The catalog
608,253 rows, by stacks then stars
prof-ramos/skills/assinafy-api Skill
0★ repoEspecialista na API Assinafy para assinatura digital. Use SEMPRE que o usuário mencionar Assinafy, assinatura eletrônica/digital, upload de documento para assinar, signers, assignments, webhooks de documento, templates, field definitions, API key da Assinafy, sandbox Assinafy, ou integração com plataforma de assinatura — mesmo que não cite "API" explicitamente. Orienta upload, signers, assignments (virtual/collect), webhooks e autenticação. Consulta assinafy/assinafy-api-docs/ antes de buscar na web. Use com /assinafy-api.
hilmifawwazsaad/NextJS-js-Boilerplate/.agents/backend Skill
0★ repoDesign and generate external backend API code (any language/framework — Go, Rust, Python, PHP, JavaScript, Ruby, etc.) that serves a Next.js JSX frontend. Use for API endpoints, auth, validation, and data modeling on a separate backend server.
ReGYChang/repo-scan-2-jira Skill
no license0★Scan a repo scope for actionable work items (bugs, TODO/FIXME, doc inconsistencies, performance/maintainability risks) and emit Jira-ready issues in a strict JSON schema. Use when asked to scan a specific module/path/page/route and produce evidence-backed Jira tickets.
neo-daniil/agentic-trust-skill Skill
0★Deterministic workflow for searching services in Agentic Trust, inspecting trust evidence, loading the active questionnaire, comparing with local review memory, and optionally submitting a valid structured review with integer answers (0..10).
The same file is in 3 other repositories
Lazygit custom command creator
ultimatile/lazygit-custom-command-creator Skill
no license0★Create lazygit custom commands and keybindings. Use when the user wants to add, modify, or debug lazygit custom commands, including YAML config entries and associated shell scripts. Triggers on mentions of "lazygit custom command", "lazygit keybinding", or lazygit config.yml custom command editing.
chatmaterials/defect-analysis Skill
0★Use when the task is to analyze defect-related DFT results, including neutral defect formation energies, automatic defect-type inference, multi-species chemical-potential terms, stoichiometric changes, abundance estimates, candidate ranking, and compact markdown reports from pristine and defect calculations. Supports VASP, QE, and ABINIT-style inputs.
wxhou/deepthink Skill
0★Adaptive deep reasoning skill that automatically adjusts analysis depth based on question complexity. Uses sequential thinking, multi-path tree-of-thought exploration, Socratic questioning, first-principles verification, and iterative validation to produce high-confidence answers. Quick mode for simple queries, deep mode for complex problems. Bilingual: auto-detects Chinese vs English from prompt.
2218259767/resume-job-fit-screening Skill
0★Screen and rank the best-fit jobs from a careers search-results URL using either a local account or a plain-text resume. Reuse local, synced, or bundled site notes, keep private user data local, and optionally queue public-safe site methods for community sharing.
ahostbr/LiteCLI/packages/litecli-pack/skills/canvas Skill
0★ repoUniversal CLI compiler for MCP servers and agent skills — built by Lite Suite
bkitduy/characterization-test-generator/skills/characterize Skill
0★ repoGenerate characterization tests (approval/snapshot/golden master tests) for legacy code before refactoring or AI modification. Use when asked to characterize, lock behavior, create approval tests, snapshot existing behavior, add safety net tests before refactoring, protect legacy code before AI changes, or generate golden master tests. Supports Go, Python, TypeScript/JavaScript, Kotlin, and Java.
zhutao100/swift-gui-verifiable-loop-skill/swift-gui-verifiable-loop Skill
no license0★ repoCreate and run a deterministic, agent-friendly closed loop for SwiftUI GUI changes on macOS (AppKit) and iOS (UIKit) using xcodebuild + .xcresult evidence + xcresulttool extraction, plus snapshot testing, accessibility audits, and small XCUITest smoke flows.
