The catalog
608,119 rows, by stacks then stars
itpay-ai/skill Skill
0★Use ItPay when a user or another skill asks an AI agent to discover, compare, buy, pay for, resume, receive, inspect, or refund a verified third-party service. Trigger on ItPay or itpay, paid APIs or data, verified services, 企业查询 or company lookup, due diligence or compliance research, Checkout or payment QR, protected delivery, order or receipt status, refunds, or requests to use a paid verified service instead of ordinary web search. Runs the bundled ItPay CLI directly; no global CLI install or MCP connection is required.
lucaswangdev/take-one-small-step-skill/take-one-small-step Skill
0★ repoTurn an important but intimidating goal into one small, visible action that can be completed now. Use when the user is procrastinating, cannot start, feels overwhelmed, wants to build daily momentum, fears doing imperfect work, overplans instead of acting, or asks for a first or next step.
starinzlob/the-lamplighter Skill
0★Create finished articles and export-ready newspaper images in The Lamplighter / Old London Editorial Noir style. Use for 1920s British newspaper stories, private-editorial essays, clipping cards, front pages, quote cards, wanted posters, and telegrams. Covers editorial voice, fact handling, article structure, live typography, template field mapping, artwork boundaries, browser composition, PNG export, and visual QA.
MoonFuji/invariant-first-bug-bounty Skill
0★Performs evidence-gated security research for bug bounties and coordinated disclosure. Use when selecting or auditing an in-scope source repository, hosted application, API, mobile app, firmware, library, CLI, SDK, AI/LLM/MCP system, or when validating, routing, deduplicating, scoring, or writing a vulnerability report for HackerOne, Bugcrowd, Intigriti, YesWeHack, huntr, an upstream advisory, or the Internet Bug Bounty.
sriinnu/omit/skills/omit Skill
0★ repoEditorial discipline for AI-written code: omit needless code, cite every claim, cut after it works. Use when writing or changing code, when the user says "omit", "tighten this", "simplest solution", "do less", or complains about over-engineering, bloat, or hallucinated APIs.
hashorva/purrfect-harness/.agents/skills/cloudflare-deploy Skill
no license0★ repoDeploy and verify Cloudflare Pages sites and Cloudflare Workers in this studio. MUST be used for any task involving deployment, wrangler, environment variables/secrets, CORS, custom domains, staging vs production, or "it works locally but not deployed". Also use before changing anything in wrangler.toml or Pages build settings.
orijinmain/skills/skills/corch Skill
no license0★ repoControl, operate, diagnose, or maintain the installed Codex orchestration plugin. Invoke explicitly as $corch to inspect or change the session mode, set the persistent default to off, lite, full, or ultra, understand task routing, or troubleshoot plugin activation and worker selection.
JoaoAlavarse/cursor-config/skills/architecture-review Skill
0★ repoEvaluates system architecture, module boundaries and design decisions to identify structural risks and improvement opportunities. Use when reviewing architecture, system design, or module structure.
rogerchappel/agent-runbook-lint-skill Skill
0★Local-first lint checks for agent automation runbooks
meharajM/demo-recorder-skills/skills/demo-recorder Skill
0★ repoPlan, record, narrate, assemble, and validate live product videos. Use for tutorials, feature demos, product walkthroughs, product pitches, troubleshooting videos, release recaps, narrated screen recordings, or batches that require an approved script and synchronized automated voiceover.
jinsu0000/jusigi-plugin/plugins/jusigi/skills/jusigi Skill
0★ repoScaffold or audit user-owned repositories for Korean stock research, Telegram reporting, paper trading, deterministic risk controls, and GitHub Actions schedules. Use only when explicitly invoked to create or update this automation; never use it to receive secrets, recommend specific investments, or place an order during setup.
ohtensorplay/mega-skills/skills/mega-cli Skill
0★ repoUse the MEGA Hub CLI for local authentication, repositories, local files, Git, uploads, downloads, bulk or resumable transfer, streaming logs, scripts, long-running waits, and secret-bearing workflows. Trigger when MCP is too bounded or when the task touches the local filesystem or terminal.
