eval-agents

SKILLWorkflowcommunity
v0.0.0FlorianBruniauxMITUpdated 4mo agoSource →

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 orche

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
37Repo stars
1Clients
1Formats
4mo agoLast update
Skill
AuthorFlorianBruniaux
Version0.0.0
LicenseMIT
CategoryWorkflow
Formatsskill.md
PromptNot published
Compatibility
Claude✓ Supported
Cursor—
Copilot—
ChatGPT—
Gemini—
About

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,

Keywords
skillclaude

No dependency coverage

This entry publishes no npm package, so Forge has no dependency tree for it. That is a gap in coverage — not a statement that it has no dependencies.