The catalog
609,856 rows, by stacks then stars
perfect7613/dsa-system-design-optimizer/skills/dsa-system-design-optimizer Skill
2★ repoAudits real codebases for data structure, algorithm, database, caching, scalability, reliability, and AI-system design improvements. Use when users ask to reduce time or space complexity, find hot paths, choose DSA patterns, optimize queries, improve architecture, scale a product, review infra, design RAG/agent systems, or create a measured performance roadmap.
yinguangyao/evidence-first-skill Skill
no license2★Use when 处理任何需要交付结论或产出物的非琐碎任务(调研、分析、排查问题、写方案、写文档、编码),尤其当任务带时间压力("快点、直接给答案")、信息来源可能互相矛盾、被要求汇报数字或事实、或产出要给他人做决策依据时。也用于用户想把这套工作方式移植到其他模型(取 portable 文件)。
The same file is in 1 other repository
srimon12/qql-go/skills/qql-skill Skill
2★ repoUse QQL to manage collections, insert documents, search, filter, rerank, recommend, and more. Use when Codex needs to write or review QQL statements for the Go CLI.
ethanolivertroy/mischief-managed Skill
2★Use when finishing a Pi, Codex, Cursor, Claude, or other coding-agent session and wanting to save a lean Markdown session note into your Obsidian vault with decisions, code changes, validation, caveats, and follow-ups.
Beichen-H/Loopower/skills/prompt-to-loop-engineering Skill
2★ repoUse when a natural-language task must be converted into a role-neutral, statically validated one-shot plan, workflow, or agent-loop specification before any user-task execution begins.
Jared13PG/ai-engineering-workflow/.agents/skills/ai-engineering-workflow Skill
2★ repoUse this skill for complex coding, coursework, data analysis, notebook, research, or multi-file projects that need structured issue creation, context analysis, task breakdown, atomic execution, verification, status tracking, and final closure.
hannsxpeter/godplans/skills/godplans Skill
2★ repoProduce an audit-aware, agent-executable master plan (PLAN.mdx) for a software project before application code is written. One command runs discovery, forces hard-to-reverse decisions, and plans product, architecture, roadmap, stack, repo, build, deploy, observability, launch, security, code quality, style genome, database, LLM integration, SEO, UI, UX, and agent memory upfront. After-the-fact audit checks become plan-time acceptance criteria, and a self-contained validator enforces task structure and approval state. Use when the user says: plan this project, godplans, master plan, plan everything upfront, idea to plan, plan before code, audit-aware plan, replan, or starts a greenfield project or major feature. Refuses plan theater (sections filled, decisions absent), vague tasks without verification, unsupported quality guarantees, and projects whose core purpose violates the Anthropic Usage Policy.
carinyaparc/skills/agents/skills/skill-review Skill
2★ repoUse when the user wants to research, review, or enhance an agent skill on a regular cadence — weekly skill uplift, audit a SKILL.md against best practice, compare with popular external skills, fix working issues, or align with agentskills.io. Triggers on "review this skill", "enhance the X skill", "weekly skills review", "uplift this skill", "align with agentskills.io". Works on one skill or a batch. Do NOT use to create a skill from scratch (create-skill / author a new skill), route which skill to use (skills-index), or review product documentation (docs-review).
bogdanbaciu21/skills/agent-coordination Skill
2★ repoCoordinate a deliberation across multiple AI agents (Claude, Gemini, Codex, Cursor, Antigravity, etc.) using a shared markdown log. Teaches Claude to read the full log before responding, append entries with the locked preface format, follow the phase model (Research → Converge → Stabilize → Action-List → Approval → Execute → Closeout), enforce the approval gate, and hand off cleanly to the next named agent. Also scaffolds a new coordination session on request. Triggers on "agent coordination", "coordination session", "multi-agent", "round-robin", "files-received", or any mention of `agent-research/agent-coordination.md` or `agent-research/files-received/`. SKIP for generic single-model multi-turn work — this skill is only for sessions where the human is brokering between multiple distinct AI agents through a shared file.
chenfei462/packsmith/examples/research-launchpad/skills/github-demand Skill
2★ repoResearch GitHub demand signals, active issues, and trend velocity before committing to a product direction.
frankxai/affiliate-agent-skills/skills/affiliate-audit Skill
2★ repoMap which content mentions paying AI tools but lacks affiliate links, and which programs to join first. Use when monetizing AI-tool comparison content, choosing affiliate programs, or auditing a passive-income site's link coverage.
