Loading...
Loading...
Found 1,170 Skills
Run Claude Code review against the current branch and report only the review comments that are still valid for the current codebase, without applying fixes.
Run Codex code review against the current branch, fix only the review comments that are still valid for the current codebase, and leave invalid comments unchanged.
Use when designing, planning, implementing, or reviewing any non-trivial change — enforces small, focused modules so any change fits in context without compaction
Use after the final approved execution scope is complete, or when the user asks whether a feature is done, ready to ship, safe to merge, or needs a quality check. Runs the post-execution quality gate: specialist review, artifact verification, and human UAT against locked decisions and the final exit state. Use for prompts like "review this feature", "is this done?", "can we ship this?", "double-check the implementation", or "run UAT".
Review a PR and submit suggestions as comments, along with an optional approval/request for changes.
Vercel Agent guidance — AI-powered code review, incident investigation, and SDK installation. Automates PR analysis and anomaly debugging. Use when configuring or understanding Vercel's AI development tools.
Use this skill during code reviews to proactively investigate the codebase for duplicated functionality, reinvented wheels, or failure to reuse existing project best practices and shared utilities.
Review football data code and visualisations for correctness. Use after building a chart, data pipeline, or analysis. Dispatches specialised reviewers for data correctness, chart conventions, visual inspection, and interactive edge cases.
Explain code functionality in detail.
Comprehensive React/TypeScript frontend code review with optional parallel agents
Analyze code for patterns, complexity, dependencies, and quality. Use when: code review, refactoring, understanding codebases.
Fetch up-to-date third-party API/SDK docs via chub before writing or reviewing integration code — so method names, payload fields, and auth headers are always sourced from live docs, not stale training data. Don't use for first-party project docs, generic programming questions, or when the user only wants a conceptual answer rather than integration code.