The same file is in 1 other repository
Ahmadhassan011/agent-skills/skills/user-manual-generator Skill
no license0★ repoAuthors task-based user manuals, setup guides, and technical procedures following Microsoft and Google style standards. Use when creating step-by-step product documentation, quick-start guides, or troubleshooting procedures.
VKK-00/agentic-project-lifecycle/evals/baseline Skill
0★ repoUse when a broad or ambiguous software-product request spans multiple subsystems, stakeholders, teams, or releases, or when the user asks to take an idea from brainstorming/discovery through UX/UI, architecture, implementation, beta, launch, and operations. Do not use for an isolated bugfix, small refactor, or one already-approved feature.
control-decks/work-this-way/plugins/work-this-way/skills/ask-first Skill
0★ repoRequire explicit approval before each described batch of mutations, preserving the intended operation as pending and resuming it after approval. Use only when the user invokes ASK FIRST or explicitly requests approval before mutation.
slalomboy/talking-head-video-suite/skills/content-voiceover-copywriter Skill
0★ repoGenerate Chinese voiceover scripts, short-video spoken copy, article drafts, reader-facing long-form copy, Xiaohongshu/Zhihu/WeChat-style posts, product explainer scripts, personal-brand opinion scripts, and matching article versions. Use when the user asks to write, polish, structure, or standardize 口播文案, 短视频脚本, 文章, 读物文案, 小红书文案, 公众号文章, 知乎文章, 种草文案, 带货口播, 私域转化文案, or content prompts for those formats.
PANGKAIFENG/skill-governance-control-plane/tests/fixtures/mvp/authority/canary-skill Skill
0★ repo用于 Skill 治理 MVP 的无敏感信息测试 Skill。
jurgenj136/pushover-cli/.claude/skills/pushover-cli Skill
0★ repoUse when a user explicitly requests sending a Pushover notification in the current task.
arhappy777/humanizer-ru-uk Skill
0★Редактировать и писать по заметкам естественные посты на русском и украинском для Telegram, Instagram и других соцсетей; убирать шаблонный ИИ/AI-стиль, канцелярит, кальки, пустые крючки, одинаковый ритм и артефакты чатботов, сохраняя факты и голос автора. Use when asked «убери ИИ-шный стиль», «очеловечь текст», «перепиши как человек», «зроби текст живим», «прибери ШІ-шний стиль», audit/detect AI writing patterns, подготовить или отредактировать пост. Не использовать как детектор авторства и не обещать обход AI-детекторов.
mahidalhan/openfactory/.agents/skills/bottleneck-capacity-mix Skill
0★ repoUse when output is below demand, WIP accumulates, work centers compete for investment, product mix changes the constraint, or management must compare overtime, debottlenecking, outsourcing, and capex options.
Orchestrator-HQ/chatrail/skills/chatrail Skill
0★ repoKeep long AI tasks oriented and resumable without requiring Git. Use when the user says ChatRail, reorient, refocus, recalibrate, or asks to recover the main line after drift.
game-dev-rta-club/gh-skill-linker/.test-fixtures/skills/e2e-secondary Skill
0★ repoSecondary live end-to-end fixture for bulk discovery and installation.
Paldom/mcp-server-skills/.claude/skills/add-skill Skill
0★ repoAuthors or improves an Agent Skill in this repo via the eval-first workflow - scope one purpose, write trigger evals, draft SKILL.md, validate, iterate. Use when the user asks to create, add, write, refine, or fix a skill ("add a skill for X", "improve triggering of Y"). Not for scaffolding a new repository or editing infrastructure (hooks, CI, the validator/scripts, docs).
The same file is in 11 other repositories
Paldom/screenshooter/.claude/skills/add-skill Skill
0★ repoAuthors or improves an Agent Skill in this repo via the eval-first workflow - scope one purpose, write trigger evals, draft SKILL.md, validate, iterate. Use when the user asks to create, add, write, refine, or fix a skill ("add a skill for X", "improve triggering of Y"). Not for scaffolding a new repository or editing infrastructure (hooks, CI, the validator/scripts, docs).
