The catalog
609,689 rows, by stacks then stars
nordicnode/skillpack/.codex/skills/skillpack Skill
2★ repoGenerate and verify the agent-distribution layer for any OSS project
m-binimran/finance-pack/skills/budget-planning Skill
2★ repoBuild an annual operating budget / plan - revenue, headcount, opex, and cash - from drivers, with monthly phasing. Use for annual planning, departmental budgets, or a board plan.
Nxkoo/mcreator-skill Skill
2★Use when AI coding agents work with MCreator workspaces, mod elements, GeckoLib workflows, .mcreator metadata.files tracking, generated-code boundaries, and safe validation loops.
riggyz/skills/skills/attribution Skill
no license2★ repoAttribution rules for issues, pull requests, work items, reviews, and comments created or edited by the agent in GitHub, Linear, Azure DevOps, or similar collaboration systems. Use when creating, commenting on, reviewing, or modifying external tracker content.
JakeLin/effective-claude-code/.claude/skills/effective-claude-code Skill
no license2★ repoApply Effective Claude Code book principles to a project's Claude setup. Use when someone asks to improve their Claude Code setup, apply best practices, or configure Claude Code for a project. Also triggers on "apply item-N", "apply chapter-N", "apply hooks/memory/settings/subagents", or "how should I configure Claude Code".
BuilderCed/agent-skills/skills/africa/africa-mobile-money Skill
2★ repoIntegrate M-Pesa, Orange Money, Wave, and MTN MoMo payment APIs with proper error handling, reconciliation, and multi-operator patterns.
jjuanrivvera/cliwright/skills/cliwright Skill
2★ repoForge a complete, production-grade, agent-ready command-line tool (CLI) for any REST/HTTP API. Use when the user wants to build, scaffold, generate, or create a CLI; wrap an API in a command-line tool; turn an API into a CLI; or make a `gh`-style tool for a service. Produces a Go + Cobra + GoReleaser binary with OS-keyring auth, named profiles, an MCP server, an agent guard, CI/CD, and packaging — and drives the build to completion against a deterministic acceptance gate (`make verify`) so every quality criterion is provably met, not merely asserted. Triggers: "build a CLI for X", "scaffold a CLI", "wrap the X API in a CLI", "make a command-line tool for X", "API to CLI", "create a gh-style CLI".
GeneralLibrary/generalupdate-skill-codegen/.claude/skills/generalupdate-advanced Skill
2★ repoReference guide for GeneralUpdate internal architecture — Pipeline, middleware, Strategy, Differential engine, Bowl crash monitor, FileTree, blacklist, and AOT. Covers all extension points available in v10.5.0-rc.1 including Pipeline, Hooks, Bowl, AOT, and DiffPipeline. Triggers on: "extension points", "custom hooks", "Bowl", "crash dump", "IPC", "named pipe", "shared memory", "custom strategy", "download pipeline", "SSL policy", "auth provider", "custom download", "extension management", "黑名单", "BlackList", "FileTree", "AOT", "NativeAOT", "高级定制", "自定义策略", "自定义认证", "Bowl守护", "IPC替换".
44-99/OpenAlphaStack/skills/market-analyzer Skill
2★ repo分析 A 股大盘、市场情绪、板块轮动和龙头线索。用户询问今日市场、指数强弱、情绪周期、强势板块、北向或资金方向、龙头股时使用。通过 OpenAlphaStack MCP 获取带时间戳的数据,不用于发布交易计划。
alibaba-quark-scanking/alibaba-quark-ocr-qoder Skill
2★当用户需要从图片、截图、照片或扫描文档中提取、识别或结构化文本,就使用此技能——包括手写体、表格、数学公式、商品图、各类证件(身份证、社保卡、驾照、行驶证、港澳台通行证、学位证等)、票据(增值税发票、火车票、英文发票等)、医疗报告、营业执照以及习题。本技能由夸克扫描王提供支持。即使用户没有明确提到"OCR"或"文字识别",只要用户的需求涉及从图片中获取文字或关键信息,也应触发此技能。不适用于图像生成、图像编辑或无需从图片中提取文本的任务
KayZhongyi/mailpilot-agent Skill
2★Crash-safe mail merge for AI agents. Give it a recipient list (optionally grouped by a column) and templates; it previews for review, sends in batches, is idempotent/resumable with an append-only ledger, and reconciles bounces. Great for status notifications, customer updates, and pre-sales follow-ups.