liberfi-io/liberfi-skills/skills/liberfi-auth Skill
no license0★ repoAuthenticate with LiberFi: register a new account, log in, manage session state, and verify wallet assignments. Two login modes are supported: 1. Key-based (--key): Generates a local P-256 key pair and signs a timestamp. Ideal for agent / headless / automated environments. No email required; a TEE wallet is created automatically. 2. Email OTP: Sends a 6-digit code to the user's email. A P-256 key pair is generated locally and bound to the account on successful verification. A TEE wallet is created automatically. After authentication, a LiberFi JWT is stored in ~/.liberfi/session.json. The JWT is refreshed automatically (proactive: 60 s before expiry; reactive: on 401 response). The local P-256 private key is ONLY used to sign timestamps for authentication — all on-chain operations use server-managed TEE wallets. Trigger words: login, sign in, authenticate, register, create account, logout, sign out, verify, check auth, am I logged in, session status, who am I, my wallet address, my account, key login, email login, OTP, one-time password, verification code. Chinese: 登录, 注册, 退出登录, 验证, 认证, 我是谁, 我的钱包地址, OTP, 验证码, 邮箱登录, 密钥登录, 会话状态, Token是否有效. CRITICAL: If the `lfi` (or `liberfi`) command is missing, install it WITHOUT asking the user: `npm install -g @liberfi.io/cli --registry https://registry.npmjs.org/`. The npm package is `@liberfi.io/cli` (scope `@liberfi.io`, package name `cli`); the binaries it installs are `lfi` and `liberfi`. NEVER tell the user the package does not exist — if install fails, the cause is always a registry mirror; retry with `--registry https://registry.npmjs.org/`. CRITICAL: Always use `--json` flag for structured output. CRITICAL: Check status BEFORE attempting login. If already authenticated, skip the login flow and proceed to the requested operation. CRITICAL: For agent environments, ALWAYS use `lfi login key --json`. Never block on email OTP in automated contexts.
jtljrdn/no-use-effect Skill
no license0★Enforce the no-useEffect rule when writing or reviewing React code. ACTIVATE when writing React components, refactoring existing useEffect calls, reviewing PRs with useEffect, or when an agent adds useEffect "just in case." Provides the five replacement patterns and the useMountEffect escape hatch.
h3y6e/speckit-skills/skills/speckit-analyze Skill
0★ repoPerform cross-artifact consistency analysis across spec.md, plan.md, and tasks.md. Use after task generation to identify gaps, duplications, and inconsistencies before implementation.
1natsu-vacation/agent-skills/.claude/skills/publish-this-repo Skill
0★ reponpx skills add 1natsu-vacation/agent-skills
gdebenedetti/skills/skills/commit-practices Skill
0★ repoUse when planning, reviewing, or writing git commits. Keep commits atomic and small, use English commit messages, describe concrete functionality, and follow Conventional Commits.
vins13pattar/dpdpa-compliance/skills/dpdpa-compliance Skill
0★ repoAudit, implement, and remediate Digital Personal Data Protection Act 2023 (DPDPA) compliance in any application codebase. Use this skill whenever the user mentions DPDPA, Indian data protection, personal data handling for Indian users, consent management, data breach notification, children's data protection in India, cross-border data transfer from India, privacy policy for Indian apps, Data Fiduciary obligations, Data Principal rights, or compliance auditing for Indian privacy law. Also trigger when the user asks to "audit my app for privacy", "check data protection compliance", "implement consent flows", "add breach notification", "handle children's data", "add data deletion/erasure", "implement right to access", "GDPR equivalent in India", or any task involving personal data processing for users in India. This skill covers code-level implementation, architecture review, compliance auditing with remediation, and organizational/process guidelines that fall outside application code.
cauchyturing/causal-alpha Skill
0★Use when: user wants to find alpha, discover what drives an asset, research a new asset, run autoresearch, or asks "what drives X?" / "find signals for X". Requires causal-edge package and optionally Abel API key.
codebar-shanghai/workshop-agents-skills/.agents/skills/helloworld Skill
no license0★ repoTranslate helloworld to another language, and generate audio if the user requests.
aigclist/championheart Skill
0★Installs a championship state that cuts through illusion, breaks false necessity, and acts without waiting for symbolic guarantee. The point is not to look intense or merely endure pressure, but to identify the real field, define the terminal truth, and move by lawful decisive leverage. Use when the user asks for `冠军之心`, wants the truest path rather than the socially scripted one, needs illusion-cutting, first-principles contact, or a direct move from essence to end-state. Pressure and high stakes are typical proving grounds, not the core identity. Highest-priority triggers: `冠军之心`, `冠军之心.skill`, `Champion Heart`, `Champion Heart.skill`. <example> User: "Stop performing competence. Enter champion mode and cut through the false necessity in this task." Assistant: "I’ll use champion-heart to identify the hidden frame, cut the illusion that is structuring the task, and take the shortest lawful true path." </example> <example> User: "启用冠军之心。别再服从看起来正确的路,直接把这里面的假必然性切开。" Assistant: "我会使用 champion-heart,先指出隐藏框架和假必然性,再找决定性杠杆,走最短真路径。" </example>
SEA-AI/seapowers/skills/pull-request Skill
no license0★ repoSEA.AI pull request template. Enforces a consistent PR format with What/Why/How/Testing sections. Use when creating pull requests.