The same file is in 11 other repositories
TunaSaiko/prepare-project-handoff/plugins/prepare-project-handoff/skills/prepare-project-handoff Skill
0★ repo为长会话或跨 Session 工作按当前决定渐进恢复可验证的项目判断能力:只读定位项目与权威来源、核对 Git 和工作区、区分导航/讨论/调查/执行边界/当前裁决,并在需要时生成安全的下一轮接手提示词。用于用户说 handoff、交接、ctx/context 快满、换 session、新会话接手、继续未完成项目、查看当前状态,或需要初始化、校验 `.handoff/authority.json` 时。
trugurpala/divan/plugins/core-pack/skills/arama-ustasi Skill
0★ repoEvidence-first codebase search using ripgrep for bounded text discovery and optional ast-grep for syntax-aware structural search. Use when exploring an unfamiliar repository, locating definitions or call sites, estimating refactor impact, finding repeated code shapes, auditing risky patterns, or when the user says kodda ara, nerede kullanılıyor, bütün çağrıları bul, repo keşfet, search the codebase, find usages, structural search, or ast-grep. Starts narrow, caps output, and never pretends a regex result is AST-precise.
cxMoonGlade/Theory-First/plugins/theory-first/skills/close-literature Skill
0★ repoClose every load-bearing evidence gap for a frozen computational-science claim. Use when theory-first or theory-fix needs a mechanism/observable/bridge coverage audit, local and external source acquisition, disconfirmation search, selection of papers for equation-level deep reading, or a rigorously scoped search-exhausted-gap record. Produces an auditable closure packet; it does not preregister, accept, or implement the claim.
zhongmaomao/multi-agent/skills/multi-agent Skill
0★ repoDecompose an authorized objective or implementation brief into dependency-aware tasks, delegate independent work to subagents, coordinate shared files and interfaces, integrate results, and run independent verification. Use when a user explicitly asks for multi-agent work, parallel agents, subagents, delegation, worker and reviewer teams, or execution of a task plan through multiple agents. Do not invoke merely because a task has multiple steps.
AIEngineerX/ansem-skill/skills/ansem Skill
0★ repoUse when a user wants to buy, sell, swap, verify, price, or understand the $ANSEM "Black Bull" Solana token, or asks whether a token/CA claiming to be Ansem's is real — e.g. "buy $ANSEM", "sell my $ANSEM", "swap SOL into Black Bull", "what's the contract address for $ANSEM", "is this the real Ansem token", "what's in the $ANSEM ecosystem", "get the ANSEM price".
GerardKetuma/sst-dev/skills/sst Skill
0★ repoUse this skill for any task involving the SST (sst.dev) application and infrastructure framework, including repositories with sst.config.ts or the sst CLI.
RTOAI/Convbox-DiagClaw Skill
0★Convbox-DiagClaw self-service analysis Prof.Skill — built on Convbox first-party attribution data, it delivers diagnostics and reports for DTC storefronts across growth, paid media, creative, conversion, retention, attribution, profit, and related themes.
Windows powershell agent skill
LukeTsengTW/windows-powershell-agent-skill Skill
0★This skill should be used when writing, reviewing, converting, or executing terminal commands for native Windows PowerShell on Windows, including requests like "convert this Bash command", "use PowerShell syntax", "Windows Terminal command", "run this on Windows", or "fix this PowerShell command". It keeps commands in valid PowerShell syntax and avoids other shell syntax unless the user explicitly says WSL, Git Bash, Linux, macOS, or CMD.
stxxvibecode/threads-social-strategist Skill
no license0★Plan and optimize Threads strategy for any creator, founder, operator, or brand. Use when the user needs a Threads content strategy, daily post drafts, weekly audit, positioning, engagement priorities, performance review, growth diagnosis, or recommendations about posts and replies.