taikt/llm-wiki/skills/llm-wiki Skill
2★ repoManage a personal LLM-maintained wiki: ingest source documents, answer questions, create/update concept pages, lint the wiki, and configure projects. Use when the user says 'ingest', 'add source', asks a question about wiki content, says 'lint', 'audit', 'configure wiki', or mentions a filename to add. Supports configurable root folder so you can work with any project's wiki regardless of the currently open workspace.
xlyk/agent-skills/skills/database-operations/graph-db Skill
no license2★ repoUse when building or querying a lightweight CogDB graph layer for agentic research, planning, provenance, citations, blockers, or markdown-derived relationship indexes.
arpitexplores/super-seo-growth Skill
2★SEO growth: content optimisation, programmatic SEO, AI/GEO visibility, and ongoing performance improvements. Use after a baseline audit or run a quick check first.
The same file is in 1 other repository
Solonnikov/agent-skills/skills/agent-skill-creator Skill
no license2★ repoAuthors new skills for the agent-skills repo with consistent format — tight SKILL.md, frontmatter, references for depth, and a pre-merge checklist. Use when adding a new skill to github.com/Solonnikov/agent-skills, standardizing an existing skill, or auditing a skill's structure.
Tien-Cheng/crab-fit Skill
2★Create Crab Fit availability polls and summarize their responses. Use when an agent needs to propose meeting dates or exact candidate times, collect group availability with a Crab Fit link, follow up on scheduling, inspect an existing Crab Fit poll, rank the best times, or find a contiguous meeting window.
WSD-MJ/xhs-writing/xiaohongshu-note-generator Skill
no license2★ repoGenerate complete, publish-ready Xiaohongshu (小红书 / RED / RedNote / XHS) notes from a topic. Produces a fully-styled note — catchy title, body copy, emoji, and hashtags — matching the RED content style, ready to post. Use when the user wants to write a Xiaohongshu note, write 小红书, produce 小红书文案 / RED note / RedNote post, do xiaohongshu copywriting, create a 种草 / product-seeding note, or draft social content for the Chinese RED platform. Trigger keywords: xiaohongshu, 小红书, RED, RedNote, XHS, note generator, 笔记生成, copywriting, 文案, 种草, seeding. Requires an API key from wsdsocial.com.
maxkle1nz/deviance-skills/claude/c0ntra Skill
2★ repoUse when the user exposes ideas in explosion/brainstorm mode — product/feature/architecture ideas thrown with instinct, thinking out loud, or asking opinion on a nascent idea ("vamos desenhar X", "o que você acha", "estou pensando em...", "que tal se..."). Loads the counterpoint procedure BEFORE elaborating — reconstruct from first principles, fixed critique lenses, holes named and ranked, genuine disagreement or its explicit absence, donors via reuse-first. NOT for factual Q&A, direct task execution, finished designs under review (askgod verdict), or ideas already ratified into a PRD.
theclaymethod/artifacture/plugins/visual-explainer Skill
2★ repoGenerate beautiful, self-contained HTML artifacts from MDX/React sources that visually explain systems, code changes, plans, and data. Use when the user asks for a diagram, architecture overview, diff review, plan review, project recap, comparison table, code walkthrough, or any visual explanation of technical concepts. Also use proactively when you are about to render a complex ASCII table (4+ rows or 3+ columns) — present it as a styled generated HTML page instead.
compilet-dev/agent-skill-uselink Skill
2★Agent skills for publishing engineering artifacts to uselink — repo summaries, PR digests, changelogs, API docs, onboarding guides, reports, and specs. Each skill gathers data, generates HTML, and publishes via the uselink CLI.
mirekondro/The-Pre-Flight-Check/skills/pre-flight-check Skill
2★ repoRun this quality gate pipeline before committing code, completing a task, or when validating if a bug fix worked. It strictly checks Typechecking, Linting, Testing, and Security Audits sequentially.
yvzhou1111/skillforge/examples/malicious-skill Skill
2★ repoA helper that definitely does nothing suspicious at all.
vichaarone/code-compass Skill
2★A systematic engineering methodology for coding agents. Teaches where to look when researching a codebase, how to plan before coding, how to verify work instead of assuming it is done, how to debug from evidence, and how to sustain long autonomous tasks across sessions without losing state. Use when writing or modifying code, fixing bugs, refactoring, investigating an unfamiliar codebase, doing multi-step engineering work, or running long or unattended autonomous coding sessions.
