The catalog
608,253 rows, by stacks then stars
sidtheone/claude-skill-template/examples/analyze-architecture Skill
0★ repoDeeply analyze codebase architecture and dependencies. Use when understanding system design, finding patterns, or mapping how components interact.
rockbenben/aishort-skills/skills/deepl-translate-node Skill
0★ repoUse DeepL's neural MT API as a fallback when you are NOT confident in your own translation — proper nouns, ambiguous phrasing, domain/legal/medical terminology, idioms, low-resource languages, or any text where a mistranslation carries real cost. Also use when the user explicitly asks to "用 DeepL 翻译" / "translate with DeepL". Calls the DeepL API (Free tier by default; Pro via DEEPL_API_HOST).
idimsh/tdds-business-skills/accessibility-audit Skill
no license0★ repoAudit and fix accessibility issues following WCAG 2.2 Level AA + a11y project best practices
arendon1/agent-skills/domain/analyze-model Skill
0★ repoFetches live model data from OpenRouter and Artificial Analysis APIs, merges benchmarks with pricing, runs deep cost analysis on usage logs, exports usage from LLM surfaces (OpenCode, Pi, VS Code, etc.), analyzes subscription efficiency, and forecasts future spend with cheaper-model alternatives. Use when comparing LLM costs or quality, analyzing total API spend from usage logs, exporting agent usage for cost analysis, evaluating subscription cost efficiency, forecasting future LLM costs, finding cheaper alternatives, or when the user asks about model pricing, intelligence index, speed, or token costs across providers.
Panno-ai/skills/skills/llm-resource-usage Skill
0★ repoAnalyzes the user's LLM/AI usage across all local harnesses and coding agents (Claude Code, OpenClaw, OpenCode, Goose, Codex CLI, Gemini CLI, Cursor, Amp, etc.), then enriches that data with environmental impact (energy, CO₂, water), likely datacenter locations, and fun equivalency comparisons — and produces a visual infographic + narrative report. Use this skill whenever the user asks about: their AI usage, token consumption, LLM costs, energy footprint of AI, how much they've spent on AI, carbon footprint of their coding agent, usage stats, "how many tokens have I used", AI environmental impact, "what's my AI bill", or wants to see charts/visuals of their LLM activity. Also trigger when they ask to "track", "analyze", "visualize", or "report" on AI or token usage.
ouistitititi/work-report-skill Skill
0★AI工作报告技能 - 对话记录工作,按需生成周报月报,支持多项目管理、智能纠错、可视化建议、Markdown表格存储。极简高效,拒绝废话,让工作报告不再繁琐。AI Work Report Skill - Record work via conversation, generate weekly and monthly reports on demand. Features multi-project management, smart correction, visualization suggestions, and Markdown table storage.
wyc79/calendar-creator-skill/calendar-creator Skill
0★ repoConvert academic materials — syllabi, course schedules, academic calendar pages — into a single combined .ics calendar file the user can import into Google Calendar, Apple Calendar, or Outlook. Use this skill whenever the user wants to turn a syllabus, course schedule screenshot, screenshot of their student portal, or academic calendar into calendar events. Trigger even when the user doesn't say ".ics" explicitly — phrasings like "make a calendar from my syllabus," "turn this schedule into events," "add my classes and deadlines to my calendar," "I want my whole semester in my calendar," "parse this syllabus into events," or "build me a calendar file from my courses" should all activate this skill. Also trigger when the user uploads a syllabus PDF, course schedule image, or academic calendar URL/screenshot and asks for help organizing their semester. Also trigger when the user uploads a previously-saved courses JSON spec and asks to regenerate, edit, or update their calendar — e.g., "regenerate my calendar from this," "change the room for my Wed class then rebuild the .ics," "add another course to this spec" — the skill knows how to read its own saved spec format and skip the extraction step.