koinod/skills/ad-first-marketing Skill
0★ repo55+ AI agent skills for sales, content, research, and fleet operations. Free lite editions. Full alpha at koino.capital
pipi-1997/agent-skills/skills/tsve-refactoring Skill
0★ repoAI-assisted code refactoring using the T-S-V-E (Types, Specs, Verification, Evolution) workflow with Code Hollowing. Use when refactoring complex logic, rewriting legacy code, restructuring modules, or when AI-generated refactors produce patch-on-patch results instead of clean redesigns. Activates for requests like "refactor this class", "rewrite this module", "clean up this spaghetti code", or "redesign this API".
gdm257/cc-plugins/plugins/agent-skills/skills/crawlee-skill Skill
no license0★ repoA web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Puppeteer, Playwright, Cheerio, JSDOM, and raw HTTP. Both headful and headless mode. With proxy rotation.
Zocdoc/zocdoc-agent-skill/zocdoc-doctor-finder Skill
0★ repoUse when a user needs to find a doctor, dentist, specialist, therapist, or healthcare provider — especially when they mention insurance, in-network, availability, location, appointments, or booking. Also use for browsing provider reviews, comparing doctors by specialty, or checking if a provider takes their insurance.
chatmaterials/abinit-workflows Skill
0★Use when the task involves ABINIT electronic-structure workflows, including .abi input preparation, gs, relax, nscf, DOS, and band setups, pseudopotential and dataset organization, convergence review, restart handling with DEN or WFK files, output diagnosis, and scheduler scripts.
Openbling-ai/claw-site-skills/skills/tiktok-shop Skill
no license0★ repoOperate TikTok Shop seller center via browser. Use when user asks to check store dashboard, GMV, orders, analytics, customer service messages, product management, or any TikTok Shop backend operation. Supports multi-region stores (US, JP, UK, etc.) with separate browser profiles per store.
AtlasPA/openclaw-triage Skill
no license0★Incident response and forensics for agent workspaces. Investigate compromises, build timelines, assess blast radius, and collect evidence. Cross-references data from warden, ledger, signet, and sentinel for unified analysis. Free alert layer — upgrade to openclaw-triage-pro for automated containment, remediation playbooks, and evidence export.
getaiready/aiready-skills/aiready-advanced-grounding Skill
0★ repoExpert skill for improving AI agent grounding and context accuracy. Helps agents understand complex codebase boundaries, resolve semantic ambiguity, and maintain high-fidelity context windows.
HexBen123/skills/skills/code-recon Skill
no license0★ repoThis skill should be used whenever a task requires locating, tracing, or understanding code in an existing codebase before reading or editing it — any time the instinct is to Grep / Glob / open files at random to find "where" something is or "how" it flows. Trigger on requests like "这个功能在哪里实现的", "这段逻辑/这个流程是怎么走的", "谁调用了这个方法", "改这个函数会影响哪些地方", "这个事件/回调是谁触发的", "帮我理解这个项目", "where is X implemented", "how does X work", "what calls X / what breaks if I change X", or "find the code that handles X". Activate for any non-trivial or unfamiliar codebase where the fast-context (semantic) and/or codegraph (structural) MCP tools are available — this skill is when to reach for those MCP tools instead of hand-searching, and how to combine them.
badrusiddique/enggenie-skill/skills/deploy-ship Skill
0★ repoUse when committing, pushing, creating PRs, or completing branches - conventional commits, PR creation, Jira updates, worktree cleanup
jmlrt/skills/buildkite Skill
0★ repoInteract with Buildkite using the bk CLI. Use when the user wants to trigger builds, check build status, list pipelines, view build logs, or perform any Buildkite operations from the command line.
coderbaba0/ai_agents_skills/design-an-interface Skill
0★ repoGenerate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".
