Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 86 696 files from 2 113 authors, of which 68 413 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguous, or only exist as a vague idea.
Prepares production launches. Use when preparing to deploy to production. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.
Read public PANews website pages as Markdown. Use for homepage, article-page, and column-page reads.
> Create and manage articles on the PANews platform. All operations require a valid user session. upload images, search tags, apply for a column, polish or review article content.
> Entry point for reading PANews cryptocurrency / blockchain news, market narratives, and Polymarket smart money leaderboards. reading specific articles, browsing columns / series / community topics, industry events & conferences, event calendar, platform hot searches and editorial picks, latest smart money boards, board highlights, and board comparisons.
深度解析 AI 论文，生成可直接发布的专业阅读笔记
Real-time web research using Google Search via Google's Antigravity (`agy`) CLI — the replacement for the deprecated `gemini-cli`. Trigger when user needs current information ("search with agy", "search with Google Antigravity", "find current info about X with agy", "what's the latest on Y"), library/API research, security vulnerability lookups, or comparisons requiring recent data.
Bump a plugin version in marketplace.json using semantic versioning. Use when user asks to "bump version", "increment version", "release new version", or after making changes that warrant a version update.
Get Google Antigravity's (`agy`) code review of git changes after Claude makes edits. Trigger when user wants a second opinion on code changes ("have agy review my changes", "get code review from Google Antigravity", "review this diff with agy"), or as a final check before committing. Replaces the deprecated gemini-cli diff-review workflow.
Get Google Antigravity's (`agy`) review of Claude's implementation plans. Trigger when user wants a second opinion on a plan ("have agy review this plan", "get a second opinion from Google Antigravity", "critique this plan with agy"), or after Claude creates a plan file that needs validation before implementation. Replaces the deprecated gemini-cli plan-review workflow.
Display plugin versions from marketplace.json. Use when user asks to "audit versions", "show plugin versions", "list marketplace versions", or wants to see the current state of plugin versioning.
>- This skill should be used when reviewing API designs, auditing REST or gRPC endpoints, designing backend APIs, evaluating BFF architecture, or discussing API best practices. "REST API audit", "gRPC API review", "PATCH vs PUT", "etag", "idempotency", "pagination design", "API error handling", "backward compatibility", "BFF architecture", "resource-oriented design", "TOCTOU", "race condition", "optimistic concurrency", "field mask", "long-running operation", "custom method", "soft delete", "API naming conventions", "declarative-friendly"
Bump a plugin version in its plugin.json file using semantic versioning. Use when user asks to "bump plugin version", "increment plugin version", or after making changes to a plugin that warrant a version update.
Deep architectural analysis of the current workspace using Google Antigravity (`agy`). Trigger when the user needs an architecture overview ("analyze this codebase with agy", "map dependencies with Google Antigravity"), is onboarding to unfamiliar code, exploring legacy systems, or hunting technical debt. Replaces the deprecated gemini-cli `codebase_investigator` workflow.
Deduplicate and consolidate CLAUDE.md memory files. Trigger when user says "condense my CLAUDE.md files", "deduplicate CLAUDE.md", "clean up my memory files", or "consolidate my instructions". Removes redundancy within files and across the file hierarchy.
Analyze recent conversation to identify improvements for CLAUDE.md memory files. Trigger when user says "reflect on this session", "reflect on this conversation", "reflect on this code", or "improve CLAUDE.md by reflecting on this session". The verb "reflect" combined with a session/conversation/code subject is the key trigger.
Deep architectural analysis using Gemini's codebase_investigator tool. Trigger when user needs architecture overview ("analyze this codebase", "map dependencies"), onboarding to unfamiliar code, understanding legacy systems, or identifying technical debt.
Codebase analysis via the Codex MCP server with a read-only sandbox. Trigger when user needs architecture overview ("analyze this codebase with Codex", "have Codex map dependencies"), onboarding to unfamiliar code, understanding legacy systems, or identifying technical debt.
Get Codex's code review of git changes via the Codex MCP server. Trigger when user wants a second opinion on code changes ("have Codex review my changes", "get code review from Codex", "review this diff with Codex"), or as a final check before committing.
Get Gemini's review of Claude's implementation plans. Trigger when user wants a second opinion on a plan ("have Gemini review this plan", "get second opinion", "critique this plan"), or after Claude creates a plan file that needs validation before implementation.