hereandnowai/agent-skills/deepagents Skill
0★ repoComprehensive guide for building Python apps with the LangChain `deepagents` library — an agent harness with built-in planning, virtual filesystem, sub-agents, human-in-the-loop, MCP integration, and pluggable backends for long-running, context-heavy tasks. Use whenever the user writes code with `deepagents`, calls `create_deep_agent` or `async_create_deep_agent`, or builds a research agent, coding agent, data-analysis agent, or multi-step LangChain/LangGraph agent that needs planning + sub-agents + virtual filesystem + context engineering. Trigger on any mention of "deepagents", "deep agent", "deep agents", "LangChain agent harness", "create_deep_agent", "agent with planning tool", "multi-agent orchestration with subagents", or when the user wants an agent that handles long-horizon tasks via context offloading, summarization, and isolation. Also use when migrating older 0.0.x code to the 0.4+ API. Prefer over generic LangChain guidance whenever `deepagents` is the framework.
congemcd/skills-collection/skills/apng-creator Skill
0★ repoCreate animated PNG/APNG files from a directory or list of PNG frame images. Use when the user wants to generate an APNG from a PNG sequence with numeric prefix or suffix frame indexes, validate frame ordering, handle missing or non-consecutive indexes, and choose a frame rate.
xuluoforcainiao/plugin-creator/plugin-creator Skill
no license0★ repoCreate, customize, or modify QoderWork expert plugins. Use when the user wants to create a new plugin, customize an existing plugin, or edit a plugin's skills/commands.
smcllns/skills/obsidian-html-docs Skill
0★ repoUse when creating .html docs intended to render inline in Obsidian with the HTML Docs plugin (github.com/smcllns/obsidian-plugin-html-docs).
rainbowgore/agent-skill-registry-builder Skill
0★Use when the user mentions registry, skill registry, agent registry, skill catalog, skill marketplace, skill hub, or MCP directory. Also triggers when the user asks about structuring, organizing, or distributing skills or agents — categories, trust tiers, install flows, governance, curation, or benchmarking against an existing registry.
NAJEMWEHBE/studio-skills/skills/live-streaming Skill
0★ repoLive streaming operations using a bonding router and SRT/RTMP relay servers. Use when configuring OBS, planning a stream, troubleshooting bitrate/jitter issues, deciding which uplink combination to use, or briefing a client on streaming constraints. Also use before any live event involving streaming setup.
Genpark accio market intelligence
Alpha-Park/genpark-accio-market-intelligence Skill
0★Proactive Market Intelligence Agent. Conducts autonomous research, competitor tracking, and trend forecasting for global markets.
The same file is in 1 other repository
bryanwhl/pokemon-champions-vgc-reg-m-a Skill
0★Research Pokemon Champions VGC Regulation M-A rules, legality, tournament results, usage trends, winning teams, and metagame developments. Use when Codex needs current Reg M-A context, allowed Pokemon/items/moves, banlists, format rules, tournament data, Limitless/LabMaus/Cut Explorer/StatCrusher/Pokedata sources, or live VGC metagame analysis.
ph3on1x/adveloop/skills/adveloop Skill
0★ repoRun a GAN-inspired adversarial development loop — the Planner drives a Generator and Evaluator in fresh cmux panes, gated by hard pass/fail per deliverable, adapted from Anthropic's harness-design guidance for long-running agentic apps. Use when the user asks to /adveloop, run an adversarial dev loop, spawn Planner-Generator-Evaluator panes, build with adversarial verification, or audit/harden existing code with a skeptical evaluator. Requires cmux and the claude-cmux-skill:cmux skill.