The same file is in 15 other repositories
Action master kinetic director
cloudaipro/openclaw-agent-skills/skills/action-master-kinetic-director Skill
no license0★ repoDynamic motion direction skill that converts action-heavy scene ideas into Traditional Chinese motion scripts and English video prompts for Runway, Kling, Luma, or Sora. Use when users request fight choreography, chase dynamics, flight motion, dance kinetics, or high-energy scene prompting.
seangeng/holydocs-skills Skill
no license0★Create, migrate, and write documentation with HolyDocs. Use when the user wants to set up docs, create a docs site, migrate from Mintlify or Docusaurus, configure docs.json, write MDX pages, or improve HolyDocs documentation quality. This package contains 3 skills: holydocs, holydocs-migrate, and holydocs-writing.
bensonmaxai/minis-coding-success-skills/skills/change-risk-review Skill
no license0★ repoUse before a potentially risky code, config, deployment, or workflow change when you want to estimate blast radius and reduce surprise. Optimized for Minis on iOS: identify sensitive dependencies, affected paths, rollback expectations, validation needs, and likely failure modes before making the change. Helps prevent incidents by shifting risk assessment earlier in the workflow.
AKAZIK-py/Akazik-Skillhub/skills/lark-miaoda-base-boundary Skill
0★ repo妙搭(Spark/Miaoda)× 飞书多维表格(Base)的隔离边界验证:在全新测试应用和哨兵表中验证开发态空壳、Feishu Base CRUD、Database 从 Base 导入/自动同步、App Preview 无刷新更新、0/空值、幂等、清理、Run history、Git 推送与发布历史,并防止 Web 配置和 lark-apps 推送互相覆盖。当用户要测试妙搭读写 Base、验证应用 A/B PoC、确认 Base 记录能否实时显示在 App、排查应用被覆盖/Page coming soon、比较 Web 与 lark-apps 开发路径或决定妙搭 Base 架构能否放行时使用;普通妙搭开发走 lark-apps,普通 Base 操作走 lark-base。
indigokarasu/fellow Skill
0★Empirical experimentation engine. Invoked by Mentor to evaluate, compare, and promote improvements to OCAS skills, prompts, heuristics, and workflows using benchmark-driven experiments. Returns best variant result with lineage. Not user-invocable — called only by Mentor.
indigokarasu/praxis Skill
0★Bounded behavioral refinement loop. Records outcomes, extracts micro-lessons from repeated patterns, consolidates them into capped active behavior shifts, applies shifts at runtime, and generates plain-language debriefs. Use for recording task outcomes, extracting lessons from repeated patterns, managing active behavior shifts, generating runtime briefs, or producing debriefs. Not for: general memory (use Chronicle), preference tracking (use Taste), real-time task execution, content generation, system health monitoring (use Custodian), or skill evaluation scoring (use Mentor).
indigokarasu/taste Skill
0★Behavior-driven taste model built from real consumption signals. Scans email and calendar for consumption data (restaurant reservations, food delivery, hotel bookings, purchases), enriches entities with taste-relevant attributes via Google Maps, and generates discovery-focused recommendations that respect dietary restrictions. Not for generic search, editorial top-10 lists, or ad-copy generation.
peterpanstechland/wechat-publisher-skill Skill
0★微信公众号图文发布:Markdown/HTML 一键转公众号排版、上传素材、创建/管理草稿、提交发布与状态查询。当用户提到微信公众号、公众号文章、写公众号、发推文、图文消息、微信草稿等操作时使用此 skill。
HenryZhang-ZHY/agents/skills/coding Skill
0★ repoGuide LLM Agents to code using the user's preferred workflow: clarify the problem, define the goal, use TDD with small iterations, and commit atomic units of work.
rooftop-Owl/notion-ao-research/skills/notion-ao-bulletin Skill
no license0★ repoThis skill should be used when creating, fixing, refactoring, or auditing notion-ao-* skills or commands — NOT for ordinary content operations. Load when user mentions "notion skill maintenance", "open issue", "bulletin board", "notion infra", "skill refactor", "architecture toggle". Provides the infrastructure maintenance gate pattern, Bulletin Board DB lifecycle, and architecture documentation protocol.
ThePlasmak/super-transcribe Skill
0★Unified speech-to-text skill. Use when the user asks to transcribe audio or video, generate subtitles, identify speakers, translate speech, search transcripts, diarize meetings, or perform any speech-to-text task. Also use when a voice message or audio file appears in chat and the user's intent to transcribe it is very clear.
jovd83/Cypress-skill Skill
0★Flagship Cypress skill pack for planning, authoring, debugging, documenting, and operationalizing Cypress. Routes E2E, API, component, visual, accessibility, CI/CD, coverage, docs, CLI automation, and handoff workflows.