Get Codex's review of an implementation plan before the user starts building — trigger when they want Codex (or a named GPT model like gpt-5.6) to review, critique, or pressure-test a plan. Applies to any plan-shaped artifact — a plan file, plan-mode plan, a migration/rearchitecture/integration/checkout write-up, or a doc describing how they intend to do something (pasted, at a repo path, or just described). Fire on any second-opinion phrasing — "poke holes in it", "sanity-check my plan", "run this past Codex", "get Codex's take", "flag the biggest risks", "look this over before I start", "did I miss edge cases, testing, or a rollback path?". The point is catching gaps, risks, missing steps, and better alternatives ahead of implementation. Do NOT use for reviewing already-written code or diffs (that's diff-review), mapping an existing codebase's architecture (codebase-analysis), or web/research questions.
Get Gemini's code review of git changes after Claude makes edits. Trigger when user wants a second opinion on code changes ("have Gemini review my changes", "get code review from Gemini", "review this diff"), or as a final check before committing.
GitHub issue management using GitHub CLI. Trigger when user wants to list issues ("show open issues"), view issue details ("view issue 456"), create issues ("create an issue", "file a bug"), or edit/close issues ("close issue", "add label to issue").
Pull request operations using GitHub CLI. Trigger when user wants to list PRs ("show open PRs"), view PR details ("view PR 123"), create PRs ("create a pull request"), review/merge PRs ("merge PR", "approve PR"), or view PR diffs ("show PR diff", "what files changed in PR").
Stacked pull requests with the GitHub CLI `gh stack` extension. Trigger whenever the user wants to split a large branch or change into a chain of dependent PRs ("stack this into smaller PRs", "split this into a stack", "create a stacked PR", "break this feature into reviewable layers"), or manage an existing stack ("add a layer on top", "rebase my stack", "sync the stack after the bottom PR merged", "merge the stack"). Use this instead of the `pr` skill whenever the work involves more than one dependent PR or any `gh stack` command; use `pr` for single, standalone pull requests.
GitHub Actions workflow management using GitHub CLI. Trigger when user wants to check CI status ("check CI", "is the build passing"), view workflow runs ("show recent runs", "view action logs"), watch running workflows ("watch CI"), or rerun failed workflows ("rerun the build").
Real-time web research using Gemini's Google Search. Trigger when user needs current information ("search with Gemini", "find current info about X", "what's the latest on Y"), library/API research, security vulnerability lookups, or comparisons requiring recent data.
Fetch raw file content from GitHub URLs. Trigger when user shares a GitHub file link (https://github.com/user/repo/blob/main/file.go) and wants to view the source code. Avoids HTML/JS clutter from WebFetch.
Repository information using GitHub CLI. Trigger when user wants to view repository details ("show repo info", "what's this repo about"), list repositories ("list my repos", "show repos for user"), or check repository metadata ("stars", "languages", "topics").
Review Go code for adherence to Go Style Guide. Use when the user requests a code review of completed work, pull requests, or feature branches in Go projects. Focuses on critical bugs, race conditions, and important maintainability issues. Trigger phrases include "review this Go code", "check against style guide", "review my PR", or "review the work done so far".
This skill should be used when the user asks "what does this mediainfo mean", "explain this video format", "what is BT.709", "what is H.264", "container vs codec", "why is this 10bit", "what does limited range mean", or wants educational explanations of video technical concepts.
This skill should be used when the user asks "check frame rate", "is this CFR or VFR", "video has duplicate frames", "video stutters", "frame rate issues", "why does video judder", or wants to analyze frame rate characteristics and detect timing problems.
This skill should be used when the user asks "what's wrong with this video", "why does this video look bad", "detect video artifacts", "find quality issues", "video has artifacts", "identify compression artifacts", or wants to diagnose specific quality problems in a video file.
This skill should be used when the user asks "check subtitles", "audit subs", "subtitle font issues", "ASS vs SRT", "missing fonts", "subtitle timing", or wants to analyze subtitle tracks for issues like missing fonts, timing problems, or format limitations.
This skill should be used when the user asks "is this interlaced", "detect telecine", "video has combing", "should I deinterlace", "3:2 pulldown", "inverse telecine", or sees horizontal lines/combing artifacts in video and wants to understand if the content is truly interlaced or telecined.
This skill should be used when the user asks "compare these videos", "which source is better", "compare blu-ray vs web", "which release should I use", "compare video quality", or needs to evaluate multiple versions of the same content to determine which has better quality.
This skill should be used when the user asks "is this real HDR", "check HDR metadata", "fake HDR", "is this Dolby Vision legitimate", "HDR vs SDR", "check HDR peak brightness", or wants to verify whether HDR content is genuine or inverse tonemapped from SDR.
