The catalog
608,253 rows, by stacks then stars
epitech-toulouse/epitech-pre-eval Skill
no license0★Pré-évalue automatiquement un projet étudiant Epitech à partir d'un barème JSON et du code source fourni (repo GitHub, archive ZIP, ou clone local). Génère un compte rendu rapide, un rapport détaillé critère par critère et un fichier Excel exportable. Utiliser ce skill dès que l'utilisateur mentionne : "pré-évaluation", "barème", "corriger un projet étudiant", "vérifier les critères", "noter un rendu", "EIP", "regarde si l'étudiant a bien fait X", "vérifie que le projet respecte le barème", "prépare mon évaluation", "analyse de code Epitech".
Senior legal contract reviewer v1.2 lite
evan66547/Contract-Reviewer-Agent-Eval/skills/senior-legal-contract-reviewer-v1.2-lite Skill
0★ repo⚖️ Benchmark evaluation framework for AI-powered legal contract review agents, with 25 expert-crafted test cases aligned to Chinese Civil Code. | 面向 AI 法律合同审查智能体的基准测试框架,含25个专家级测试用例,对齐《民法典》及司法解释实务。
marcm8793/skill-forger/.claude/skills/git-commit Skill
0★ repoExecute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping
The same file is in 10 other repositories
kavins14/claude-goodness/skills/capture-session-learnings Skill
no license0★ repoAnalyze the current Claude Code session and identify useful patterns, workflows, or configurations worth saving to the claude-goodness repository. Use at the end of a session or after completing something useful.
ekreloff/adversarial-reviewer Skill
0★Adversarial code review that breaks the self-review monoculture. Use when reviewing code changes, before merging a PR, or when you suspect the AI is being too agreeable about code quality. Forces perspective shifts through three hostile reviewer personas that catch blind spots.
ekovegeance/agent-skills/skills/laravel Skill
no license0★ repoLaravel 13 conventions and best practices. Use when creating controllers, models, migrations, validation, services, or structuring Laravel applications. Triggers on tasks involving Laravel architecture, Eloquent, database, API development, or PHP patterns.
indigokarasu/weave Skill
0★Private provenance-backed social graph. Maintains queryable records of people, relationships, preferences, and shared experiences for recall, gifting, hosting, introductions, and serendipity. Use for storing or retrieving facts about a person, recording a relationship, or discovering connections between people. Not for sending messages (use Dispatch), calendar management (use Sands), OSINT research (use Scout), or web research without a social graph need (use Sift).
gigio1023/clear-writing/clear-writing Skill
0★ repoUse when creating, restructuring, rewriting, humanizing, or reviewing prose documents in English or Korean: README, guides, specs, API references, ADRs, memos, wiki pages, blog drafts. Covers de-AI-ifying tone ("humanize", "deslop", "AI 티 빼줘"), turning notes into standalone docs ("이 메모를 문서로"), surgical Korean polishing ("윤문해줘"), terminology review ("용어 이상한지 봐줘", "term check"), and repository-grounded doc authoring ("README 작성", "문서 정리해줘", "스펙 작성"). NOT for Python docstrings, prompt coaching, diagrams, PR/commit/issue copy, translation, or implementation changes.
thedevappsecguy/sec-skills/skills/devil-advocate Skill
0★ repoInterview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when the user wants to stress-test a plan, challenge their design, or says things like `devil's advocate`, `grill me`, `poke holes in this`, `challenge my thinking`, `interrogate my design`, or `stress-test this`.
Powerladder-Tech/Plugin/skills/golden-equilibrium-scoring Skill
no license0★ repoRun a Golden Equilibrium assessment on any business. Triggers when users ask "what's my score", "assess my business", "run Golden Equilibrium", "score my opportunity vs risk", "which Business Play am I", "am I ready to grow", "should I expand or play it safe", "what's my Opportunity Score", "what's my Financial Readiness Score", or any request to evaluate a business's strategic position using the OS/FRS framework. Use this skill proactively whenever a user shares enough business context to estimate scores.
ThanhTNV/Novel-Generator/.cursor/skills/novel-character-consistency Skill
no license0★ repoRetrieve and maintain character consistency in novel generation by querying Milvus for all passages mentioning a character. Ensures character traits, appearance, relationships, and voice remain consistent across thousands of tokens. Use when continuing a story, introducing recurring characters, or when the model generates new scenes involving existing characters.
