The catalog
609,689 rows, by stacks then stars
steadwing/agent-skills/skills/steadwing Skill
2★ repoUse when the user asks to run Root Cause Analysis (RCA), debug a production incident, analyze an error log or stack trace, or trigger Steadwing. Also use when a production-style error (traceback / unhandled exception / stack trace) is surfaced and the user wants automated investigation. Handles agent registration, authentication, optional auto-detection hook setup, and RCA triggering via the Steadwing API.
coachmanjeet/agilefitness/skills/fitness-wellness Skill
no license2★ repoAgilefitness Book: Fitness and Wellness for the modern human
lhohan/claude-code-plugins/skill-evaluator/skills/skill-evaluator Skill
2★ repoHans' reusable Claude Code commands, skills, hooks, etc
The same file is in 2 other repositories
mikamboo/agent-skills/skills/tech-blog-writer Skill
no license2★ repoAI Agent SKILLS
alexsmedile/apm/skills/apm Skill
2★ repoAgent Package Manager: Local-first CLI package manager for AI agent prompt files and skills. Write an agent once, install it everywhere.
codyjlandstrom/pm-skills/skills/mom-test Skill
2★ repoApply Rob Fitzpatrick's "The Mom Test" framework to product discovery work. This skill is invoked explicitly when the user asks to use "the mom test skill" or phrases like "apply the mom test", "mom test this", or "use mom-test". It helps with: reviewing interview questions for bias, generating good customer discovery questions from hypotheses, analyzing conversation transcripts for weak signals and deflections, and extracting risky assumptions from product ideas. Use this skill any time the user wants to pressure-test their customer discovery approach, even if they phrase it casually (e.g., "are these good interview questions?" after invoking the skill earlier in the conversation).
adlsdztony/claude-marketplace/web-clone/skills/progress-tracker Skill
no license2★ repoThe same file is in 2 other repositories
dirkkok101/skills/docs-skills/skills/adr Skill
2★ repoSkills for AI agents
ncoevoet/claude-loop/skills/goal-loop Skill
2★ repoHard-verifier + escalation layer for Claude Code /goal: a deterministic, project-agnostic oracle (lint/test/build + review-all gate) enforced by a Stop hook, with stuck-detection and escalation.
Priyadarshiswain/tokenomics/skills/tokenomics Skill
2★ repoMeasure where a Claude Code session's tokens and context actually go — HTML reports, live status line, compact nudge. Token counts only, no pricing.
zaakirio/feature-wiki/skills/building-feature-wikis Skill
2★ repoUse when the user wants to document, catalogue, or build a wiki of the features in a codebase (e.g. "build a wiki of what this repo does", "document this project's features", "generate onboarding docs", "collate what I've built across my projects"). Reconstructs features from git history, enriches them with project-management ticket context from whatever PM MCP is connected (Jira, Linear, GitHub, Shortcut, Asana), and publishes deduplicated docs to Confluence, Linear, Notion, a GitHub wiki, or a local HTML wiki.
wyh0626/troubleshoot/skills/troubleshoot Skill
2★ repoProduction troubleshooting + knowledge-capture assistant for ANY live/online issue — infrastructure or application, backend or frontend. Use when investigating a production problem and pulling logs, traces, metrics, or cloud/cluster resources to find the cause: errors/exceptions, 5xx/timeouts/latency, crashes/restarts, K8s/pods/networking, gateways/auth/OIDC, DB/data anomalies, third-party integration failures, alerts, CI/build failures, log forensics and security audits. Searches past incidents and runbooks first, reasons over service topology, proactively corrects stale topology/log-source facts, and archives the investigation to the knowledge base only after explicit user confirmation.
goperigon/skills/skills/perigon-sdks Skill
2★ repoPerigon Agent Skills - Point your agent and let it build using the Perigon APIs
virgil-king/kbtz/plugin/skills/kbtz-basics Skill
2★ repoTask tracker for AI agents
nathanonn/claude-skills-sandbox-architect/.claude/skills/sandbox-architect Skill
2★ repoAnalyze codebases to generate optimal Claude Code Sandbox configurations. Use this skill when users need to set up sandbox security settings for their projects. This skill should be triggered when users ask about sandbox configuration, security settings, or when setting up Claude Code for a new project. It analyzes the codebase stack (Node.js, Python, Rust, Go, PHP, etc.), detects dependencies, and generates appropriate sandbox and permission settings through an interactive Q&A process.