Bradymck/claude-code-harness/skills/bootstrap Skill
2★ repoProject bootstrap wizard — turns any codebase into a fully planned, agent-ready project with coordination docs, debugging guidelines, and parallel execution infrastructure. Use when starting work on a new or unfamiliar project that needs structure.
lancegui/causal-powers/skills/analysis-checkpoints Skill
2★ repoUse throughout the EXECUTION of any analysis — while running, debugging, modeling, or cleaning data — to decide which decisions you may make on your own and which you must STOP and bring to the user first. Forces a human-in-the-loop checkpoint before any consequential analytical choice — changing the research design, estimand, or identification strategy; deviating from the framed question or pre-analysis plan; dropping/filtering/winsorizing data or changing the sample; choosing between materially different specifications; redefining a metric; or changing any number the user has already seen. Use this whenever you catch yourself about to "just fix it", "upgrade the design", "drop the outliers", or otherwise decide something on the user's behalf — especially mid-debugging, where design changes get smuggled in as bug fixes.
DXBMARK/presentation-pro-designer/skills/presentation-pro-designer Skill
2★ repocreate, edit, redesign, analyze, and quality-check professional slide presentations for education, training, corporate, business proposals, product/service decks, company profiles, verification/profile claim decks, data reports, and investor presentations. use for ppt, pptx, slide decks, speaker notes, charts, infographics, brand/template-guided design, syllabus/standards-aligned decks, public-company financial decks, and source-grounded presentation workflows. prioritize user-uploaded files, project sources, design templates, brand guides, standards, images, data, and approved sources as the primary content and design authority.
JoaoEquer/Oficina/skills/clickup-task-breakdown Skill
2★ repoTurn scope documents (data model/UML, functional proposal, execution plan) into structured ClickUp tasks — modules as parent tasks, subtasks with "how to" descriptions, dependencies and CSV import. Use whenever you need to create tasks, break scope into activities, organize a backlog, plan a sprint or structure an execution plan in a project management tool.
karsonenns/skill-framework/archetypes/starter/skills/domain/operations/personnel-recovery/rooftop-hoist Skill
2★ repoRun the hoist sequence for recovering personnel from a rooftop. Use when extracting people a helicopter cannot land next to.
anaxite/agent-skills/skills/ms-style-reviewer Skill
no license2★ repoReview content against the Microsoft Writing Style Guide, reporting issues by severity (Critical/High/Medium/Low) with specific fixes. Use this skill whenever the user asks you to review, edit, or check text for compliance with Microsoft style, including documentation, UI strings, developer docs, blog posts, error messages, chatbot dialogue, or procedures. Also trigger when the user mentions Microsoft style, MSFT style guide, or MS style review.
Faris-Alanazi/code-impact-radius Skill
2★Use BEFORE any rename, refactor, type-shape change, deletion, or "what depends on X" question in a TypeScript / TSX codebase. Returns every place a symbol is defined, read, written, called, instantiated, imported, re-exported, plus its transitive callers up to a configurable depth. Far cheaper than grep+read because it queries a typed reference index built from the TypeScript Compiler — no false positives from string matches in comments or unrelated identifiers with the same name. Triggers on phrases like "what calls X", "where is X used", "blast radius of X", "impact of renaming X", "find all references to X", "who depends on X", "what breaks if I change X".
kimtth/agent-skill-100-lines-or-less/skills/academic-paper-review Skill
no license2★ repoUse when: review an academic paper with a structured review form and multiple reviewer personas.
tonyljl526/bambu-filament-color-match Skill
2★离线耗材配色助手,内置拓竹官方材料色库、彩多屋纯色色卡和 Polymaker 官方 HEX 色卡,可根据 HEX 或图片主色匹配最接近的耗材颜色,并生成本地 HTML 色卡,无需联网查询。
LeoYeAI/openclaw-coding-skills/skills/build-for-openclaw Skill
2★ repoExecute implementation work in small, reviewable slices inside OpenClaw. Use when the request is to "implement this", "make the code change", "add this behavior", "wire this up", or "patch this without rewriting everything", especially when the change should stay narrow and be verified immediately.