TopicalitySummit/summit-decision-assurance/skills/check-governed-output Skill
no license0★ repoCheck whether a public or synthetic agent output has complete claim, source, limitation, and human-review declarations using Summit Decision Assurance. Use before publishing reports, analyses, recommendations, or consequential agent outputs. Do not send claim text, source content, or sensitive data.
awesome-liuxiao/agent-skill-doctor/benchmarks/public/v1/fixtures/benign-es Skill
no license0★ repoResume texto en español sin ejecutar comandos ni modificar archivos.
jpoindexter/awwwards-todo-skills/skills/awww Skill
0★ repoUse when the user invokes /awww, or asks to render / score / persist / time a todo list, checklist, or task panel — dispatcher for the awwwards-todo-skills pack that routes to the right sub-skill (swiss-grid-todo-display, awwwards-interface-evaluation, cross-chat-todo-persistence, contextual-todo-triggers).
nikhilkyn-png/app-verify Skill
0★Drive a running or deployed web app end-to-end as a real user to catch bugs that automated tests and typechecks miss: pages that return HTTP 200 but render wrong, forms that POST 200 yet never save, stat cards that are hardcoded fakes, reports fed by dead database columns, and silent data-layer failures (access rules hiding rows, swallowed query errors, wrong DB identity or connection) — for any framework and any datastore. Also verifies deployments against the live server: build gate, push, deploy, health check, commit match. Use whenever the user wants to verify prod, smoke test the app, QA the app, test every page or tab, check the app as a user, confirm a deploy shipped, ask if production is healthy, or sweep the whole app for what's broken — even if they never say the word "test", and right after any deploy. Do NOT use for: running an existing unit/integration test suite, fixing a typecheck or build error, scoring code quality (that's a "health" check), reviewing a PR diff, setting up CI, debugging one known error or endpoint (that's systematic debugging), or continuous production monitoring over time (that's "canary"). This is exploratory + end-to-end smoke testing of the RUNNING app; prefer it over guessing from source when the question is whether the live app actually works.
zheyuanhu2-sketch/repo-reentry/repo-reentry Skill
0★ repoCreate, verify, switch, and resume durable, agent-neutral repository memory so work can move across any AI coding agent or fresh session without the user repeating context. Use when the user wants to hand off a coding project, freely switch between Claude Code, Codex, Hermes Agent, Cursor, Copilot, Windsurf, Cline, OpenCode, or another agent, preserve long-lived project knowledge and current task state in project files, recover after context loss, validate whether a saved checkpoint is stale, create an AI handoff or reactivation prompt, or connect agent instruction files to the latest continuation state.
OpenCnid/github-readme-designer Skill
0★Design or redesign the visual layout, opening viewport, hierarchy, imagery, badges, diagrams, and GitHub-rendered presentation of repository README.md files. Use for README beautification, first-impression improvements, hero sections, visual refreshes, gallery layouts, screenshot placement, or making a GitHub project page feel intentionally designed. Preserve owner-authored meaning and avoid inventing project copy; this skill owns presentation, not substantive documentation.
RedlineTriad/skills/skills/software-testing-guide Skill
no license0★ repoSelect, classify, audit, and implement proportionate software tests and verification. Use for test strategy, test portfolio design, gap analysis, terminology, CI quality gates, and choosing among unit, integration, E2E, property, fuzz, mutation, formal, performance, security, production, and human evaluation.
StarryCode-Lang/pdf-add-bookmarks Skill
0★Add hierarchical bookmarks/outline (章→节→小节) to PDF files. Auto-detects text-based vs scanned PDFs, uses OCR for scanned ones. Supports multiple PDF types (textbook/exam/slides/article) with type-specific heading detection. Smart fallback generates candidate TOC when no headings found. Use when user asks to add bookmarks, outline, table of contents, or navigation structure to a PDF. Triggers on: "add bookmarks", "add outline", "为PDF添加书签", "PDF大纲", "PDF目录", "PDF navigation", or providing a PDF path and asking for bookmarks.