The same file is in 3 other repositories
EladAriel/pseudo-code-prompting-plugin/skills/prompt-structurer Skill
2★ repoThe Pseudo-Code Prompting Plugin enhances Claude Code with automated conversion, validation, and optimization of natural language requirements into concise, function-like pseudo-code. This structured approach eliminates ambiguity, ensures completeness, and accelerates development.
Rushour0/fabri/skills/agency-builder Skill
2★ repoLocal memory + orchestration layer for custom LLM agents: SCOPE-style tactical/strategic memory over execution traces, Qdrant-backed, polyglot subprocess tools, agent-as-tool composition.
N0v4ont0p/Refract/.claude/skills/ftc-rule-check Skill
2★ repoCitation-grounded FTC rules compliance: delivers legal/illegal/ambiguous verdicts with verified rule citations for "is X legal" questions, inspection readiness, scoring and gameplay rules, robot-size/mechanism restrictions, and Team Update changes. Use whenever the user asks about legality, compliance, penalties, inspection, or whether a mechanism, part, material, or strategy is allowed — even when the question is mixed with hardware or strategy concerns — and whenever any part of an answer would rest on what the Competition Manual says. Never answer a rules question from memory; this skill grounds every verdict in the tagged manual with cross-reference traversal.
base2Services/strategy-skills/plugins/strategy-skills/skills/north-star Skill
2★ repoOrganisation-neutral Claude Code skills for strategy, service definition, marketing, and pricing. Question-led, evidence-tagged, configurable per project.
chriswch/praxis/plugin/skills/clear-writing Skill
no license2★ repomalkoG/squire/plugins/wireframe-picker/skills/wireframe-picker Skill
no license2★ repoPatrick-DE/claude-adapt-rules/skills/claude-adapt-rules Skill
2★ repohungson175/document-processor-skill/skills/document-processor Skill
2★ repoIngest business documents (.pptx, .pdf, .xlsx, .docx) into FAITHFUL markdown for a RAG knowledge base or review — VLM-first (Vision-Language Model), NOT OCR. Use this whenever the user wants to convert, ingest, extract, or "turn into markdown/text" any slide deck, report, spreadsheet dashboard, or PDF — ESPECIALLY chart-, dashboard-, or image-heavy and Vietnamese/mixed-language documents where chart numbers, tables, and verbatim text must survive. Trigger on phrases like "convert this deck/report/pptx/pdf to markdown", "ingest these documents", "extract the data/tables/charts from this presentation", "build a knowledge base from these files", or any document→markdown task where faithfulness matters. Prefer this over a plain text-extraction/OCR approach, which silently drops charts and merged-cell layouts. Validated 10/10 on real documents by an independent Opus-4.8 faithfulness judge (see references/validation.md).
ywj3493/claude-skills/dev-docs-plugin/skills/sync-translations Skill
no license2★ repotagoro9/dotfiles/config/dot_claude/skills/fotingo Skill
no license2★ repoMy dotfiles.
Bardli/AIHubSkillSet-dataconvert/skills/dataset-acquisition Skill
no license2★ repoThe same file is in 1 other repository
medfm-flare/flare-skills/skills/dataset-acquisition Skill
no license2★ repoCommonly used skills for biomedical image analysis
The same file is in 1 other repository
budzikt/edu-vulcan-mcp/.agents/skills/marketplace-creator Skill
no license2★ repoThe same file is in 3 other repositories
isas1/blindspot/skills/blindspot Skill
2★ reponcihtan/htan-claude/skills/htan Skill
2★ reposixoverground/claude-phases/skills/phase-planner Skill
2★ repoWrite a phased implementation plan to a docs/plans markdown file named for the project. Break work into one-PR phases, detect each repo's CI and review setup, and propose matching configuration. Use when asked to plan a project, break work into phases, set up a phased plan, or create a plan for phase-driver to execute. Also use when revising an existing plan's phases or configuration.
agora-oss-org/agora-plugins/plugins/agora/skills/sdk Skill
2★ repoClaude Code plugins for the Agora platform — marketplace + skills that teach an agent to build on the @agora-sdk SDK (and, soon, its API and admin surfaces).