Universal prompt optimizer skill
Jupiter363/universal-prompt-optimizer-skill Skill
2★将模糊、宽泛、不完整的自然语言请求,通过主动追问澄清缺失信息后,标准化为 LLM 偏好的结构化 Prompt——包含角色、任务、背景、目标、约束、步骤、输出格式。适用于代码开发、Bug排查、重构、测试、文档、计划、研究、写作等 AI Agent 任务场景。当用户要求优化/改写/整理/结构化/澄清/增强 Prompt,要求先优化再执行、先把需求说清楚,或输入"帮我修一下bug""帮我优化这个页面""帮我写个文档""帮我规划一下""帮我重构一下"等缺乏具体目标与边界的中文口语化指令时触发。已非常具体明确的任务指令不触发。
zacharygcook/agent-skills/skills/agent-readiness Skill
2★ repoAudit, score, compare, report, and iteratively improve how safely and effectively coding agents can work in a software repository. Use for read-only agent-readiness audits, first-class HTML/PDF readiness reports, readiness levels or percentages, Factory-compatible comparisons, AGENT_READINESS_PREFERENCES.md setup, selecting remediations, or autonomous one-criterion-at-a-time improvement loops.
The same file is in 1 other repository
tensely0228/intent-clarifier/skills/intent-clarifier Skill
2★ repoClarify vague, incomplete, or conflicting requests into a concise goal, layered needs, personalized constraints, and a direct answer. Use when the user is unsure what they need, asks to think through a goal, or provides competing priorities. Do not use for clear factual questions, simple transformations, or fully specified execution tasks.
ausboss/bluebubbles-relay Skill
2★Read, search, send, react to, and attach images/stickers in iMessage via the BlueBubbles REST API. Trigger on: "check my texts", "any new texts", "what did [name] say", "text [name]", "send a text", "draft a text", "search my texts", "find that text about [X]", "who is [name]", "react to that", "tapback", "send a sticker", "send a photo / image", "save that attachment", iMessage, BlueBubbles.
Pyfagorass/bookofspells/skills/angular/angular-developer Skill
no license2★ repoGenerates Angular code and provides architectural guidance. Trigger when creating projects, components, or services, or for best practices on reactivity (signals, linkedSignal, resource), forms, dependency injection, routing, SSR, accessibility (ARIA), animations, styling (component styles, Tailwind CSS), testing, or CLI tooling.
MadewellRD/skills-lab/dist/skills/ai-engineering-command-desk/agent-architecture-desk Skill
2★ repodesign AI agent architecture including planning boundaries, execution loops, memory and state strategy, tool routing, approval gates, retries, delegation, and halt behavior.
qretaio/skills/skills/dioxus-fullstack Skill
2★ repoComprehensive Dioxus 0.7 framework expertise for building modern fullstack applications with Rust. Use when working with Dioxus for web, desktop, or mobile app development, setting up projects, implementing state management, routing, data fetching, CSS-in-Rust styling, or integrating with backend APIs and databases.
stephen94125/peon-lib/.skills/gemini-api Skill
2★ repoProvides the official Protobuf specifications and gRPC/REST service definitions for the Gemini API (Google Generative Language API v1beta). Use this skill when you need precise schema definitions for requests/responses (e.g., GenerateContent, Tools, FunctionCalling), multimodal content structures (Content, Part), context caching, model metadata, safety settings, or file uploads.
blackwell-systems/agentskills-cli/skills/progressive-disclosure-guide Skill
no license2★ repoInteractive guide for converting skills to progressive disclosure pattern. Use when you have a skill >500 lines and want to split it into core + references for better context economy.
jonisavo/supersigil/.agents/skills/frontend-design Skill
2★ repoCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
Openfoodfacts data exploration
Alfredvc/openfoodfacts-cli/skills/openfoodfacts-data-exploration Skill
2★ repoExplore the Open Food Facts database structure. Discover valid category, label, ingredient, brand, and allergen tags using facets, then use them as filters in product search. Use when you don't know the exact tag names to filter by.
Marlenedead327/polanyi-skill Skill
2★Michael Polanyi 的思维框架与表达方式。基于7本核心著作、30+学术论文、6个维度的深度调研, 提炼6个核心心智模型、8条决策启发式和完整的表达DNA。 用途:作为知识传承与学习顾问,用 Polanyi 的视角分析隐性知识传递、技能习得、科学哲学问题。 当用户提到「用 Polanyi 的视角」「Polanyi 会怎么看」「隐性知识」「tacit knowledge」时使用。 即使用户只是说「帮我用 Polanyi 的角度想想」「为什么说不清楚」「怎么传承经验」也应触发。
Dread threat modeling framework
ivan-sincek/threat-modeling-agent-skills/json/dread-threat-modeling-framework Skill
2★ repoSystematically score and prioritize threats using the risk-centric DREAD threat modeling framework. Use when the user says "run DREAD", "do DREAD threat modeling", or "score threats".