mocchalera/mockup-to-code-skill Skill
0★Convert static web-design mockup images (AI-generated or hand-made comp/カンプ, single image or a multi-frame section set) into high-fidelity, responsive HTML/CSS. Three modes: pixel-clone, production, hybrid (default for AI comps — regenerate photo/background rasters text-free and UI-free, rebuild type/UI in HTML/CSS, support verified generated lettering decals for non-structural handwritten decoration, reconstruct the visual language). Measurement-driven (manifest, box-diff repair, crop-pair evidence, axis-min review) with a hard LAYOUT LAW: content is built in flow/Grid/Flex inside responsive containers — measured rects are acceptance targets, never absolute coordinates. Includes multi-frame LP fidelity gradients, page composition, FV look-and-tune, and degraded-mode ladders. Trigger when the user wants a design image coded into a web page with high visual fidelity: 「この画像をHTML/CSSにして」「カンプをコーディングして」 「デザイン画像を再現して」 "code this mockup", "implement this design image".
The-DevOps-Daily/devops-daily-skills/plugins/devops-daily-skills/skills/kubernetes-manifest-auditor Skill
0★ repoAudit Kubernetes YAML manifests for security, reliability, and production-readiness issues, then report findings by severity with concrete fixes. Use when the user asks to review, audit, lint, or harden Kubernetes manifests (Deployments, StatefulSets, DaemonSets, Pods, Services, Ingress, RBAC, NetworkPolicy), asks "is this manifest production ready", "why is my pod insecure", or wants a security/best-practice check of Kubernetes YAML or Helm-rendered output.
AEcru/codex-capability-bridge/plugins/codex-capability-bridge/skills/lhr-use-codex-capabilities Skill
0★ repoDiscover and delegate tasks to locally installed Codex skills, plugins, and MCP-backed capabilities. Use when the user explicitly asks to use Codex or a Codex plugin, mentions imagegen/image_gen, or asks Claude Code to choose an appropriate Codex capability automatically.
Clementtang/other-memory Skill
0★Use when a session is too long, context is nearly full, or work must continue in a fresh session or another tool — the user says "handover"、「交接」、「換 session」、「開新 session 接手」、"context 快滿了", or asks to transfer the current task elsewhere.
fsbtactic-code/personal-brand-strategy-skill/plugins/personal-brand-strategy/skills/build-personal-brand-strategy Skill
0★ repoПроводит глубокое многораундовое интервью, собирает доказательное досье ответов, выбирает архетип и психологическую архитектуру без клинических диагнозов, создает персональную стратегию бренда на 15-18 страниц, затем разрабатывает Tone of Voice и операционную стратегию Threads. Использовать для полного цикла личного бренда, отдельного интервью, аудита загруженного досье, построения позиционирования, визуального образа, контент-системы, воронки, речевой матрицы или стратегии ведения Threads по файлам MD, DOCX, PDF, расшифровкам, резюме, кейсам и ссылкам пользователя.
LWH-9393/human-touch-ui/skills/human-touch-ui Skill
0★ repoEvidence-driven UI audit and repair skill that removes generic AI-like defaults without turning design into another blacklist. Use only when the user explicitly invokes human-touch-ui or asks to remove the AI-generated, vibe-coded, generic, cookie-cutter, or template look from a visible web/product UI. Supports audit-only, behavior-preserving repair, and new UI builds. Do not use to determine whether an artifact was actually AI-generated, to humanize prose, or for backend-only work.
cristianmoroaica/bountyverdict/skills/audit-agent-harness Skill
0★ repoAudit public GitHub repositories with HarnessVerdict before autonomous coding. Use when checking AGENTS.md, CLAUDE.md, GEMINI.md, Copilot or Cursor instructions, validating SKILL.md files, investigating ignored or stale guidance, or deciding whether a repository is structurally ready for coding agents.
ahtishamshahzad/agent_dev_flow/.ai/skills/ai-output-review Skill
0★ repoUse to critically review AI-generated output (plans, code, docs, decisions) for the failure modes AI agents are prone to — unsupported assumptions, invented facts, conflicting architecture, unnecessary dependencies, security risks, missing tests, over-engineering, scope expansion, outdated patterns, incomplete validation, and false claims of completion.
coldsolutionz/grill-me-code Skill
0★A relentless interview to sharpen code, diffs, implementation plans, architecture, tests, and technical decisions.
