The catalog
609,344 rows, by stacks then stars
parkscloud/okf-author/skills/okf-author Skill
1★ repoAuthor, convert, and validate Markdown in Open Knowledge Format (OKF) — the open, vendor-neutral spec for representing knowledge as a directory of Markdown files with YAML frontmatter. Use this skill when the user mentions OKF or is working inside an existing OKF bundle (apply OKF directly), and also when creating or substantially revising Markdown knowledge, reference, notes, or documentation files (offer OKF once). Do not use it for trivial or throwaway Markdown, code, chat prose, or content the user has not asked to structure.
i-am-anshul/de-ai/de-ai-plugin/skills/de-ai Skill
1★ repoRemove signs of AI-generated writing from text. Use when editing, reviewing, or generating text to make it sound natural and human-written. Applies to all content: resumes, cover letters, LinkedIn posts, professional writing, documentation. Detects and fixes: inflated symbolism, promotional language, superficial analyses, vague attributions, em dash overuse, rule of three, AI vocabulary, negative parallelisms, excessive hedging, and sycophantic tone.
sichengchen/esper/skills/esper-atom Skill
1★ repoCreate or refine a single increment. Smart stage detection — no active creates one, incomplete refines, ready waits for `esper:go`.
octivi/skills/common-changelog Skill
1★ repoDraft and normalize user-facing CHANGELOG.md entries in Common Changelog format from release notes, pull requests, and Conventional Commits (including git trailers like Category, Ref, and Co-authored-by). Use this skill whenever the user asks for changelog text, release notes, "what changed", version summaries, or Unreleased notes, even if they do not explicitly mention CHANGELOG.md.
KirKruglov/OFFICINA/skills/committing-changes Skill
1★ repoUse BEFORE creating any git commit. Enforces Conventional Commits format, analyzes staged changes to propose atomic splits, validates safety (no secrets, no --amend, no --no-verify unless explicitly requested), and removes Co-Authored-By trailer. Trigger phrases — "commit this", "make a commit", or any user request that implies creating a commit.
andrew-shwetzer/daily-intel/skill Skill
1★ repoBuild your own AI-powered intelligence newsletter. Monitors any niche via RSS, scores signals with Claude, and delivers a daily editorial brief to your inbox or Slack. Full auto-setup: asks 6 questions, researches your niche, provisions Supabase, generates config, shows a live sample brief, and sets up cron. Everything runs on your machine. Supports personal mode (Gmail/Slack delivery) and audience mode (Beehiiv drafts for newsletter publishers).
veyralabsgroup/shopify-suite/skills/shopify-suite/shopify-dev Skill
no license1★ repoShopify Developer. Activate when a user is building or modifying a Shopify theme, app, or integration. Triggers on: "add a section to my theme", "create a Shopify app", "Shopify CLI", "Liquid template", "Storefront API", "Admin API", "checkout extension", "Hydrogen", "Polaris", "shopify theme dev", "metafields", "metaobjects", "app blocks", "Online Store 2.0", "section schema". Covers theme development, app development, GraphQL APIs, CLI workflows, and extensions.
The same file is in 2 other repositories
assoumaaa/odoo-superpowers/skills/odoo-code-review Skill
no license1★ repoUse when reviewing Odoo code — yours before commit, Claude's after generation, or a teammate's PSDU PR. Catches shape-of-bad-code issues that lint won't, plus customer-readiness gaps. Invoke before claiming Odoo work is done.
Vingedal/bjorn-skills/skills/tsqlt-testing Skill
1★ repoAuthor, run, and debug tSQLt unit tests for SQL Server. Use when the user asks to write a SQL unit test, add test coverage for a stored procedure / function / trigger, fake or spy out a dependency (table, function, or procedure), assert on query results, expect an exception, or run a tSQLt suite.