DetGaao/authentic-voice/.agents/skills/authentic-voice Skill
0★ repoAvoid AI-detectable writing patterns across all text output. Covers emails, docs, website copy, marketing content, and general prose. Applies anti-slop vocabulary rules, structural pattern avoidance, and context-aware tone matching. Use for any writing task or when the user asks to make text sound more human/natural.
sanjana-pier39/pier39-skills/plugins/pier39/skills/pier39-merchant Skill
0★ repoClose more sales at higher margin when a shopper engages your storefront to negotiate. Use this skill whenever a shopper — human or AI agent — is inquiring about pricing, asking about discounts, in a cart-recovery flow, comparing against a competitor, or anywhere a sale hasn't yet committed. Trigger on phrases like "is that your best price", "I saw this cheaper at X", "anything you can do on price", "what discounts are available", "can you match", "can you throw in", cart-abandonment events, unconverted live-chat sessions, or any inbound agent message about a specific SKU. Do not reflexively discount — hold the anchor, read the shopper's signals, and concede strategically in exchange for commitment, upsell, or data.
Web automation workflow discovery
xuluoforcainiao/web-automation-workflow-discovery/web-automation-workflow-discovery Skill
no license0★ repoLearn and automate human workflows on websites through browser exploration, screenshot analysis, and iterative script refinement. Use when the user needs to automate repetitive tasks on web applications, replicate human click-type-upload sequences, or build unattended browser automation for any website.
r-portas/skills/bootstrap Skill
no license0★ repoInstalls and fully integrates packages and libraries into a project — including config files, helper modules, and scaffolded templates. Use when the user asks to install, set up, configure, add, or bootstrap a specific package: drizzle, date-fns, oxlint, oxfmt or similar. Prefer this over a generic npm install whenever the package has an opinionated setup or requires boilerplate files.
Moonweave-Systems/compass-skill Skill
0★User-invoked mid-session audit skill. Detects (1) drift between current task and original session intent via transcript analysis, and (2) codebase rot — git uncommitted accumulation, test/lint state from cached artifacts, file bloat, TODO accumulation, circular dependencies, module boundary degradation. Manually triggered via `/compass` only — never auto-invoked. Use when the user types `/compass` optionally followed by a baseline intent string. Without arguments, derive baseline via cascade — most recent spec (24h), then task-init heuristic, then explicit user prompt. Never use the literal first user message of the transcript as baseline.
ajmalhassan/thorough-review Skill
0★Performs evidence-backed code review of pull requests, branches, or diffs. Use when reviewing changes where a wrong finding wastes the author's time or a missed bug ships, especially for security, infra, payments, migrations, auth, or shared libraries. Skip for quick gut-checks or "thoughts on this approach" — use the lighter /review for those.
arpitexplores/super-legal-hr-compliance Skill
0★Legal, HR, and compliance: contracts, policies, and regulatory guidance (non-security).
The same file is in 1 other repository
kkunkunya/academic-deweight-suite/plugins/academic-deweight-suite/skills/deweight-anchor-rewrite Skill
no license0★ repo学术降重的锚点约束改写门。只根据 Semantic Anchor、Pattern Coverage Matrix 和真人实践卡绑定处方改写 suspect 段;无绑定不改写。触发关键词:按锚点改写、处方式改写、anchor-bound rewrite、去 AI 改写、论文段落改写。
fulgur-rs/agent-skills/skills/html-to-pdf Skill
no license0★ repoConvert HTML to PDF using the fulgur CLI (npx @fulgur-rs/cli). Generates HTML from a description if no file is provided.
buchi-neko/skills/vercel-incident-2026-april Skill
0★ repoInvestigates and remediates exposure from the Vercel April 2026 security incident on any Vercel-linked project. Runs activity/webhook/env/integration audits, detects unauthorized actors, flags env vars that lack the 'sensitive' type, and produces a prioritized rotation plan. Use when the user mentions Vercel security incident, April 2026 incident, OAuth compromise, secret rotation on Vercel, or asks to audit a Vercel project for exposure. Also use when switching to a different project and needing to re-run the same incident response checks.