miguelbacalhau/orca/skills/pr Skill
2★ repoLand a finished orca run's deliverable branch through a GitHub pull request instead of a local merge. Picks a delivered-but-unlanded run — a finished run whose `feature/<slug>` branch exists and is unmerged, from `triage snapshot` (newest by default, or the one named) — refuses unless the report says `**Deliverable state:** verified` with nothing blocked, composes the PR title and body from the run's `report.md` translated into an ordinary external-facing description (no run vocabulary, no mention of Claude, AI, agents, or orca anywhere, enforced by the same deterministic marker check as run commits), previews both with the user, and only on their confirmation pushes the branch and creates (or refreshes) the PR with the `gh` CLI. Report-only: a branch no run produced gets plain `gh pr create`, not this skill. Never merges, never edits the report, never touches the integration worktree.
xdevs23/workflow-skills/skills/research-loop Skill
no license2★ repooh no
AndyElessar/skills/plugins/aspire-dev/skills/aspire-dev Skill
no license2★ repoCopilot plugin marketplace, including dotnet, meta-prompts, etc.
Azure/amg-skills/plugins/amg-toolkit/skills/amg-check-azure-spend Skill
2★ repoAgent skills for Azure Managed Grafana
AirZona/site-autopsy/skills/site-autopsy Skill
2★ repoAudits any small business website and produces a brutal, prioritized fix list. Runs Lighthouse, axe-core accessibility checks, mobile vs desktop screenshot diff, and a niche-aware design critique. Use whenever the user asks to audit, review, grade, score, or critique a website, or asks "what's wrong with this site", "is this site any good", "how can I improve example.com", or pastes a URL and asks for feedback. Also use when the user mentions a small business website, prospect site, client site, lead site, or asks for a website audit, site review, or website report.
merge-api/merge-gateway-skills/skills/migrate-openrouter Skill
no license2★ repoClaude Code skills for Merge Gateway integration and migration
Shallow-W/github-starlist-skill/skills/github-starlist Skill
2★ repoClaude Code skill for managing GitHub Star Lists via GraphQL API
Knowledgebase search enterprise
kingdol666/rag-knowledge/.claude/skills/knowledgebase-search-enterprise Skill
2★ repoRAG Knowledge Platform - Monorepo with frontend & backend submodules
MarcelRoozekrans/superpowers-extensions/plugins/compress-memory/skills/compress-memory Skill
no license2★ repoExtension skills for the superpowers suite: regression testing, pre-push review, refactor analysis, decision tracking, Roslyn code graph integration, and companion ecosystem plugins for Claude Code
psylch/ch-project-context/skills/ch-project-context Skill
2★ repoInitialize a project-level context management system with a structured docs/ directory, automatic session and subagent context injection, docs validation, and project instruction navigation. Supports Claude Code, Codex, or both. Use when starting a long-lived project, bootstrapping context management, or when the user says '/ch-project-context init', 'init project context', 'setup context management', or 'initialize docs structure'.
sanafi-onchain/sanabot-skills/skills/sanafi-portfolio Skill
2★ repoSana Bot - Skills
vamgan/claude-harness-builder/skills/harness-builder Skill
2★ repoClaude Code skill: GAN-inspired multi-agent harness for building apps from brief prompts with independent quality evaluation
M4cs/compressoor/skills/compressoor Skill
2★ repoCompress Codex tokens without compromising readability
The same file is in 1 other repository
RiceTooCold/circuit/plugin/skills/using-circuit Skill
2★ repoGraph-backed code intelligence for coding agents — compiler-grade code structure wired to the git/PR/issue history that explains it, served over MCP.
ghchinoy/binder/plugins/okf-convert/skills/okf-convert Skill
2★ repoOKF ingestion and validation - cli, skills, mcp
williamtsoi1/google-cloud-slides-skill/skills/google-cloud-slides Skill
no license2★ repoCreate slide decks with the visual style of the Google Cloud 2025 presentation template. Use for: generating professional, branded presentations with specific Google Cloud layouts, colors, and typography.
frenchieTST/prompt-shield/skills/prompt-shield Skill
no license2★ repoSecurity audit for Claude Code skills, MCP servers, and npm packages. Detects prompt injection, data exfiltration, supply chain attacks, persistence mechanisms, and hidden malicious content. Use when: (1) Installing a new skill or plugin, (2) Adding an MCP server, (3) Evaluating npm packages for security, (4) User asks to 'audit', 'check security', 'is this safe', 'scan for threats', or 'prompt injection check'. Runs 18 automated checks covering zero-width unicode, directional overrides, tag characters, homoglyphs, base64, non-ASCII analysis, prompt injection, hidden comments/CSS, sensitive data, crypto wallet targeting, network exfiltration, IP addresses, data URIs, code execution, path traversal, obfuscation, persistence mechanisms, and background processes.