DigitalPine/claude-skills/plugins/biome/skills/biome Skill
1★ repoSetup, configure, audit, and optimize Biome linter/formatter in JavaScript/TypeScript projects. Use when installing Biome, auditing existing configs, migrating from ESLint+Prettier, fixing configuration issues, or optimizing unsafe fix workflows. Checks for proper version pinning, Next.js integration, VS Code setup, and script configuration. Emphasizes safe handling of "unsafe" fixes in development workflows.
jefdiesel/clawphunks Skill
no license1★Mint and trade ClawPhunks NFTs. The first collection designed for AI agents.
entpnomad/bootstrapper-toolkit/.claude/skills/analyze-idea Skill
no license1★ repoOrchestrated business idea analysis. Runs 10 dimension skills for deep factual research, applies Bootstrap Oracle scoring with full context, then synthesizes a strategic verdict with Venture Sensei voice. Use when user runs `/analyze-idea`, asks to "analyze this business idea", "full analysis", "comprehensive evaluation", "give me the full picture on this idea", or wants the most thorough business idea critique.
GautamSrikrishna/craft-claudemd Skill
1★Create or update CLAUDE.md files following research-backed best practices. Use when asked to: create a new CLAUDE.md, improve/update an existing CLAUDE.md, set up Claude Code for a project, write project instructions for Claude, or generate a CLAUDE.md at any location (home, project root, parent, child directory). Triggers on: "make a CLAUDE.md", "improve my CLAUDE.md", "set up Claude Code for this project", "create project instructions", "optimize my CLAUDE.md", "CLAUDE.md is too long", "what should go in CLAUDE.md", "help me write a CLAUDE.md", "craft a CLAUDE.md", "initialize Claude Code for this repo", "configure Claude for my project". Also trigger when users mention CLAUDE.md quality, bloat, or effectiveness issues.
Manzanita-Research/pedalboard/artist/skills/onboard Skill
no license1★ repoGuided artist onboarding for independent musicians. Use when a musician wants to set up, clarify, refresh, or document the creative and promo context for an artist project before making social posts, reels, lyric videos, visualizers, show recaps, campaign assets, brand kits, merch concepts, bios, captions, or release materials. This skill interviews conversationally, one question at a time, then writes or updates ARTIST.md and DESIGN.md so later Pedalboard skills can sound and look like the artist instead of producing generic marketing output.
thespamer/claude-skill-ma-engineer Skill
no license1★Augmented VP of Operations / M&A Engineer persona (Juliano). Activates for any M&A, due diligence, contract analysis, SG&A overlap, vendor rationalization, P&L optimization, cloud cost reduction, VDR review, integration planning, or distressed software company turnaround task. Use whenever the user uploads contracts, CSVs of spend, financial statements, asks to compare two companies' cost structures, or needs Python/automation to process deal data. Also triggers for: "analyze this acquisition", "compare SG&A", "find cost savings", "review vendor contracts", "build integration plan", "closing checklist", "run rate analysis".
x0c/doc-skills/doc-compact Skill
1★ repo文档整理与压缩。核心职责是在不丢行为信息的前提下压缩冗余文档——删复述、删死链、删历史沿革、收敛重复提醒;配套完成结构整理(纠正文档放置、重建根 AGENTS.md 索引、补 inline 指针、规范 CLAUDE.md 为单行 @*.md、判定并拆分过大项目的二级索引)和全局文档管理规范的检查/安装。当文档冗余膨胀、索引失效、AGENTS.md 膨胀、CLAUDE.md 混入杂质,或需要确认全局规范是否写清文档管理模式时使用。
pltnk/conventional-comments-skill Skill
1★Format review and feedback comments using the [Conventional Comments standard](https://conventionalcomments.org/). The goal is comments that are easy to understand and act on, with a collaborative tone. Use whenever the user asks for a review, critique, or feedback on anything — code, docs, RFCs, designs, drafts, PRs, or any other artifact — including indirect prompts like "thoughts on this" or "what could be better?". Defines comment format and tone, not review content, structure, or length. Labels and decorations in English; subject and discussion in the user's language.