Jeelislive/SkillPack/.agents/skills/deploy-to-vercel Skill
0★ repoDeploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".
chihebnabil/token-saver Skill
0★Reduce API token usage by eliminating verbose output while preserving code blocks and technical accuracy
indigokarasu/custodian Skill
no license0★Monitors agent gateway logs, cron jobs, skill journals, and OCAS data directories for operational failures. Detects errors, applies safe non-destructive fixes autonomously during quiet hours, and escalates only what it cannot fix. Performs root cause analysis on recurring errors with fix-loop detection and confidence-tier auto promote/demote. Use when: cron jobs fail or show stale errors, gateway logs show repeated error patterns, skill journals have gaps, disk usage exceeds thresholds, MCP servers crash-loop, or after any gateway restart. Keywords: cron health, log analysis, system monitoring, error fingerprinting, auto-repair, fix-loop detection, operational conformance. NOT for OKR trend analysis, skill design evaluation, behavioral lesson extraction, briefing delivery, entity knowledge queries, or social graph queries.
jovd83/defensive-appsec-review-skill Skill
0★Use when you need an authorized, non-destructive security review of repos, APIs, and cloud apps. Trigger for OWASP reviews, dependency/secret audits, scanner consolidation, and security reports. Use for AppSec triage. Do NOT use for offensive exploitation or unauthorized testing.
Eu ai act hitl oversight skill
jovd83/eu-ai-act-hitl-monitor-skill/eu-ai-act-hitl-oversight-skill Skill
no license0★ repoDesign, review, and retrofit human-oversight controls for autonomous agent systems with pause, review, resume, reject, or halt behavior. Use for EU AI Act Article 12/14 logging, human handovers, typed review-decision contracts, reviewer reports, timeout/escalation rules, or critiques of unsafe approval flows.
stephenrogan/csm-skills/skills/account-strategy-builder Skill
0★ repoDevelops a structured 90-day strategic plan for a key account by defining priorities, setting measurable objectives, mapping stakeholder strategy, and identifying risks and opportunities. Use when asked to build an account strategy, create an account plan, develop a strategic approach for a key account, set quarterly objectives for an account, or when moving from reactive account management to proactive strategic management. Also triggers for questions about account planning, strategic account management, quarterly account objectives, or how to develop a structured plan for a high-value customer.
subsquid-labs/skills/pipes-sdk Skill
0★ repoBuild, configure, deploy, and troubleshoot durable blockchain indexers with the Subsquid Pipes SDK (EVM, Solana, Tron, Bitcoin, Hyperliquid) when Portal MCP or curl previews are insufficient for backfills, recurring syncs, joins, app-owned data, or production analytics.
CorentinLumineau/gmail-assistant/skills/gmail-analyze Skill
0★ repoAnalyze Gmail inbox patterns to identify high-volume senders and suggest filter rules. Use when organizing email, creating automation rules, or understanding inbox composition. Works with personal Gmail accounts via gog CLI.
Harkirat155/ai-native/vscode-bridge Skill
0★ repoVS Code as a programmable backend for AI agents — full IDE power via JSON-RPC
mogglemoss/openclaw-birdbuddy-skill Skill
0★Query your Bird Buddy smart bird feeder - check status, battery, food level, and see recent bird visitors with species identification.
hi-space/strands-agentskills/docs Skill
0★ repoAgent Skills implementation for Strands Agents SDK
lu-zhengda/skill-port/test/fixtures/claude-skill Skill
0★ repoExplains source code with analogies and diagrams. Use when teaching architecture or onboarding developers.
chatmaterials/mechanics-analysis Skill
0★Use when the task is to analyze mechanics-relevant quantities from DFT results, including equation-of-state fits, EOS quality descriptors, bulk modulus estimates, elastic tensor summaries, elastic-stability heuristics, anisotropy and hardness descriptors, candidate ranking, stress-state interpretation, and compact markdown reports from finished calculations.
sskaye/email-triage Skill
0★Reads the user's Gmail inbox and classifies every email as Suspected Junk, Action Needed, Informational, Unknown, or a user-defined custom label based on a user-provided triage-rules.md file. Then applies Gmail labels and archives emails via a Google Apps Script web app. Use this skill whenever the user says "triage my email", "label my email", "sort my email", "clean up my inbox", "process my email", or anything that sounds like they want their inbox organized, filtered, or prioritized. Also trigger if the user mentions email labeling, email archiving, or inbox zero workflows.
planifest/planifest-framework/plan/_archive/0000003-hook-based-enforcement-2026-04-20/external-requirements Skill
0★ repoPhase 7 only — raises the PR, writes the changelog, handles skips, and archives plan/current/. Invoked by the orchestrator at the end of the feature pipeline.