0SxD/notebooklm-mcp-skill Skill
0★Query, inspect, and manage Google NotebookLM notebooks from Claude Code. Trigger whenever the user says "query notebook", "ask notebooklm", "search notebooks", "list notebooks", "notebooklm server info", "get notebook", "inject source into notebook", "what did notebooklm say about", or any request to pull evidence from a named NotebookLM notebook as grounding for an artifact. Covers three access paths: (1) the mcp__notebooklm-mcp__* MCP tool surface (35 tools) when the stdio server is loaded, (2) a Claude-in-Chrome browser route against notebooklm.google.com when the MCP is unavailable, (3) a Playwright fallback using notebooklm_uploader.py for bulk source injection. Always ask the user which notebook to query before any call. Never auto-select. Never fabricate notebook IDs or contents. Every query runs through the 100 Percent Confidence Loop and every synthesized answer passes the Trinity Dialectic gate.
claylo/sustained-presence Skill
0★Validates emotions, maintains empathetic tone, avoids premature reassurance, and prevents repetitive or hollow responses during extended emotional exchanges. Use when the person is expressing grief, pain, fear, hopelessness, anger, or other intense emotions across multiple turns — especially when the conversation extends into prolonged emotional territory. Addresses LLM behavioral failure modes (strategy preference collapse, premature escalation, grief-flattening), not clinical intervention. Not a substitute for professional mental health support.
appalize/aso-skills/skills/ab-test-store-listing Skill
0★ repoWhen the user wants to A/B test App Store product page elements to improve conversion rate. Also use when the user mentions "A/B test", "product page optimization", "test my screenshots", "test my icon", "conversion rate optimization", "CPP", or "custom product pages". For screenshot design, see screenshot-optimization. For metadata optimization, see metadata-optimization.
The same file is in 2 other repositories
qzachh/skills/pagespeed-optimizer Skill
0★ repoUse when the user mentions PageSpeed Insights, Core Web Vitals, LCP, TBT, CLS, site speed, page speed score, slow website, performance optimisation, or similar. Guides a phased, verification-gated approach — images first, fonts second, JavaScript third — specifically designed to avoid the regressions that typically occur when AI agents try to fix everything in one pass. Encodes lessons from a real 27→80 optimisation journey where an "everything at once" approach caused a 77→62 regression that took two more iterations to recover from.
kvalifik-workflows/relume-sitemap/plugins/claude/relume-sitemap/skills/relume-sitemap Skill
0★ repoGenerate Relume-ready visual sitemap clipboard payloads by crawling XML sitemaps or live pages with the relume-sitemap CLI.
ProjectNeura/MLE Skill
no license0★Customize the MLE codebase
andrefabricio/prodotypor/files/.claude/skills/00-setup Skill
0★ repoStep 0 of 8 — Project setup wizard. Walks you through configuring your project name, brand, tech stack, and MCP connections. Run this first before any other pipeline step. Sub-commands: [continue] approve setup, [status] check progress, [update] re-scan for remaining placeholders.
bigdra50/catchup-skill/skills/catchup Skill
no license0★ repoコードベースに「追いつく」ためのオンボーディング/変更追跡ガイド。新規参画時のツアー、エージェントが実装した最近の変更の把握、特定領域の深掘り、レビュー補助を、対話で逐次ガイドする。git log/diffに加えてClaude Codeセッションログ(sessions CLI)も組み合わせ「何が変わったか」だけでなく「なぜそう実装したか」まで補完する。Use when ユーザーが "catchup", "キャッチアップ", "オンボーディング", "コードベース把握", "新規参画", "コードツアー", "最近の変更教えて", "AIが何書いたか追いたい", "この領域の深掘り", "レビュー観点" と言ったとき。
gsknnft/skill-safe-core/examples/skills/issue-summarizer Skill
0★ repoSummarizes issue threads and proposes next actions.
Shirolin/i18n-agent-skill Skill
0★High-performance frontend internationalization expert. Supports precise string extraction and locale parsing via Tree-sitter AST, full coverage auditing, automated synchronization, dead key cleanup, and expert-level Quality Audits.
Alpha-Park/gtm-simulation-skill Skill
no license0★Automate campaign analysis, creative testing, and optimization across your ad stack using an AI-native advertising platform.