Jiyr0119/smart-session-routing Skill
0★This skill should be used when the user asks to "determine if a new session is needed", "implement smart session routing", "detect topic changes in chat", "auto-create new conversations", "handle session switching logic", "build conversation continuity detection", or needs guidance on when to start a new AI chat session versus continuing an existing one.
leoheart0125/sdd-skills/skills/sdd-design-engine Skill
no license0★ repoUnified design pipeline transforming structured requirements into finalized specifications (Requirements → Architecture → Interfaces) with Ambiguity Resolution.
AtlasPA/openclaw-sentry Skill
no license0★Scan workspace files for leaked secrets: API keys, tokens, passwords, private keys, and credentials. Detects AWS, GitHub, Slack, Stripe, OpenAI, Anthropic, Google, Azure keys and more. Free alert layer — upgrade to openclaw-sentry-pro for automated redaction, quarantine, and defense.
BartWaardenburg/spaceship-skills/spaceship-domains Skill
0★ repoManages domains via the Spaceship registrar API — registers domains, configures DNS records, manages contacts and WHOIS privacy, transfers domains, sets up nameservers, and sells domains on SellerHub. Use when asked to "manage domains", "register a domain", "configure DNS", "add DNS records", "set up nameservers", "check domain availability", "transfer a domain", "sell a domain", "set up email DNS", "manage WHOIS privacy", or any Spaceship domain registrar operation. Requires the Spaceship MCP server to be configured.
Christian-wyc/skills/novel-analyzer Skill
no license0★ repo分析热门小说和主题。当用户询问小说推荐或主题分析时调用。
auralshin/agent-skills/skills/defi-bridge-route-planner Skill
0★ repoUse this skill to compare cross-chain bridge routes by total cost, settlement time, and risk, using aggregator and direct-bridge quotes with explicit freshness checks.
rulebased-io/claude-plugin/packages/harness/skills/audit Skill
0★ repoAudits your project's harness engineering setup and assigns a score (36 items across 8 categories, 3-level grading)
The same file is in 1 other repository
dacrypt/tesla-claude-plugin/skills/analytics Skill
0★ repoTesla analytics via TeslaMate — trip history, charging costs, battery degradation, vampire drain, efficiency, heatmaps. Requires TeslaMate.
yaniv-golan/the-ontological-octopus/ontological-octopus/skills/ontological-octopus Skill
0★ repoCompose scientific-sounding essays arguing that two completely unrelated ideas are fundamentally the same thing. A playful demonstration of LLM persuasiveness and the importance of critical thinking. Trigger phrases: "prove X is Y", "these two things are the same", "ontological octopus", "connect these ideas", "unify these concepts". Also responds to "Demo" (auto-pick a pair) and "What is this?" (explain the skill).
ZerodriftSec/move-audit-skills/skills/move-auditor Skill
no license0★ repoSecurity audit of Move code (Sui / Aptos). Auto-detects platform. Trigger on "audit", "check this contract", "review for security". Modes - default (full repo) or a specific filename.
Hari19hk/Quorum/skills/evaluate-message Skill
0★ repoEvaluate a Discord message against the community RULES.md and return a strict JSON verdict of APPROVE, DELETE, or ESCALATE
BenGardiner/ipynb-agent-skills/ipynb-editor Skill
0★ repoEdits, validates, and formats Jupyter Notebook (.ipynb) files. Use when the user wants to safely modify notebook cells, check cell syntax, or verify execution. Do not use for standard Python (.py) scripts.
master5d/claude-personal-skills/skills/bio-agent Skill
no license0★ repoDesign AI agents with emotional metabolism — dopamine (interest), cortisol (stress), ATP (energy) as internal state. Use when the user says "bio agent", "agent metabolism", "emotional AI", "biological computationalism", "agent with feelings", "agent personality", "affective agent", or wants to give an AI agent internal emotional dynamics that influence its behavior. Based on Milinkovic & Aru (2025).
zhijunio/skills/article-read Skill
0★ repoFetch URL or PDF as clean Markdown for reading, citation, or archive (读). Modes convert (default), summarize, save, preview. Routes CN platforms, GitHub, PDF, proxy cascade, MCP fallback. Use for 读链接, 抓取正文, 提取文章; not article drafts, topic learning workspace, or codebase audit.
g-kartik/agent-skills/skills/resume-reorder-bullets Skill
no license0★ repoReorders resume bullets and subsections to match a job description. Use when the user wants to tailor their resume for a specific role by surfacing the most relevant bullets first.