This skill should be used when the user asks to "audit this video", "analyze video quality", "check this video file", "is this video good quality", "should I reencode this", "what format is this video", or wants to understand a video file's technical properties and quality before working with it.
> This skill should be used when working with SwiftData — @Model definitions, @Query, @Relationship, ModelContext, ModelContainer, schema migration, Swift 6 concurrency, performance optimization, or "predicate problems", "background context patterns", "N+1 queries", "SwiftData vs SQLiteData vs GRDB", "CloudKit sync with SwiftData", "SwiftData migration fails", or "SwiftData migration diagnostics". Covers auditing existing code, writing new SwiftData code, migration debugging, and architecture review.
> 🔒 Security & Compliance skill suite derived from GetBindu/awesome-claude-code-and-skills. Security audits, vulnerability management, GDPR/SOC2/ISO27001 compliance and incident response. Provides 10 specialised commands for security, compliance, gdpr workflows.
Audit and optimize content for SEO, GEO (generative engine optimization), and AEO (answer engine optimization). Use when user asks to "audit SEO", "check search visibility", "optimize for AI search", "generate schema markup", "validate metadata", "extract keywords", "optimize for Perplexity/ChatGPT/Gemini", "check Open Graph tags", "submit to IndexNow", or mentions SEO, GEO, AEO, or search optimization. Do NOT use for creating new content from scratch or image optimization.
> 🤖 Data Science & AI/ML skill suite derived from alirezarezvani/claude-code-skill-factory. Data pipelines, model training, evaluation, MLOps and analytical reporting. Provides 10 specialised commands for data-science, machine-learning, analytics workflows.
Read the Convex deployment's 72h insights (read limits, OCC contention), root-cause each event in code, report evidence-backed perf/cost findings with fixes.
Add an AI agent / RAG backend (@convex-dev/agent) to the Convex app.
Add Stripe billing/payments to the Convex app via @convex-dev/stripe (checkout + webhook + gating).
Add a capability to the CURRENT Convex app — consults the served Convex capability catalog for always-current procedures (billing, crons, auth, agent, search, …); falls back to built-in hosting or @convex-dev component search. TRIGGER when the user runs /add, or asks to add hosting/publishing or any backend capability to an existing Convex app.
Set up Convex backups and run a restore DRILL that proves recovery — snapshot, restore into a throwaway preview, assert the data came back — plus a schedule matched to your RPO and a gated recovery runbook.
Preview Convex spend — rank functions by bytes/documents-read × call-volume from insights, project each cost driver's growth curve, name the cheapest fix; confirm-cost for paid actions.
Add authentication (passkeys/OAuth) to the current Convex app, including the auth.config.ts wiring.
Audit and harden Convex authorization: identity-from-arg impersonation, missing per-document ownership checks, PII-leaking public queries, and writes into containers the caller doesn't own. Deterministic scan + canonical requireIdentity/requireOwner fix + tsc verify. Use for 'secure my app' / 'audit auth' / 'who can access this data', not generic code review.
Convex backend specialist. Use this agent for any code inside a `convex/` directory — function definitions, schemas, indexes, queries, mutations, actions, HTTP endpoints, cron jobs, file storage, auth wiring, and component installation. Knows the object-form function syntax, validator patterns, resource limits, and component ecosystem that generic Claude routinely gets wrong.
Design and build reactive, type-safe, production-grade backends on Convex. Covers schema, queries/mutations/actions, indexes, auth, file storage, scheduling, real-time multiplayer, mobile backends, and LLM/agent workflows on Convex's one-platform stack.
Add recurring scheduled jobs (crons) to the Convex app.
Classify + announce the target Convex deployment before any deployment-affecting command; fresh explicit consent for prod actions; session read-only mode.
Set and wire Convex deployment env vars / secrets for the app.
Point a domain you already own at your Convex app (DNS records, custom-domain attach, auth-origin rebind).
Pull version-current Convex docs for the version this project uses — pin the installed version, fetch page-as-markdown or check node_modules types, freshness hierarchy — instead of writing a possibly-stale API from memory.
Explain an existing Convex app — data model + relationships, public vs internal functions, auth/ownership model, components, a request→data flow — read from the schema and function surface. Read-only.
Send this coding session's transcript to the Convex team for an AI post-mortem that improves the quickstart system.
Query a running Convex app's logs + health in natural language (official MCP): failures, slow/expensive functions, deploy causality — scoped, evidence-backed, with a dashboard deep link.
Claude Skills — questions
Answers built from the skills we actually parsed.