Pratiyush/skill-sdk/examples/basic-skill Skill
0★ repoA minimal example skill that demonstrates the Agent Skills format. Use when learning how to create skills.
badass-courses/a11y-agent/.claude/skills/a11y-advocate Skill
no license0★ repoBuild accessibility culture and communicate with stakeholders. Generate statements, prioritize issues, write tickets, create team checklists, produce risk assessments. Use when asked to "prioritize a11y", "accessibility statement", "convince PM about a11y", or "create testing process".
pvergaraf/chart-skill/skills/chart Skill
no license0★ repoGenerate minimal, clean charts using QuickChart.io with a modern light/dark palette and DM Sans typography. Supports bar, line, area, pie, and more. No dependencies required.
brlin-tw/searching-ubuntu-packages Skill
no license0★Provide guidelines on how to search the proper Ubuntu package name for a given Ubuntu release. Should be used when searching for package names or updating package names to newer releases.
eriksjaastad/state-business-tax-skills/skills/de-grt Skill
0★ repoDelaware Gross Receipts Tax calculator for businesses. Computes tax by business category (0.0945%-1.9914%) with monthly exclusions. Triggers on Delaware gross receipts, Delaware business tax, Delaware GRT.
chatmaterials/topology-analysis Skill
0★Use when the task is to analyze topological quantities from DFT or Wannier-based outputs, including compact topological invariant summaries, Wilson-loop winding summaries, surface-state or arc-spectrum summaries, evidence consistency scoring, mode-specific candidate ranking, and markdown reports from finished calculations.
mahavirteraiya/tidy-laptop-folders Skill
0★Organize messy laptop folders like Desktop, Downloads, and Documents into smart categories. Scans your folders, groups files by purpose and content, and creates a clean structure with dynamic depth based on how many files you have. Works on macOS, Windows, and Linux. Always asks before moving anything.
thierryteisseire/leadgenius-cli Skill
0★Manage B2B leads, enrichment, AI scoring, and sales automation via the LeadGenius Pro platform. Use when the user asks to find leads, enrich contacts, score prospects, manage campaigns, import CSV leads, provision users, run FSD pipelines, check EpsimoAI credits, manage territory companies, or interact with the LeadGenius API. Also use when the user mentions "lgp", "LeadGenius", "lead enrichment", "lead scoring", "ICP", "FSD pipeline", "territory companies", or "EpsimoAI".
arc-claw-bot/arc-shield Skill
no license0★Output sanitization for agent responses - prevents accidental secret leaks
brothaakhee/superclaw Skill
no license0★Complete software development workflow enforcing design → plan → execution with checkpoints
winetree94/devtools/skills/commit-and-push Skill
0★ repoCommit
ZZy979/agent-demos/langchain/skill/skills/langgraph-docs Skill
no license0★ repoUse this skill for requests related to LangGraph in order to fetch relevant documentation to provide accurate, up-to-date guidance.
MasahiroSakoda/skills/skills/chezmoi Skill
0★ repoManage dotfiles with chezmoi. Use when working with chezmoi config, setup, or repo structure, managing files, templates, or script's (Go template syntax, run_once_/run_onchange_ scripts, .chezmoidata), handling file attributes (symlinks, permissions, encryption, external sources), Troubleshooting chezmoi operations or understanding application order.
michelve/hugin-v0/skills/accessibility Skill
0★ repoUse this skill for any accessibility concern: WCAG compliance (any success criterion including SC 1.3.5 autocomplete, SC 2.4.11 focus obscured), ARIA roles/attributes, screen reader behavior, axe-core or WAVE audit failures, color/non-text contrast, keyboard navigation, focus trapping/management, skip links, touch targets, VPAT reports, or accessible form patterns. Also trigger when a user asks whether a UI library (DSAI) handles keyboard interactions — but only if the question is specifically about accessibility behavior, not general usage. Do NOT trigger for general component usage questions where keyboard behavior is incidental (e.g., "does DSAI Tooltip show on hover and focus?" without an accessibility problem to solve).
woyxiang/skills/skills/freebasic Skill
0★ repoFreeBASIC programming language skill for AI code assistants
zhutao100/prek-agentic-onboard-skill/prek-agentic-onboard Skill
0★ repoOnboard or migrate repositories from pre-commit to prek, including workspace-mode polyglot setup and agent-friendly auto-format+auto-stage commit convergence (global shim or per-language wrapper hooks).
lunaticfluker/claude-web-remote Skill
0★Set up remote browser access to Claude Code and dev site preview from any device (iPad, phone, another computer) with QR codes. Use when the user wants to access Claude Code remotely, work from a tablet or phone, or set up browser-based terminal access.
