Loading...
Loading...
Found 6 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.
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
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.
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.
Teaches beginners and vibe coders how their own project works in plain, simple English. Explains the architecture, what each file and folder does, how the frontend, backend, database and API connect, how a click becomes a request, and what the runtime is (for example Node.js). Gives a transparent code quality score out of 100, security red flags, a prioritized fix list with ready-to-paste prompts, big-tech best practices, and feature ideas, all as structured cards and tables. Use when the user asks to explain, understand, tour, map, review, score, rate or improve their codebase, asks what a file does or what happens when a button is clicked, asks if their app is safe, or mentions vibe teacher.