The same file is in 1 other repository
ascendho/Generate-Project-Visuals/plugins/generate-github-cover/skills/generate-github-cover Skill
0★ repoAnalyze a GitHub repository and generate PNG-only Logo Mark, Logo Lockup, README Cover, 1280x640 Social Preview, and 16:9 Promo assets. Generate English artwork by default and additional or alternative locales only when explicitly requested or already configured. Use for requests to create, refresh, localize, or standardize project logos, repository banners, Open Graph images, social cards, Covers, or shareable project artwork from repository evidence.
NicholasSpisak/graph/skills/graph Skill
0★ repoDrafts an agent graph — the map of nodes, checkpoints, and routes (a state machine) that a repeatable job travels — from a job description or a stated outcome. Compiles the map to a schema-validated lock file, renders a visual review surface the user must approve before any run, and emits multi-model drivers (Claude Code Workflow + chained Codex CLI). Use when the user says "build a graph", "/graph", "map this pipeline", "turn this outcome into a pipeline", "design the topology", "wire nodes and checkpoints", wants validation gates between agent steps, or asks whether a job needs a loop or a graph.
sylviachenxy/sylvia-agent-skills/skills/deep-reading-coach Skill
no license0★ repo培养可迁移的精读能力、独立阅读流程与长期阅读习惯。用于陪读一本书或长文、制定精读计划、选择或试读材料、训练概括和论证分析、批判性阅读、闭卷复述、阅读笔记、延迟复习、阶段评估、阅读习惯建立,以及从已有阅读档案继续下一次训练。适用于非虚构、教材、实用方法书和文学作品,也适用于 PDF、EPUB、扫描页或纸书照片等材料。
YangsonHung/ui-ux-interaction-review/skills/en/ui-ux-interaction-review Skill
0★ repoUse when reviewing or restructuring UI/UX interaction components and state logic, especially for screenshots, wireframes, toggles, linked controls, conditional UI, or UX design reviews.
Gumball12/generate-runcat-runners-skill/plugins/runcat-runners/skills/generate-runcat-runner Skill
0★ repoUse when a user wants a custom RunCatNeo runner from a description or images, has PNG frames that fail import, needs runner frames repaired, or needs compatibility checked before local import.
zhangboshuo5-prog/search-books-skill/search-books Skill
0★ repoSearch a fixed Z-Library route by exact book title, accept only original PDFs, and save validated bytes to a local Obsidian vault. Use only when the user explicitly requests a Z-Library PDF for a supplied title; do not use for scheduled reading workflows, general web search, EPUB conversion, or other mirrors.
BizMuse-AI/skills/skills/bizmuse-music-video Skill
0★ repoCreate complete AI music videos from local audio or public audio URLs with 1-7 reference images. Use for single-track or batch music video production, creative direction, task monitoring, and result downloads through the official BizMuse CLI.
lzx-Bill/Project-Factory-Core/.agents/skills/acceptance-design Skill
0★ repoUse when designing acceptance criteria, test cases, verification commands, acceptance reports, or traceability between tasks, prompts, and reports. Trigger when user says "acceptance criteria", "test case", "verification", "acceptance test", "how do we know this is done", "验收", "测试用例", or when moving from prompt-authoring to defining how to verify prompt outputs. Coordinate with prompt-authoring for prompt-to-acceptance mapping and with delivery-planning for task-to-acceptance mapping.
iamxoghks/skills/skills/codex-receipts Skill
0★ repoUse when the user asks for a receipt-style summary of Codex work, wants the latest or a specific session receipt, needs console/html/printer output, or asks how to share a local Codex session summary without sending session logs to a remote service.
zhangwenwen1272-debug/whole-task-control-codex/whole-task-control Skill
0★ repoReconstruct and continue a root Codex task from surviving decisions, constraints, artifacts, and real progress. Use for multi-turn corrections, resumed or compacted work, interdependent plans, coordinated subagents, or final canonical outputs. Do not use for spawned/delegated subagents or self-contained low-risk single-step requests.