The same file is in 1 other repository
jayjeo/econometrics-phd-level-skill/skills/econometrics-phd-level Skill
2★ repoPhD-level econometrics skill distilled from a 12-lecture Korean series (수학없는 쉬운 계량경제학, 2026-03-11 to 2026-04-29). Progressive Disclosure router covering OLS mechanics & OVB, exogeneity assumption hierarchy, inference (SE/t/p/CI), multicollinearity, dummies & interactions, polynomial/log functional forms, panel data with fixed effects, IV/2SLS/GMM, Difference-in-Differences (DiD), Regression Discontinuity (RD), MLE/Logit/Probit, and STATA command interpretation. Triggers on any of these topics, on specific lecture dates (260311~260429), or on the lecturer's signature analogies (taste/맛 analogies, Gangbuk-Gangnam metaphor, 단물 sweetness extraction). The body is a decision tree; actual derivations, examples, and STATA code load from references/*.md.
mrloldev/artificial-analysis-skill Skill
2★Pick the right LLM or media model for a task, backed by live benchmark data from artificialanalysis.ai. Use when the user asks "which model should I use for X", "what's the best/fastest/cheapest model", "compare model A vs B", "model leaderboard", or anything about model intelligence / speed / price / context / coding-or-math ability. Also for text-to-image, image-editing, text-to-speech, text-to-video, and image-to-video rankings. Triggers on "which model", "best model for", "cheapest LLM", "fastest model", "compare models", "model pricing", "artificial analysis", "MMLU score", "model ELO".
jukrap/ai-agent-playbook/skills/ai-harness/agent-orchestration-handoff Skill
2★ repoUse when splitting work across agents, subagents, workers, review passes, or long-running handoffs.
mmnaderi/localwp-cli-skill Skill
2★Use when WP-CLI, MySQL, Composer, or PHP must run inside the environment of a site managed by LocalWP on macOS. Guides agents to run the zero-config localwp-wpcli.sh helper script to execute commands in the correct site environment automatically.
osseous/skills/skills/read-ue-logs Skill
2★ repoRead and filter Unreal Engine log output from disk for any UE project. Auto-detects the project from the nearest *.uproject, merges entries across all concurrently-active log files (editor session, standalone clients), and surfaces only recently-active sessions by default. Use when diagnosing a silent failure after a repro, checking startup warnings, inspecting what UE printed for a recent gameplay action, or analyzing multi-client test runs.
m1crodevil/hermes-video-rs/skill/watch2 Skill
2★ repoRust-powered video analysis for AI agents — transcript-first with scene detection
seatlayer/seatlayer-ai-toolkit/skills/integrate-seatlayer Skill
2★ repoAdd, review, diagnose, or verify SeatLayer integrations inside existing applications. Use for managed hosted booking, direct links, embeds, Organizer Websites, Buyer SDK installation, SeatPicker or SeatingChart, mobile SDKs, server SDKs, custom checkout, holds, private or partner sales, buyer access sessions, channels, workspaces, Embedded Designer or control room, webhooks, analytics, checkout recovery, go-live review, and SeatLayer-related code generation or troubleshooting.