vitorhugo-dotnet/jasper-jrxml-claude-skill/plugins/legacy-jrxml-toolkit/skills/jasper-jrxml Skill
2★ repoPortable AI agent skill for creating, compiling, and validating legacy iReport/JasperReports 2.x JRXML reports with high-fidelity layouts.
mailerlite/mailerlite-skills/skills/email-marketing Skill
no license2★ repoThis skill should be used when the user asks to "send a newsletter", "create an email campaign", "write a subject line", "set up a welcome series", "build an automation", "improve open rates", "re-engage inactive subscribers", "clean my list", "segment my audience", "grow my email list", "check deliverability", or any task involving planning, writing, sending, or analyzing email marketing through MailerLite. Provides email marketing best practices, safety rules for sending on a user's behalf, and playbooks for campaigns, automations, segmentation, and deliverability.
joshuatownsend/huh-skill/skills/huh Skill
2★ repoA Claude Code skill for the moment your brain stops. /huh makes the agent stop, find the context you never saw, and explain itself like a person.
Adversarial fingerprint testing
sjawhar/pivot/skills/adversarial-fingerprint-testing Skill
2★ repoUse when testing Pivot fingerprint correctness against a real pipeline, hunting for undetected code changes that cause stale cached outputs, or validating Change Detection Matrix claims against production code
Gamma-Software/figma-llm-export/skills/figma-to-code Skill
no license2★ repoConvert a Figma design into application code from a figma-llm-export payload — the JSON produced by the "LLM Export" Figma plugin (node tree + inlined design tokens + rendered PNG/SVG crops). Use whenever the user points at such a .json export, says "build/implement this Figma screen/component", "turn this design into code", references a "figma payload", "design tokens from Figma", or shares a node JSON with `{value, variable}` pairs. Produces token-faithful, framework- appropriate code (React/Tailwind/shadcn, Vue, plain HTML, SwiftUI, …) and verifies it against the exported screenshot.
Colgate13/claude-cdp-debugger/skills/cdp Skill
2★ repoLive-debug a running Node.js service via Chrome DevTools Protocol. Use this skill whenever the user says 'debug', 'set a breakpoint', 'investigate runtime', 'inspect at runtime', 'why is variable Y wrong', or asks to attach to a running container/process to step through real execution. Works on any Node.js project (NestJS, ts-node, plain Node, compiled to dist/) that has a `.vscode/launch.json` with an `attach` config — the skill discovers the inspector port, container name, and source-map setup automatically. The skill is conversational: Claude picks breakpoints from the request context, the user manipulates the system (curl/browser), the breakpoint hits, Claude reports findings, then resumes. Do NOT use this skill for: writing/running unit tests (use jest directly), static code review, log inspection (use docker logs).
mrchaarlie/agent-consent-patterns/plugins/agent-consent-patterns/skills/agent-consent-patterns Skill
2★ repoHeadless React components for AI agent consent UX patterns:human-in-the-loop, least-privilege, and audit-friendly primitives. WCAG 2.2 AA, npm provenance, MIT.
schuettc/mixcraft-app/packages/plugin/skills/playlist-assistant Skill
no license2★ repoMixcraft - MCP server for music service integrations
LottePitcher/oss-health-skills/skills/project-funding-profile Skill
2★ repoClaude Code skills for analysing the health of GitHub repositories
MikeCodeur/skills/plugins/youthumb-api-plugin/skills/youthumb-api Skill
2★ repoMike Codeur skills
topspinj/florajs/skills/flora Skill
2★ repoGenerate Flora diagram syntax and render interactive flowcharts. Use this skill whenever the user wants to create a diagram, draw a flowchart, visualize architecture, map out a data pipeline, show relationships between components, or describe any system they want to see as a graph. Also trigger when the user provides or references a dbt manifest.json and wants to visualize lineage, or says things like "show me the lineage", "diagram this manifest", or "visualize my dbt project". Trigger on phrases like "draw", "diagram", "visualize", "flowchart", "map out", "show the flow", "lineage", "manifest", or when the user describes a system and would clearly benefit from a visual representation — even if they don't explicitly ask for a diagram.