All categories
Code Review & Quality
Code review, refactoring, debugging, maintainability, and engineering quality
- 15,943
- 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 2,137–2,160 of 15,943 skills
- Simplify CodeReview a diff for clarity and safe simplifications, then optionally apply low-risk fixes.Votes: 0GitHub stars: 6
- Posix Shell ProExpert in strict POSIX sh scripting for maximum portability across Unix-like systems. Specializes in shell scripts that run on any POSIX-compliant shell (dash, ash, sh, bash --posix).Votes: 0GitHub stars: 6
- Clean CodeThis skill embodies the principles of \"Clean Code\" by Robert C. Martin (Uncle Bob). Use it to transform \"code that works\" into \"code that is clean.\"Votes: 0GitHub stars: 6
- Tech Debt Skill> Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection. A Claude Code skill that runs a structured, three-phase tech debt audit across an entire codebase and writes `TECH_DEBT_AUDIT.md` — a persistent, file-cited, severity-ranked artifact you can commit and track over time.Votes: 0GitHub stars: 81
- Omnivoice TtsExpert skill for OmniVoice, a massively multilingual zero-shot TTS model supporting 600+ languages with voice cloning and voice design capabilities.Votes: 0GitHub stars: 81
- Oh My Claudecode Orchestration> Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection. `oh-my-claudecode` (OMC) is a Teams-first multi-agent orchestration layer for Claude Code. It coordinates specialized AI agents in parallel, routes work intelligently by complexity, and runs persistent verify/fix loops — so you describe what to build and it handles the rest. ---Votes: 0GitHub stars: 81
- Llm Architecture Gallery> Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection.Votes: 0GitHub stars: 81
- Khazix Skills Agent> Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection.Votes: 0GitHub stars: 81
- Gstack Workflow AssistantTeam of specialist AI workflows for Claude Code with CEO review, engineering planning, code review, shipping, QA testing, and browser automationVotes: 0GitHub stars: 81
- Evanflow Tdd Loop> Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection. EvanFlow is a TDD-driven iterative feedback loop for software development with Claude Code. 16 cohesive skills + 2 custom subagents walk an idea from brainstorm → plan → execute → iterate, with real checkpoints where you stay in control. The agent never auto-commits, never auto-stages, never proposes a PR without your explicit direction. ``` brainstorm → plan → execute (vertical-slice TDD per task) → iterate → STOP └─ sequent...Votes: 0GitHub stars: 81
- Ponytail ReviewCode review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. One line per finding: location, what to cut, what replaces it. Use when the user says "review for over-engineering", "what can we delete", "is this over-engineered", "simplify review", or invokes /ponytail-review. Complements correctness-focused review, this one only hunts complexity.Votes: 0GitHub stars: 23
- Analyze ProjectForensic root cause analyzer for Antigravity sessions. Classifies scope deltas, rework patterns, root causes, hotspots, and auto-improves prompts/health.Votes: 0GitHub stars: 8
- GhGitHub operations using gh CLI for any repository. Use when the user asks to "create pr", "create pull request", "view pr", "check ci", "pr status", "list prs", "create issue", "view issue", "search code", or any other GitHub-related operations. Handles PR creation with proper base branch detection, template support, and project conventions.Votes: 0GitHub stars: 7
- ReviewPre-landing code review of the git diff; critical issues block the PR. Use before a PR or when asked to review changes.Votes: 0GitHub stars: 86
- RetroRun a project or session retrospective and capture reusable lessons.Votes: 0GitHub stars: 86
- Domain ModelingSharpen a project's domain terms and maintain CONTEXT.md as its glossary. Triggers: \"what should we call this\", \"domain model\".Votes: 0GitHub stars: 86
- ArchitectFind shallow modules and propose deepening refactors, ranked with file refs; never edits code. Use when code is hard to change or planning a refactor.Votes: 0GitHub stars: 86
- AdrCapture qualifying architecture decisions as ADRs in the right HQ or repo location.Votes: 0GitHub stars: 86
- Ajustar Meu RoteamentoAtualizo as regras que decidem como os tickets recebidos são classificados e para onde vão. Mudo o que conta como bug versus pedido de funcionalidade, redireciono bugs para um novo sistema de rastreamento, atualizo quem aprova reembolsos, adiciono uma nova categoria, ou ajusto o roteamento VIP. Toda triagem depois da atualização segue automaticamente as novas regras.Votes: 0GitHub stars: 117
- Typst Test SlideThis skill should be used when the user asks to 'test a slide', 'isolate a slide', 'debug a slide', 'preview a single slide', 'test this slide', 'render one slide', or when you need to visually verify a single Typst slide from a presentation in isolation. Provides the exact file setup pattern to avoid access-denied and import errors.Votes: 0GitHub stars: 22
- Cite CheckALWAYS use when a draft's citations need checking against what the sources actually say — 'check citations', 'check my cites', 'verify cites', 'cite-check', 'run citation review', 'are my citations grounded', 'does this source actually support that claim', 'does source X support claim Y', 'what does source X say about Y', 'did I cite that right', 'make sure the cites hold up before I send this'. Use proactively before a draft goes out. NOT for Bluebook formatting (use bluebook / bluebook-audi...Votes: 0GitHub stars: 22
- OrchestrateRun a piece of work as an ORCHESTRATOR of sub-agents instead of doing it all inline: decompose the task, dispatch scoped sub-agents — each on the cheapest model that can do its piece well — then verify and synthesize their results. The work to perform is whatever is passed as the skill's argument (`/orchestrate <work>`). Also use whenever the user asks to "orchestrate", "coordinate agents", "fan out", "parallelize", or "delegate" a task, or hands over a large multi-part job — a repo-wide audi...Votes: 0GitHub stars: 2
- Dash DiscoverDiagnoses latent architectural modernization opportunities across Dart and Flutter packages (language idioms, testing hygiene, CLI patterns, doc rot) and prescribes matching specialized skills.Votes: 0GitHub stars: 147
- Dart Multiline StringsGuidelines and best practices for refactoring consecutive prints, single-line string concatenations, and complex output blocks into triple-quoted multi-line string literals (''' or """) in Dart.Votes: 0GitHub stars: 147