nchemb/neej-frontend-craft Skill
2★Comprehensive frontend design and implementation skill for building production-grade, visually distinctive UIs. Combines design intelligence, personal aesthetic preferences, animation patterns, and self-evaluation into a single unified workflow. Use this skill whenever the task involves building, designing, reviewing, or improving any frontend — landing pages, dashboards, SaaS interfaces, marketing pages, component libraries, or full application UIs. Triggers on any mention of UI, frontend, landing page, dashboard, design, layout, styling, animation, component design, or visual polish. Also triggers when reviewing or critiquing existing frontend code for quality. This skill should be used INSTEAD of frontend-design, ui-ux-pro-max, or ui-animation when they are available — it supersedes and unifies all three.
hoiung/sst3-skills/plugins/design-fidelity/skills/design-fidelity Skill
2★ repoSST3 Skills — Claude Code plugin marketplace. Ralph Review Trio (Haiku → Sonnet → Opus, restart-on-fail) + more packs coming.
mishanefedov/skillrot/examples/stale-skill Skill
2★ repoA deliberately out-of-date example skill, for the skillrot README/demo. Each bash command below uses a flag the installed CLI does NOT accept (a renamed or removed flag) — exactly the silent drift skillrot catches. Run: `skillrot examples/stale-skill`.
ainova-systems/intelligence-dev-packs/packs/core/skills/dev-handoff Skill
2★ repoCompact the session into a self-contained continuation prompt for a fresh agent session
lishix520/jtbd-skills/principles Skill
2★ repoShared principles, terminology, evidence discipline, and core contracts for all Jobs-to-be-Done (JTBD) and Outcome-Driven Innovation (ODI) agent skills.
blackwell-systems/polywave-codex Skill
no license2★Coordinate Polywave scout and wave flows in Codex. Use for parallel implementation planning, IMPL creation, and guarded wave execution with polywave-tools and the installed Polywave agents.
luisnavarrete12/threejs-ai-skill Skill
2★Makes AI-generated Three.js / WebGL / react-three-fiber code produce coherent, playable 3D scenes instead of code that compiles but looks and feels broken — correct model scale and orientation, grounded and non-overlapping placement, real collisions, frame-rate-independent controls, and characters that walk without sliding or floating. Use this whenever the work touches Three.js, react-three-fiber, or WebGL: creating, reviewing, or refactoring a scene, world, or game; loading GLTF/GLB/FBX models; setting up cameras, controls, lighting, shadows, or physics; adding player movement or character animation; or debugging why a scene looks wrong — objects at the wrong size, floating, clipping through each other, facing the wrong way, a broken-looking camera or lighting, or a character that slides or floats. Apply it even when the user just says "make a 3D scene/world/game" without naming these problems — these rules prevent the most common silent failures in generated 3D code.
knowhowlab/agent-testkit/skills/test-e2e Skill
2★ repoExecute the repository's TESTS_E2E.md plan as a complete, autonomous end-to-end integration test — every phase sequentially, failures investigated and fixed immediately, everything logged to a timestamped protocol file. Use when the user asks for an e2e test, a full integration run, acceptance testing, stack verification, a regression run, or to "run the test plan" — with optional scope arguments like quick, no-build, or keep-up.
zbflcy/tui-use/tui-use Skill
no license2★ repoOperate TUI (terminal user interface) programs through the tui-agent CLI tool. Use this skill whenever the user asks to interact with, automate, control, or test any terminal-based program — including editors (vim, nano, emacs), system monitors (htop, top, btop), file managers (ranger, mc), database clients (mycli, pgcli), or any ncurses/TUI application. Also trigger when the user mentions tui-agent, screen capture of terminal programs, sending keystrokes to running programs, or automating terminal workflows. Even if the user just says "open vim and edit a file" or "check what's running in htop", this skill applies.
adtn0810/truestack/skills/truestack-agent-coordination Skill
2★ repoCoordinate multiple agents and multiple sessions on the same repo without overwriting or colliding with each other. Use whenever work is big enough to split across parallel agents, when a research or planning task is explicitly split across parallel sub-agents (the research content itself belongs to truestack-deep-research), or when continuing work another session started. Covers task decomposition, worktree isolation, a shared task ledger, and the merge protocol.