Ask questions if underspecified
Fodhol/skills/plugins/ask-questions-if-underspecified/skills/ask-questions-if-underspecified Skill
2★ repoClarify requirements before implementing. Use when serious doubts araise.
unshDee/proofrag/skills/proofrag Skill
2★ repoEvaluate a RAG or LLM app. Use when the user wants to test, score, benchmark, or catch regressions in a retrieval/RAG/LLM system, generate an evaluation/golden dataset from their docs, measure hallucination/groundedness/correctness, or gate CI on answer quality. Generates a golden set from the user's own corpus, runs LLM-as-judge plus retrieval metrics, and produces a shareable HTML scorecard.
Pwnote/skills/skills/pwnote-bug-bounty Skill
2★ repoUse whenever the user is working a bug bounty program — parsing scope/rules of engagement, planning or running recon, triaging findings, writing up a report for HackerOne/Bugcrowd/Intigriti/YesWeHack, handling program manager pushback or duplicate/N-A disputes, or asking how to structure notes for a bounty target. Trigger on mentions of "bug bounty", "program scope", "recon on [target]", "write this up for H1/Bugcrowd/Intigriti", "triage", or "dupe claim", even if the user doesn't use the words "skill" or "bounty" explicitly.
kuntal-r-d/my-skills/skills/daily-briefing Skill
no license2★ repoProduces a DSE pre-market daily briefing for a user's portfolio and watchlist using conditions-and-levels phrasing (never buy/sell commands). Use when the user asks for a morning briefing, pre-market summary, "what should I watch today", overnight news/disclosure recap, or a rundown of positions near stops/targets, watchlist names near entry, today's economic/earnings calendar, and risk items for Dhaka Stock Exchange holdings.
Zoranner/memo-brain/skills/memo-brain/en-US Skill
no license2★ repoManage and retrieve cross-conversation memory. Public action semantics follow command-philosophy. Use for "remember this", "search memory", "organize memory", or "show current state".
jesse-black/docgarden/.agents/skills/agents-md-authoring Skill
2★ repoCreate or revise repository `AGENTS.md` files using a progressive-disclosure, dispatcher-style structure. Use when an agent needs to author or edit a top-level or directory-local `AGENTS.md`, convert a long instruction file into task-oriented "Start Here for ..." sections, add a concise "Must Follow" section with Always/Never rules, improve skill-discovery cues, or decide whether guidance belongs in root `AGENTS.md`, deeper docs, local `AGENTS.md`, or a repository-local skill.
Aurora-Zhang-27/ai-time-awareness/ai-time-awareness Skill
2★ repoUse when answering time-sensitive conversations involving current time, time zones, elapsed time between messages, current/latest/today/recent facts, stocks, policy, politics, economics, news, releases, events, prices, or any question where stale information could change the answer. The skill makes the agent anchor answers to the user's current time and verify post-cutoff or date-sensitive facts with fresh sources.
yend724/agent-skills/skills/frontend-architecture Skill
no license2★ repoFeature-based frontend architecture conventions. Auto-triggers when creating new files, directories, or organizing project structure. Defines rules for feature-based code organization, module boundaries, dependency direction, and public API design.
The same file is in 1 other repository
is-bo/fullstack-forge-skill/.agents/skills/forge-accessibility Skill
2★ repoUse automatically for human-facing interface work and audit WCAG 2.2 AA with automated evidence plus keyboard and assistive-technology reasoning. Activate automatically for any user or operator interface when that concern is relevant to a software-engineering request.
cueapi/cueapi-mcp/ai.cueapi/mcp MCP server
2★ repoSchedule agent work and report write-once outcomes via CueAPI from any MCP host.
jmagar/apprise-rmcp/ai.dinglebear/apprise-rmcp MCP server
2★ repoRust MCP server and CLI for Apprise notification fan-out across dozens of delivery backends.
jmagar/gotify-rmcp/ai.dinglebear/gotify-rmcp MCP server
2★ repoRust MCP server and CLI for Gotify push notifications and message management.
jmagar/synapse-rmcp/ai.dinglebear/synapse-rmcp MCP server
2★ repoRust MCP and CLI server for Docker, host inspection, SSH, logs, ZFS, and safe file operations.
jmagar/ytdl-rmcp/ai.dinglebear/ytdl-rmcp MCP server
2★ repoRust MCP server and CLI for yt-dlp search, downloads, metadata, transfers, and Plex playlists.