keman-ai/harness-skill Skill
no license0★Use when setting up AI-agent-friendly engineering infrastructure for a project — AGENT.md navigation, harness/ knowledge base, mechanical constraint scripts, and agent team role definitions. Trigger when user says "setup harness", "build harness engineering", or asks to make a project agent-navigable.
tdw419/glyphlang Skill
no license0★AI-first backend programming language with spatial assembly substrate. Use when building APIs, backend services, or spatial computation programs with GlyphLang, compiling .glyph files, or working with the Geometry OS stack.
avantika-msr/agent-skills/repo-setup Skill
0★ repoAutonomous local development environment setup agent. Use this skill whenever a user wants to clone a repository and get it running locally, set up a dev environment for a project, install dependencies for a codebase, or run a project from a GitHub URL or repo name. Triggers on phrases like "set up this repo", "clone and run", "get this project running", "set up my dev environment", "help me run this locally", repo URLs (github.com/...), or org/repo-name patterns. Also use when a product manager, designer, or new team member wants to run a project locally and needs hand-holding through the process. This skill runs commands itself rather than listing them — it is an autonomous agent, not a tutorial. Even if the user just pastes a GitHub URL with no other context, use this skill.
ragnos-labs/agent-skills/skills/ship Skill
0★ repoRelease workflow that takes a branch from done coding to reviewed, committed, pushed, and PR-ready. Works with Claude Code and Codex.
mifunedev/skills/skills/agent-browser Skill
0★ repoOpen a URL in the headless agent-browser, with a preflight health check. Verifies agent-browser is installed and Chromium launches before navigating. Errors out with a diagnostic trace if anything fails. TRIGGER when: asked to open a page, browse a URL, take a screenshot, or test a site with agent-browser.
xing-yiren/earth-online-skill/.claude/skills/earth-online-skill Skill
0★ repo把日常任务、晨间签到、积分、成就和奖励组织成“地球Online闯关”式体验。 当用户说“早安”“今天有什么任务”“我今天要做某事”“我完成了某事”“今天结算”“我想兑换奖励”时使用。
chokwinlee/repo-context/skills/repo-context Skill
0★ repoBuild and maintain a repo-local progressive context pack for large, legacy, or weakly documented codebases, especially when plain file discovery may miss relevant paths behind `.gitignore`. Use when an agent needs a repo map, hotspot analysis, module/file briefs, legacy-service onboarding, or better context discipline before non-trivial multi-file work and refactors.
james-chien/summarizer-skills Skill
0★Produce faithful, information-dense summaries from raw text and return them as structured JSON for both human and agent consumption. Use when Codex needs to summarize articles, documentation, code explanations, transcripts, notes, or similar text into a consistent schema with a short summary, key points, entities, actionable insights, and a confidence score.
William-Yeh/hackmd-to-pptx/skill Skill
0★ repoUse when converting HackMD/Marp markdown slides to PowerPoint presentations, or when merging multiple HackMD/Marp decks into one combined deck.
leocarsons/outclaw/.claude/skills/outclaw Skill
no license0★ repoManage Claude Code skills using the outclaw CLI - create, install, list, search, and publish skills
jeffchen006/skills/.agent/skills/algorithmic-art Skill
no license0★ repoCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
The same file is in 33 other repositories
jiangyinzuo/agentic-software-engineering/cli-tools Skill
no license0★ repo当前环境下已安装的通用命令行工具
LoogacyStudio/skills/.agents/skills/create-reusable-skill Skill
0★ repoCreates or upgrades reusable agent skills by selecting the right skill pattern, generating the minimum useful file structure, drafting SKILL.md, and validating the result before returning it. Use when building a new skill, refactoring a weak skill, or scaffolding companion references and assets.
bowen31337/long-running-agent-skill Skill
0★Build autonomous, long-running AI agents that parse PRDs/specifications into structured task lists and execute them autonomously with state persistence, error recovery, and cross-session resumption. Works with any agent framework (Cursor, OpenCode, etc.).
The same file is in 1 other repository
sametcn99/product-planning-copilot/.github/skills/prd-planning Skill
no license0★ repoUse when creating, refining, or validating product planning documents (project brief, PRD, roadmap, architecture notes, task breakdown, risks).
xainflow/skills/skills/official/background-batch Skill
0★ repoRemove backgrounds from multiple images in batch. Processes a folder or selection of assets and saves results in a dedicated folder.
AtlasPA/openclaw-action Skill
no license0★GitHub Action for automated security scanning of agent workspaces. Detects exposed secrets, prompt/shell injection, and data exfiltration patterns in PRs and commits.