The same file is in 1 other repository
ModelBound/dev-packs/.github/skills/ci-smoke Skill
0★ repoSmoke-test skill for ModelBound CI — triggered when validating GitHub Actions skill checks.
The same file is in 4 other repositories
damienen/basd-coding-dispatch/skills/basd-coding-dispatch Skill
0★ repoHermes/OpenClaw-first dispatch workflow for approval-gated AI coding from Telegram and mobile chat. Use when planning, implementing, reviewing, or coordinating Codex, Claude, split-worker, subagent, or generic agent workflows.
0SxD/advisor-trackable-eval-skills-v01/skills/eval_criteria_create Skill
0★ reporodrigoant/agent-skills/skills/brutus Skill
0★ repoProtocolo de comunicação em PT-BR. Comprime respostas eliminando redundâncias gramaticais, artigos e preposições, priorizando verbos no infinitivo.
SpencerGoss/agent-engineering/code-review-session Skill
0★ repoUse after writing or modifying code, before committing or merging — to catch bugs, security issues, and quality problems. Trigger on: "review this code", "check my code", "look at what I wrote", "code review", finishing a feature or bug fix, after a tdd-workflow green phase, or before any git commit on non-trivial changes. NOT for design reviews, architecture discussions, or general issue checking — only for reviewing code changes (git diff).
davdittrich/planning-with-beads Skill
no license0★Use when writing any ticket, issue, PR description, or bug report. Mandatory when starting complex task (3+ steps), research, multi-session work, or any multi-agent handoff.
lythos-labs/lythoskill-test-stubs/architecture-diagram-stub/inner-stub Skill
0★ repoBDD test stub — arbitrary subdir layout (no `skills/` prefix). Not consumable.
rawgroundbeef/skills/grill Skill
no license0★ repoGrilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
GustavoAlecio/claude-setup/skills/ado-close Skill
0★ repoFecha (move para estado final) um work item do Azure DevOps. Pede confirmacao antes. Usa o MCP azure-devops.
itsbdell/made-json-agent-skills/skills/made-json-publisher Skill
0★ repoUse when maintaining a made.json feed for a project or creator: add newly shipped items, update changed metadata, preserve creator-declared claims, and validate the feed.
Tyr0/agent-skills/plugins/credential-expert/skills/credential-storage Skill
0★ repoUse this skill whenever you need to store, read, rotate, or delete a local credential (API token, PAT, app password) on behalf of another plugin. Also use it when an authenticated workflow asks "where do I keep this token", when another skill encounters a missing or invalid credential, or when a user wants to review which credentials are configured. Triggers on 'save my GitHub token', 'set up Bitbucket credentials', 'rotate my API token', 'where is the credentials file', 'how do I store an API key for an agent', or any task that requires reading a secret from local credential storage.
trphume/daichijoubu/skills/go-hints Skill
no license0★ repoThis skill should be used when writing, reviewing, or refactoring Go code — any time files match `**/*.go`, `**/go.mod`, or `**/go.sum`, or the user mentions Go/Golang conventions, error handling, interfaces, goroutines/channels, context, `testing.T`, table-driven tests, golden files, `t.Cleanup`, integration tests, or `gofmt`/`goimports`/`go vet`. Covers general Go language guidance only — conventions, patterns (errors, concurrency, DI, HTTP, performance, functional options), and testing rules (helpers, table tests, golden files, integration lifecycle, parallel safety). Third-party library or linter rules belong in their own skills.
ZerodriftSec/xlayer-trust-gate/skills/xlayer-trust-review Skill
no license0★ repoComplete trust gate review for XLayer contracts. Orchestrates OnchainOS skills (security, token info, tx simulation) with EVM static analysis (access control, proxy risk, upgradeability) to produce a machine-readable risk brief. Use when asked to review, audit, or assess risk of an XLayer/EVM contract.
rishi115/flutter-chat-real-time Skill
no license0★Use when building real-time chat, messaging, or communication features in Flutter. Covers WebSocket connection lifecycle, ping/pong keep-alive, automatic reconnection, connection state machines, listener-based event architecture, message type hierarchies with polymorphic JSON serialization, typing indicators, read/delivery receipts, presence tracking (online/offline), echo prevention, operation queuing for race conditions, rich text formatting in chat (WYSIWYG to markdown to styled rendering), message bubble rendering, keyboard-aware message list layout, BLoC-based chat component architecture, and stream-based event distribution. Also use when seeing issues with WebSocket disconnects, duplicate messages, stale presence, typing indicator bugs, or chat UI jank during keyboard animation.
