Agent skills

Code Review & Quality skills

Read straight from the source repositories, not from submitted listings. Every skill shows what it does, what is inside, where it came from — and whether attention around its source is actually growing.

Toolclaude-code 29,140codex 4,755cursor 3,111copilot 976windsurf 55cline 34
CategoryWorkflow & Productivity 4,979AI & Agents 3,037Data & Analytics 2,345Code Review & Quality 1,376Backend & API 1,244Security 1,194Design & Presentation 1,154Documentation 965Content & Marketing 916Testing & QA 777DevOps & Cloud 576Databases 550Frontend 469Business & Finance 328Media & Video 257Other 9,833
2,936 found
1,0091,056 · page 22 / 62
openai-agentsComplete skill for building AI applications with OpenAI Agents SDK (JavaScript/TypeScript), covering text agents, realtime voice…majiayu000openai-agentsOpenAI Agents SDK for JavaScript/TypeScript (text + voice agents). Use for multi-agent workflows, tools, guardrails, or…majiayu000openai-audioProduce and understand audio with OpenAI request-based audio APIs and audio-capable chat models, including text-to-speech…calesthioopenapi-swaggerExpert skill for OpenAPI/Swagger specification analysis, validation, and documentation generation. Parse and validate specs…a5c-aiwritesopenpitrixKubeSphere OpenPitrix application management Skill. Use when users ask about KubeSphere App Store, OpenPitrix, Helm/YAML…kubesphereOpposing Counsel ReviewAct as experienced opposing counsel to attack, undermine, and expose weaknesses in a legal argument, submission, witness…lawve-aioptimistic-reviewIdentify content strengths and opportunities for expansion. Suggests new topics and connections.majiayu000optionality-reviewReview code, architecture, plans, or decisions through the lens of strategic optionality. Assesses reversibility, resilience, and…majiayu000optionality-reviewEvaluate design decisions for flexibility and reversibilitymajiayu000oracle-codexThis skill should be used when the user asks to "use Codex", "ask Codex", "consult Codex", "Codex review", "use GPT for…majiayu000oracle-codexThis skill should be used when the user asks to "use Codex", "ask Codex", "consult Codex", "use GPT for planning", "ask GPT to…majiayu000oracle-geminiThis skill should be used when the user asks to "use Gemini", "ask Gemini", "consult Gemini", "Gemini review", "use Gemini for…majiayu000oraclecloud-debug-bundleCollect OCI instance diagnostics \u2014 serial console, cloud-init logs,\ \ metadata, and VCN flow logs \u2014 into a single…jeremylongshorewritesorchestrated-executionExecute work units through the rigorous 4-phase Metaswarm cycle (Implement -> Validate -> Adversarial Review -> Commit) with…a5c-aiwritesouter-reviewCommission and process external AI analysis to reduce blind spots. Manual invocation only.majiayu000overviewDisplay comprehensive project status combining git state, framework analysis, active work, and code quality metrics.majiayu000p-imageGenerate images with Pruna P-Image models via inference.sh CLI. Models: P-Image, P-Image-LoRA, P-Image-Edit, P-Image-Edit-LoRA.…majiayu000p-videoGenerate videos with Pruna P-Video and WAN models via inference.sh CLI. Models: P-Video, WAN-T2V, WAN-I2V. Capabilities…majiayu000paper-referee-reviseRevise an academic paper based on journal referee reports. Reads referee comments from review report or annotated manuscript…brycewang-stanfordwritespaper-reviewReview academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline. Supports PDF files and LaTeX…agentscope-aiparallel-debuggingDebug complex issues using competing hypotheses with parallel investigation, evidence collection, and root cause arbitration. Use…wshobsonpatent-reviewGet an external patent examiner review of a patent application. Use when user says \"专利审查\", \"patent review\", \"审查意见\"…majiayu000writespatent-reviewGet an external patent examiner review of a patent application. Use when user says \"专利审查\", \"patent review\", \"审查意见\"…majiayu000writespatternsCommon agent patterns and templates for Claude Code. Use when implementing agents to follow proven patterns for proxy mode…majiayu000paw-review-baselineAnalyzes the codebase at the PR's base commit to establish baseline understanding for review comparison.majiayu000paw-review-correlationSynthesizes findings across multiple PRs to identify cross-repository dependencies, interface mismatches, and coordination gaps.majiayu000paw-review-understandingAnalyzes PR changes to create ReviewContext.md and DerivedSpec.md artifacts. Handles both initial analysis