youseiushida/benkyo/.claude/skills/benkyo-graph-edit Skill
2★ repoEdit the structure of a benkyo concept/problem graph — add or remove nodes and edges, adjust granularity, fix duplicates. Use this skill when the learner says 「これも追加して」「これとあれは関連してる」「これは別物」「これも勉強したい(新概念)」「これとこれ同じ」「これは分けるべき」, or when you (the tutor) notice during a session that a concept the learner just mentioned isn't in the graph yet, or that a relationship between existing nodes is missing/wrong. Also trigger when reviewing or refining the graph structurally — e.g., during project init when assessing the initial set of nodes.
Docx batch variable replacement
kuliantnt/docx-batch-variable-replacement Skill
2★批量替换 docx 文档中的变量、占位符、甲乙方名称、项目名称等内容时使用。
apostl-dev/apostl-skills/skills/sdk-onboarding-audit Skill
2★ repoDemo/onboarding review for SDKs, CLIs, API clients, agent skills, and quickstarts. Use when a team launches a developer-facing product and the user wants a clean-env proof pass that turns first-run failures into command-level repros, an onboarding scorecard, a founder-readable report, and a release-readiness fix map. Also use as a lightweight free preview for continuous release-readiness checks.
gtskevin/ob-methods-results-check/skills/ob-methods-results-check Skill
2★ repoAudit organizational behavior, management, HRM, and work-psychology manuscript Methods and Results evidence before submission. Use when checking full manuscripts, methods/results sections, tables, figures, appendices, field surveys, experiments, mediation, moderation, CFA, SEM, multilevel reporting, statistical consistency, or causal claims.
sfrangulov/skills/book-to-skills Skill
2★ repoDistill a book, long-video transcript, podcast, course, or interview into a coherent set of executable agent skills. Use when the user asks to "distill this book into skills", "turn this video/podcast/course into agent skills", or wants the frameworks, principles, and methodologies in long-form content extracted into atomic, reusable skills an agent can invoke in real situations. NOT for plain summarization, book reviews, or role-playing the author.
caoyuan-fire/engi-foundry-skill/skills/engifoundry-audit Skill
2★ repoClassify new EngiFoundry work as direct Agent action, Package orchestration, or factually blocked before a Package exists. Use when deciding whether new work needs Orch.
Imtylerrrrrr/TK/en Skill
2★ repoUse when starting or joining a team project or competition repository and collaboration rules need to be set up — commit/PR/branch conventions, agent context files, GitHub merge settings. Triggers — new hackathon/competition repo, "collaboration rules", "commit convention", "PR rules", "set up team repo", team develops with coding agents (Claude Code, Codex, Cursor, Gemini CLI).
rumotion/ai-agent-project-template/.agents/skills/code-reviewer Skill
2★ repoReviews code changes for correctness, maintainability, security, performance, tests, and adherence to project rules. Use when reviewing diffs, PRs, or completed agent work.
Solatrader/syft-news-cli-assistant/.github/skills/syft-cli-assistant Skill
2★ repoUse when the user needs help installing, authenticating, troubleshooting, or using the local `syft` CLI for Syft AI news workflows. Trigger for first-time setup, `syft login` or `syft status`, followed-topics inspection, top stories, personal search, global search, Codex skill installation via `syft install-skill`, or any request asking which Syft CLI command to use.
osodevops/keito-skill/keito-time-track Skill
2★ repoTrack billable AI coding-session time to Keito through the Keito CLI. Use when the user asks to set up repository time tracking, install or configure the Keito skill, log agent work, check tracking status, pause or resume tracking, disable tracking, or review today's source=agent time entries.
hannsxpeter/arc-ready Skill
2★Plan, build, ship, and audit software across the full idea-to-launch arc: PRD, architecture, roadmap, stack, repo, implementation, deploy, observability, launch, and hardening. Use for greenfield kickoff, brownfield gap filling, retroactive artifact audits, multi-repo suites, or requests to write a PRD, design architecture, choose a stack, scaffold a repo, build a web app, API, CLI/SDK, mobile or desktop app, data/ML system, or infrastructure project, add CI/CD or SLOs, launch a product, or run an OWASP or compliance review. Routes by product form, archetype, industry, and regulatory overlay; preserves stable tier artifact paths; enforces disk-backed completion, upstream grounding, vertical slices, real backends, tested rollback, and a hardening recheck immediately before public release.
