project.
Run `npx skills use "https://github.com/florianbruniaux/claude-code-plugins" --skill "florianbruniaux/claude-code-plugins/eval-agents"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/florianbruniaux/claude-code-plugins" that are relevant to the current task. Run `npx skills add "https://github.com/florianbruniaux/claude-code-plugins"` and select the relevant skills, then follow their instructions.