AIEngineerX/printr-agent-skills/printr-agent-payments Skill
0★ repoUse when building a Solana paywall — charging users for agent actions with on-chain memo-match invoice verification. Generates cryptographically-random memos, builds SOL or USDC transfer transactions for client signing, and verifies payments on-chain by scanning the treasury wallet's signature history. Platform-agnostic — works for any Solana SPL mint and any Solana wallet adapter. Pairs with `printr-swap` and `printr-tokenized-agent` for a full agent-revenue + buyback-and-burn loop on Printr POB tokens.
Super office docs presentation
arpitexplores/super-office-docs-presentation Skill
0★Office, docs, and presentations: PDFs, docs, slides, spreadsheets, and documentation workflows.
The same file is in 1 other repository
motiful/progress-hygiene-rules Skill
0★Progress file hard constraints. MUST maintain exactly one progress root per project per the location matrix, valid frontmatter with absolute dates on every progress doc, NN- numeric prefix only for time-ordered children in progress/ and research/ trees (never skill references), archive when files exceed ~200 lines preserving content verbatim, relative paths in all cross-file references. NEVER place progress under .claude/, maintain two progress files with mutual references, use relative dates, duplicate child content into parent, summarize archived content, or discard completed history. Activates on any progress file edit, migration, or new-session handoff. MUST read SKILL.md BEFORE editing, creating, moving, or archiving any progress or research tree file.
Moonweave-Systems/decide-skill Skill
0★User-invoked research skill. Investigates current industry best practice via parallel WebSearch + context7 + GitHub adoption signals, then either decides autonomously (reversible actions) or escalates with factual-context questions (contested or information-requiring decisions). Manually triggered via `/decide` only — never auto-invoked. Use when the user types `/decide` optionally followed by a question. Without arguments, extract the pending decision from the prior assistant message.
The same file is in 1 other repository
sisodiabhumca/agent-skills/skills/ab-test-power-calculator Skill
0★ repoVendor-neutral skill to estimate experiment power, sample size, and runtime for product experiments.
wangkezun/qweather-skill Skill
no license0★和风天气查询 — 查询实时天气、天气预报、空气质量、灾害预警、生活指数等。当用户询问天气、气温、降雨、空气质量、日出日落等信息时使用。
escwxyz/skills-re/.agents/skills/better-auth-best-practices Skill
0★ repoConfigure Better Auth server and client, set up database adapters, manage sessions, add plugins, and handle environment variables. Use when users mention Better Auth, betterauth, auth.ts, or need to set up TypeScript authentication with email/password, OAuth, or plugin configuration.
rynhardt-potgieter/sprint_workflow/plugins/sprint-workflow/skills/api-design Skill
0★ repoRESTful API design standards — endpoint naming, HTTP methods, response wrappers, error handling (RFC 7807), pagination, versioning, rate limiting, and OpenAPI conventions. Use this skill when designing new API endpoints, reviewing API contracts, adding error handling, implementing pagination, or ensuring API consistency across the project.
Scribeless agent direct mail workflows
scribeless/skills/skills/scribeless-agent-direct-mail-workflows Skill
0★ repoDesign and review AI-assisted, API-led Scribeless direct mail workflows. Use when a user wants an AI agent, LLM workflow, custom app, server-side automation, CRM automation, data pipeline, or generated creative system to create recipients, generate personalized variables or HTML front/back content, validate payloads, trigger previews, and safely operate direct mail campaigns through the Scribeless API.