navishachiku/agentskill-config Skill
1★Stores and retrieves per-user, per-project preferences for AI skills via a unified JSON-backed CLI. Loaded by consumer skills that declare a '## Skill Config' section with keys to persist across invocations.
jp-solumhealth/jpstack/chief-of-staff Skill
1★ repoDaily CEO morning briefing that reviews all data sources: HubSpot pipeline, Fireflies meetings, Apollo outreach, and email activity. Surfaces hot deals, at-risk deals, action items, pending responses, new leads, and daily priorities. Use this skill when the user says "morning review", "daily briefing", "chief of staff", "review my pipeline", "what's hot", "what needs attention", or "start my day".
dcs-soni/skills/api-docs-generator Skill
1★ repoA collection of custom Claude Code Skills to supercharge your development workflow.
im-shashanks/claude-plugins/shaktra/skills/shaktra-adversarial-review Skill
no license1★ repoAdversarial Review workflow — treats code changes as behavioral hypotheses and systematically falsifies them through mutation testing, adversarial inputs, and fault injection. Produces execution-based risk assessment.
Chrike/coding-agent-skills/skills/agent-workflow Skill
no license1★ repoLightweight Claude Code skills for daily AI-assisted development workflows.
NerdBase-by-Stark/claude-code-skills/mass-deploy-ux Skill
1★ repoUX patterns for desktop tools that commission or configure device fleets in parallel — status grids, error triage, resumable worklists, LED locate, throughput ETA. Use when designing a UI that tracks 50+ parallel device operations.
The same file is in 1 other repository
KonH/ClaudeTools/plugins/k/skills/commit Skill
1★ repoClaude Code plugin with skills shared across project
scagogogo/versions-skills/skills/cli-operations Skill
1★ repoCompose the versions CLI in shell pipelines, scripts, and CI/CD — output formats, exit codes, input methods, and command patterns.
TiagoDanin/skills/.claude/skills/lovable-to-nextjs Skill
1★ repoConvert Lovable/Vite React projects to Next.js App Router with static export for GitHub Pages. Handles full project restructuring: routing, SEO (metadata, OpenGraph, JSON-LD), sitemap, GitHub Actions CI/CD pipeline, data/ folder as file-based CMS, and proper 'use client' boundaries. Use this skill whenever the user mentions converting a Vite project to Next.js, migrating from Lovable to Next.js, restructuring a React SPA for static export, setting up a Next.js site with SEO and GitHub Pages deployment, or wants to turn a Vite/React project into a production-ready static Next.js site. Also trigger when the user has a Lovable-generated project and wants better SEO, performance, or deployment setup.
Multi agent system architect v2
ingcontartese-netizen/multi-agent-system-architect-v2/skills/multi-agent-system-architect-v2 Skill
1★ repoDesign, audit, build, verify, or port governed agentic systems for one host or optional teams. Triage no-system, workflow, agents; govern authority, state, tools, security, evals. Not for one-offs.
nix-tkobayashi/ask-devin Skill
1★Asks Devin for Terminal for coding assistance. Use for getting a second opinion, code generation, debugging, or delegating coding tasks.
Jeremyx000/claude-session-index/skills/session-index Skill
1★ repoSearch, analyze, and synthesize across all your Claude Code sessions. Ask "what did I try last time?" and get answers with resume links.