and resumption after…majiayu000peer-reviewSystematic peer review toolkit. Evaluate methodology, statistics, design, reproducibility, ethics, figure integrity, reporting…majiayu000writesperformance-reviewWrite structured, balanced performance reviews from bullet-point inputs. Use when asked to write a performance review…mohitagw15856permission-managerManage opencode permissions: review always-allow lists, suggest safe read-only commands, configure permission patternssickn33pessimistic-reviewCritically analyze content for logical gaps, unsupported claims, and potential counterarguments. Does not modify content.majiayu000phaser-coreSet up and debug a Phaser 3 game: the Game config, the Scene lifecycle (init/preload/create/update), the asset loader, cameras…gamedev-skillsphoto-content-recognition-curation-expertExpert in photo content recognition, intelligent curation, and quality filtering. Specializes in face/animal/place recognition…majiayu000writesphoto-content-recognition-curation-expertExpert in photo content recognition, intelligent curation, and quality filtering. Specializes in face/animal/place recognition…majiayu000writesphx-codex-loopFix Elixir/Phoenix code until Codex CLI review comes back clean — bounded review, fix, verify loop before opening a PR. Use when…oliver-kriskaphx-compoundCapture solved problems as searchable solution docs. Use after fixing bugs, when "that worked", or after successful…oliver-kriskaphx-triageTriage review findings interactively — approve, skip, or prioritize each issue. Use after /skill:phx-review to filter findings…oliver-kriskaplan-review-gateAdversarial plan review by 3 independent reviewers (Feasibility, Completeness, Scope & Alignment) before presenting to user.a5c-aiwritespositioning-icpWhen the user wants to define their ideal customer profile, position an AI product, build messaging architecture, or validate…tech-leads-clubPostmortem AnalysisA postmortem (also called incident review or retrospective) is a structured process for analyzing incidents to understand what…majiayu000pptx-quality-gatesUse when validating or repairing an editable PPTX deck for geometry, accessibility, native editability, source lineage, and OOXML…wshobsonppw:reviewer-simulationSimulate peer review of academic papers with structured feedback. Produces bilingual review report with scoring and actionable…majiayu000pr-feedback-classifierFetches and classifies PR review feedback with context isolation. Returns structured JSON with thread IDs for deterministic…majiayu000pr-reportReview a pull request or contribution deeply, explain it tutorial-style for a maintainer, and produce a polished report artifact…majiayu000pr-review-analysisAnalyze PR review comments from a GitHub PR URL. Fetch review comments, verify each finding against the actual codebase, assess…majiayu000pr-shepherdingMonitor PR lifecycle from creation through merge including CI monitoring, review comment handling, thread resolution, and merge…a5c-aiwritespreprocess-debugDebug preprocessing pipeline failures. Guides through reading checkpoint files, checking step artifacts, interpreting QC metrics…majiayu000principal-investigatorDirect research projects by gathering team feedback and delegating implementation tasks. Writes publication-quality scientific…majiayu000writes
← Prev22 / 62Next →
How the catalog works
What is an agent skill?

A folder with a SKILL.md inside — instructions, and often scripts and assets, that an AI agent loads when the task matches. Claude Code, Codex, Cursor and Copilot all read the same format, so one skill usually works across them.

Where does this catalog come from?

We read 660 source repositories straight from their file trees rather than from submitted listings — what you see is what is actually published. 98 repositories were rejected because they advertise skills but contain none: link lists, not folders.

Why is there no install counter?

Because install counts live in the registry that serves `npx skills add`, and that is not ours — publishing a number we cannot verify would be worse than showing none. Instead we show where a skill comes from and whether attention around its source is actually growing, measured from our own weekly snapshots.

Do you deduplicate?

Yes, and it matters more than expected. Aggregator repositories republish the same skill in several places — one source carried 6,317 SKILL.md files for 2,001 actual skills. We collapse by folder name and keep the canonical copy, so the catalog counts things, not copies.

Keep going