All categories
Code Review & Quality
Code review, refactoring, debugging, maintainability, and engineering quality
- 15,938
- 665
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse code review & quality skills
Showing 13,873–13,896 of 15,938 skills
- Code Review ExcellenceThis skill should be used when the user asks to review a diff or pull request, write review comments, audit code quality, establish review standards, or improve how a team performs code review.Votes: 0GitHub stars: 3,639
- AdrEvaluate whether session changes warrant an Architecture Decision Record, and create one if justified. Use when significant architectural decisions have been made, new patterns introduced, or after major refactors.Votes: 0GitHub stars: 45
- ShipUse when the user says "ship this" or explicitly asks to review, finish, merge, and push implementation that is ready to deliver.Votes: 0GitHub stars: 13
- Review PrReview someone else's GitHub PR as a Staff Engineer and post a high-precision review — mechanical grounding (CI, local verification), focused design + security passes, calibrated severity labels, inline comments with suggestion blocks. Use when asked to review a PR, give feedback on a PR, or act as a code reviewer.Votes: 0GitHub stars: 13
- Writing SkillsUse when creating new skills, editing existing skills, or verifying skills work before deploymentVotes: 0GitHub stars: 25
- Review ReportUse when you want the rich human-facing code review experience — a walkthrough with prose explanation plus mermaid architecture/sequence diagrams plus an HTML report of verified findings, not just terminal findings. Triggers include "review report", "코드리뷰 리포트", "리뷰 HTML", "다이어그램 리뷰", "리뷰 다이어그램", "walkthrough 리뷰", "PR 리뷰 리포트".Votes: 0GitHub stars: 25
- Pin Wrap UpUse at the end of a work session to review the WHOLE session and record entities worth pinning. This is the manual, deliberate complete-sweep review — NOT an automated nudge. Triggers on "wrap up", "wrap-up", "session wrap", "end of session", "what should I pin".Votes: 0GitHub stars: 25
- Project DevelopmentIdentify tasks suited to LLM processing, design pipelines, and iterate with agent-assisted development.Votes: 0GitHub stars: 7
- Github Pr ReviewReview open pull requests in a GitHub repository, checking code changes and leaving review comments.Votes: 0GitHub stars: 7
- EvaluationEvaluate agent systems with multi-dimensional rubrics accounting for non-determinism and multiple valid paths.Votes: 0GitHub stars: 7
- Code SimplifierSimplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.Votes: 0GitHub stars: 7
- Anti Render智能识别任何领域的"理想承诺 vs 残酷现实"对比需求，生成理想化渲染、现实主义真实面貌或对比图的三种视觉风格转换Votes: 0GitHub stars: 7
- zodchiyАрхитектурный аудит по трём осям: намерение, структура, поведение git-истории. Находка допускается, только когда измерена её цена. Вызывать при «разбери архитектуру», «где техдолг», «что рефакторить», «оцени кодовую базу», «изучи чужой репо», «стоит ли переписывать», перед крупным рефакторингом и при планировании миграции. Сюда же — жалобы на цену изменения, в которых слова «архитектура» нет: боимся трогать модуль, страшно менять, почему тут больно менять, одна правка задевает соседние файлы,...Votes: 0GitHub stars: 23
- Workflow Checkpoint RefactorMulti-phase refactoring with checkpoint files that survive context limits. Use when refactoring spans 10+ files, needs phased rollout, or risks running out of context mid-session.Votes: 0GitHub stars: 58
- Design Legacy SeamsGet legacy code under test before changing it — find seams, write characterization tests. Use when changing untested code, breaking dependencies, or taming legacy.Votes: 0GitHub stars: 58
- Vulture Dead CodeVulture and deadcode tools for detecting unused Python code (functions, classes, imports). Use when cleaning up codebases or removing dead code. Triggers vulture, deadcode.Votes: 0GitHub stars: 58
- Ruff LintingPython linting with ruff. Fast linting, rule selection, auto-fixing, and config. Use when checking Python code quality, enforcing standards, or finding bugs.Votes: 0GitHub stars: 58
- Python DevelopmentCore Python development idioms and language features (3.10+). Use when mentioning Python, type hints, or async. For scripts see uv-run; for project setup see uv-project-management.Votes: 0GitHub stars: 58
- Plugin AuthoringAdd, modify, or delete a skill or plugin in this repo — frontmatter shape, the seven metadata files a plugin touches, and the create/delete checklists. Use when creating a new skill or plugin, removing one, or asking which files a plugin change must update.Votes: 0GitHub stars: 58
- Model SelectionStrategic Codex model selection for .NET development workflows. Guides when to use Opus 4.6 (deep reasoning, architecture, ambiguous problems) vs Sonnet 4.6 (throughput, large context, routine implementation) vs Haiku 4.5 (fast, cheap subagent tasks). Covers model switching workflows, subagent model assignment, and cost-effective task routing. Load this skill when choosing models for tasks, optimizing costs, working with subagents, or when the user mentions "model", "Opus", "Sonnet", "Haiku",...Votes: 0GitHub stars: 229
- Ce Compound RefreshRefresh the repo's captured learnings against the current codebase. Use when auditing stale, overlapping, superseded, or drifted learnings; avoid general refactor, debugging, or code review unless the learnings store is explicit.Votes: 0GitHub stars: 25,340
- Ce BrainstormExplore vague or ambitious ideas into a right-sized requirements-only unified plan. Use when the user wants to brainstorm or scope what to build. Not for executing already-specified work. Use ce-pov for a verdict on adopting a named external technology.Votes: 0GitHub stars: 25,340
- Tests Guard Intentional WorkaroundsBefore removing code that looks redundant, wasteful, or "wrong" based on log observations or code review instinct, grep the test suite for tests whose names describe the exact behavior you're about to remove. A test whose title literally describes the "weird" thing (e.g. "calls play() even when player reports playing", "retries even when first call succeeded", "skips cache even when fresh") is a load-bearing workaround, and the production log you're reacting to is probably the workaround work...Votes: 0GitHub stars: 265
- Stale Cache External Service RecoveryHandle stale local cache when external service loses/resets data. Use when: (1) Token refresh fails with "not found" or 404 errors, (2) Cached identifiers (pubkeys, user IDs) don't exist on external service anymore, (3) External service was reset/migrated but local cache has old values. Pattern: detect 404 specifically, delete stale cache entry, recreate on external service, update cache with new values. Complements local-cache-idempotency-fallback skill.Votes: 0GitHub stars: 265