RainSunMe/toolcapsule/.github/skills/toolcapsule-release Skill
2★ repoUse when: developing, validating, publishing, deploying, or maintaining ToolCapsule; GitHub repo setup, Vercel deployment, npm Trusted Publishing, release tags, domain checks, Dependabot cleanup, CI failures, and launch workflow.
FarhanMalik082/creator-scout/.commandcode/skills/creator-scout Skill
2★ repoDiscover dev-focused YouTube channels worth pitching for a dev tool brand, using content-based discovery. Use when the user asks to find YouTubers to sponsor, discover dev creators, build an influencer outreach list, or prospect YouTube channels similar to a set of seed channels. The tool extracts topics from seed channels' recent video titles, searches YouTube for channels covering the same topics, and ranks candidates by topic overlap, size, and activity.
14790897/my-skills/public/daily-new-record Skill
no license2★ repoAI Agent 实习生每日新增事项记录生成器。用户输入今天的新发现、新问题、新知识、新资产等,AI 按结构化模板输出完整记录,直接输出到对话中,不创建文件。记录重点是可复用性,不是流水账。
0xherve/qa-skill/skills/qa Skill
2★ repoAssist a QA engineer by navigating the app, drafting test cases from requirements, executing them, and recording results — with the human in the loop for judgment.
guofu-shiqu/ux-expert-skills/skills/exp-asset-accumulation Skill
2★ repo体验资产沉淀。当一次体验分析或服务复盘产生了可复用的场景、规则、话术、指标或案例时调用。
Ai startup due diligence skill
PiroteQueen/ai-startup-due-diligence-skill Skill
2★Evidence-driven due diligence for AI startups: turns decks, interviews, demos, and public research into an auditable evidence ledger, then derives a verdict and decision documents. Use when evaluating an AI startup or investment target, reviewing a pitch deck or data room, comparing companies' AI products, preparing investor or founder questions, writing a DD memo or IC note, or assessing VC-fit, PMF, GTM maturity, fundability, and red flags.
b2bforce/b2bforce/.agents/skills/client-account-plan Skill
2★ repoMap an account's buying committee and build expansion hypotheses from the firm's services this client has not bought, each with a trigger that says when to raise it. Use for account planning, expansion or cross-sell planning, or when asked where growth in the existing client base could come from.
ProdaZhang/aigd/aigd-concept Skill
2★ repoAIGD Phase 1 · brainstorming & top-level design. Use this when you want to set the concept for a new game, fix the core loop / platform / target users, or split the game into a system list + dependency graph and start the project spine. Produces / revises the project charter + manifest (system list). Part of the aigd package; methodology in ../aigd/references/.
gunwoo55/adaptive-token-efficiency Skill
2★Escalation-only workflow for materially ambiguous, research-heavy, high-impact, cross-system, or failed-validation tasks. Do not load for clear, bounded, low-risk work; use the AGENTS fast path.
jasonChen0604/codebase-to-portfolio/skills/batch-init Skill
2★ repoBatch-initialize project docs for valid projects in projects-list.md that are missing a doc file or have an outdated version. Triggers when the user says "batch init", "batch initialize", "update project docs", "批次初始化", or "initialize unfinished projects".
