Evaluates a single agent .md across 7 dimensions including activation precision and trigger coverage. Use when asked to 'review agent' or dispatched by /review-claude-config. Do NOT use for skills or rules — use /review-skill or /review-rule.
This listing is imported from SkillsMP metadata and should be treated as untrusted until upstream source review is completed.
Install skill "review-agent" with this command: npx skills add Nosmoht/skillsmp-nosmoht-nosmoht-review-agent
This source entry does not include full markdown content beyond metadata.
This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.
Related by shared tags or category signals.
Evaluates MCP server configuration (.mcp.json manifest, transport, servers-block) across 4 dimensions (Completeness, Goal Alignment, Safety, Metadata). Use when asked to 'review mcp', 'review mcp server', or 'review .mcp.json'. Do NOT use for skills, agents, rules, hooks, or settings.json.
Evaluates a single rule .md (always-load imperatives, injection-prone prose) across 3 dimensions (Clarity, Completeness, Goal Alignment). Use when asked to 'review rule' or dispatched by /review-claude-config. Do NOT use for skills or agents — use /review-skill or /review-agent.
Evaluates a single SKILL.md across 7 quality dimensions and produces an optimization certificate. Use when asked to 'review skill' or dispatched by /review-claude-config. Do NOT use for agents or rules — use /review-agent or /review-rule. Does NOT apply findings — use /apply-skill-review-findings to implement recommendations.
Estimates token cost of a repo's Claude Code configuration (CLAUDE.md, rules, skills, MCP servers, agents) and recommends optimizations. Use when context feels cramped at session start, after adding MCP servers or skills, or before optimizing a Claude Code setup. Do NOT use to audit source code tokens — use /audit-repo for that.