Loading...
Loading...
Found 985 Skills
Use when the user asks for a broad codebase review, substantial PR/branch review, architecture audit, tech-debt scan, cleanup assessment, structural sanity check, or design-alignment review. Default workflow: use sub-agents when available unless specifically forbidden; do not require the user to mention sub-agents, council mode, delegation, or parallel review. Focus on cruft, duplication, weak boundaries, missed reuse, lifecycle/concurrency risks, test/roadmap drift, and code aesthetics. Do not use for narrow bug fixes, ordinary small-diff reviews, frontend visual QA, repo-onboarding docs, or OpenAI Agents SDK production-readiness review. Output evidence-backed findings first, then pressure points, design alignment, open questions, and follow-through.
Walk the user through a PR as a single top-to-bottom narrative ordered by dependency/causal flow, with a heavy scrutiny pass for bugs, missing tests, scope creep, and security. Operates on a temp git worktree so it works while the main working tree is dirty. Use when the user asks to review a PR, walk through a PR, review a PR, or review one branch against another.
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Four LLM reviewers challenge changes from independent angles.
Provides comprehensive code review covering 6 focused aspects - architecture & design, code quality, security & dependencies, performance & scalability, testing coverage, and documentation & API design. Use this skill for deep analysis with actionable feedback after significant code changes.
Use this skill to run a multi-persona expert advisory review on a labelled pull request in microsoft/apm. The panel fans out to five mandatory specialists plus a test-coverage specialist (active on every PR that touches src/) plus two conditional specialists (auth, doc-writer), all running in their own agent threads, and a CEO synthesizer. The orchestrator is the sole writer to the PR: ONE recommendation comment, no verdict labels, no merge gating. The panel is advisory -- it surfaces findings, prioritizes follow-ups, and renders a ship-recommendation that the maintainer and author weigh. Activate when a non-trivial PR needs a cross-cutting recommendation (architecture, CLI logging, DevX UX, supply-chain security, growth/positioning, optionally auth, docs, and test coverage, with CEO arbitration).
Chinese Code Review Communication Reference - Script Templates, Priority Labeling (Must Fix/Suggested Change/For Reference Only), Countermeasures for Common Anti-patterns in Domestic Teams. Only invoke when the user explicitly uses /chinese-code-review, do not trigger automatically based on context.
Use when performing a standalone PR double-check in a clean context — review, fix, and post.
Single adversarial review pass over the integrated branch diff — spec-compliance, code quality, and test adequacy judged together by one fresh-context reviewer. Triggers: /review, 'review the changes', or after delegation completes. Emits one verdict (reviews.review.status). Do NOT use for plan-review (that is its own dispatched gate) or for debugging.
Implement Git hooks using Husky, pre-commit, and custom scripts. Enforce code quality, linting, and testing before commits and pushes.
You are a technical debt expert specializing in identifying, quantifying, and prioritizing technical debt in software projects. Analyze the codebase to uncover debt, assess its impact, and create acti
Unified router for 7 canonical software engineering knowledge bases. Routes queries to appropriate underlying skills: gof-patterns (23 design patterns), clrs-algorithms (40 data structures), clean-code (SOLID + practices), ddia (distributed systems), pragmatic-programmer (craftsmanship), ddd (domain modeling), sicp (CS fundamentals). Auto-activates for architecture decisions, pattern selection, algorithm choice, and system design.
Guide on React patterns, performance optimization, and code quality for Epic Stack