SmallNoc/noc-living-docs/.agents/skills/project-living-docs Skill
no license2★ repoUse for AI-assisted code changes that must keep project living docs in sync. Triggers on feature work, bug fixes, refactors, API/schema/security/deployment changes, requirement updates, tests, guardrails, and change records. Do not use for general Q&A or non-project snippets.
shiquda/skills-sync/skills/skills-sync Skill
no license2★ repoManage, upload, and version local Agent Skills with the `skills-sync` CLI. Use this skill whenever the user wants to scan local/global/project Skills, upload selected Skills to a private or public GitHub skill repository, automate non-interactive Skill syncs, inspect remote Skill metadata/history, remove or restore repository Skills, or troubleshoot `skills-sync` workflows.
3yesore/LetUenforskills/examples/sample-skill Skill
2★ repoDemonstrates the Agent Skill Anatomy harness with a tiny local skill.
OthmanAdi/chronos Skill
2★Gives AI coding agents temporal awareness via a hook-backed ledger and decision rules. Activates whenever an agent reasons about recency, retry windows, memory staleness, deploy cooldowns, idle detection, or any "when / how long ago" question. Required for autonomous or long-running agents.
008993368-yaz/Growth-Scout Skill
2★Agent-agnostic skill that recommends what feature a product should build next by combining codebase analysis, product context, competitor gaps, market signals, growth scoring, and implementation feasibility. Use when the user asks what to build next, wants growth opportunities, competitor gap analysis, a growth roadmap, market scouting, feature prioritization, or turning an opportunity into a PRD or GitHub issues. Works in any coding agent.
leafyuan1988/wechat-miniprogram-ai-skill/skills/wechat-miniprogram-ai Skill
2★ repo用于将微信小程序接入微信小程序 AI,判断自动模式/开发模式,生成或审查微信 AI SKILL、原子接口、原子组件、mcp.json、app.json agent 配置、wx.modelContext 用法、pageMetadata、知识库、调试与评测;also trigger for WeChat Mini Program AI developer mode, automatic mode, atom APIs, atom components, MCP integration, and wxa-skills evaluation.
Bmob cloud function development
bmob/agent-skills/skills/bmob-cloud-function-development Skill
2★ repoWrite, upload, and verify Bmob server-side cloud functions using the Bmob MCP server when available. Use when the user asks to 编写云函数, 写云函数, 上传云函数, 部署云函数, 发布云函数, 验证云函数结果, or mentions `function onRequest(request, response, modules)`.
AIwork4me/open-llm-wiki/skills/query-writeback Skill
2★ repoAnswer cross-source questions about an open-llm-wiki vault and optionally write reusable synthesis back into concept pages. Use when the user asks a wiki question that requires comparing, connecting, or tracing multiple source/concept pages. By default answer first and propose writeback; modify files only when the user explicitly asks for writeback, pre-authorizes wiki growth, or approves the proposed changes.
gg-mo/repo-hygiene/skills/cleaning-existing-codebase Skill
2★ repoUse when the user asks to "clean up", "apply repo-hygiene to", or "fix the hygiene of" an existing codebase — orchestrates the other hygiene skills in a phased, reviewable order rather than firing a 200-file mega-diff
emekdahl/skills/skills/grouchy-mentor Skill
2★ repoBattle-hardened senior engineer who reviews plans and code before they cause a 3 AM incident. Stress-tests architecture, catches data-pipeline fragility, flags security gaps, and calls out missing error handling, then signs off with a severity summary and grudging approval if earned. Use when reviewing new or existing plans, specs, design docs, PRs, or diffs.
wangxuan200105-sudo/network-radar/plugins/network-radar/skills/network-radar Skill
2★ repoDiscover, verify, prioritize, and organize professional contacts from authenticated web pages, search results, profile links, or existing contact spreadsheets. Use when a user wants to build or update a networking candidate pool, find alumni or target-role contacts, audit missed relationship labels, compare old and new contact data, export a structured Excel/CSV table, or draft evidence-based outreach messages. Supports Maimai first and can extend to other professional-network sources.