Loading...
Loading...
Found 5 Skills
Grades a repo's agent skills by scoring agent conversations against efficiency and code-quality rubrics, then drafts concrete skill edits and a shareable report. Use when the user wants their agent setup graded from real conversation history, or asks which of their installed skills are actually working.
L3 Worker. Analyzes single pattern implementation, calculates 4 scores (compliance, completeness, quality, implementation), identifies gaps and issues. Usually invoked by ln-640, can also analyze a specific pattern on user request.
Audits architectural patterns against best practices (MCP Ref, Context7, WebSearch). Maintains patterns catalog, calculates 4 scores, creates refactor Stories via ln-220. Use when user asks to: (1) Check architecture health, (2) Audit patterns before refactoring, (3) Find undocumented patterns in codebase.
Use when reviewing or scoring AI-generated business/application code quality in any language, especially when a numeric score, risk level, or must-fix checklist is requested, or when C++ code must comply with OpenHarmony C++ and security standards
Review git diffs, staged changes, and GitHub PRs. Change-focused analysis across seven pillars (Security, Performance, Architecture, Error Handling, Testing, Maintainability, Paranoia) with numeric scoring 1-10. Supports GitHub PR review, staged changes, and arbitrary diffs. Use when: reviewing a PR, reviewing staged changes, reviewing a diff, pre-commit review. Triggers: review PR, review my changes, review the diff, review staged, review-pr, check my changes.