The same file is in 1 other repository
lc-semba-ryuichiro/semba-claude-plugins/plugins/atl-fetch/skills/atl-fetch-confluence Skill
1★ repoatl-fetch CLI を使った Confluence 情報取得のガイドを提供するスキル。「Confluence ページを取得したい」「Confluence のドキュメントを見たい」「atl-fetch で Confluence を取得」「Confluence のバージョン履歴を確認」「Wiki ページの内容を取得」などのリクエストで使用する。
Roly67/cc-skills/dotnet-coding-standards Skill
1★ repo.NET coding standards and patterns. Use when: creating new .NET solutions, writing C# classes/services/controllers, setting up Serilog logging, configuring Sentry error tracking, reviewing pull requests, checking code coverage, fixing StyleCop warnings, adding unit tests, or scaffolding Web API/Console/Worker/Blazor projects. Covers Clean Architecture, async/await patterns, ConfigureAwait usage, and CI/CD pipeline configuration. Apply to all .cs and .csproj files.
michellepellon/superpowers/skills/documentation-audit Skill
1★ repoSystematically verify documentation claims against codebase reality. Use when auditing docs, before releases, after refactors, or when documentation drift is suspected. Two-pass approach with pattern expansion ensures comprehensive detection of false claims, dead references, and gaps.
cappt-team/skills/skills/cappt Skill
1★ repoGenerate a PowerPoint presentation from a topic, title, or article using Cappt. Use this skill when the user asks to create a PPT, presentation, or slide deck, or mentions Cappt. The skill first generates a structured Markdown outline, then calls the Cappt CLI to produce the final presentation. Trigger phrases include "生成PPT"、"做一个演示文稿"、"制作幻灯片"、"create a presentation"、"make a PPT"、"generate slides".
The same file is in 1 other repository
veyralabsgroup/venture-suite/venture-analyst Skill
1★ repoStartup and SaaS idea validation. Researches market evidence, maps competitors, scores viability, and generates concrete validation experiments. Zero API keys required.
The same file is in 2 other repositories
Yesterday-AI/ytstack/.claude/skills/check-consistency Skill
1★ repoAudit ytstack internal consistency. Compares README (source of truth) against docs/concept.md, .ytstack/DECISIONS.md, and actual plugin content (skills/, hooks/, agents/, artifacts). Reports drift: missing or extra skills, workflow mentions that do not resolve to real skills, trigger-map gaps, hook-list mismatches, skill-count drift, banned-words hits. Run before approving doc changes or after a vendor subtree pull. Does not fix anything -- humans decide how to reconcile.
yokeloop/yoke/.claude/skills/sync-docs Skill
1★ repoRegenerates the public skill catalog from `skills/*/SKILL.md` — per-skill MDX pages under `site/src/content/docs/skills/`, the table between `<!-- yoke:skills:start -->` markers in `README.md`, and the bullet list between the same markers in `CLAUDE.md`. Activates when the user writes "sync docs", "regenerate docs", "update the skill catalog", "rebuild docs", "refresh the catalog", or passes `--check` to detect drift. Refuses to write when sentinels are missing or unbalanced.
Ludovic33Fr/product-ai-toolbox/skills/committee-prep Skill
1★ repoUtiliser pour préparer un comité d'arbitrage ou un comité de pilotage. Produit une synthèse de fond, des contre-arguments classés, les objections anticipées par participant, une formulation médiane et les critères de décision attendus.
cjcsecurity/claude-code-dual-build/skills/dual-build Skill
1★ repoOrchestrate a parallel multi-agent build with mandatory cross-review across Claude and Codex. Splits a multi-component coding task into ~equal Claude and Codex subtasks, runs them in parallel in isolated git worktrees, then has the OPPOSITE model review each diff before consolidation. Use for multi-file features, refactors with parallel slices, batch fixes, or audit-and-fix passes — bail to a single-agent build for trivial changes. The cross-review is the value: different model families catch different bug classes.
elmaxid/sequential-thinking-skill/skills/sequential-thinking Skill
1★ repoThis skill should be used when facing complex architecture decisions, multi-step root cause analysis, comparing multiple approaches with trade-offs, debugging that requires hypothesis tracking, planning with branching possibilities, or any problem requiring structured step-by-step reasoning with potential revisions. Trigger phrases include 'think through this', 'analyze step by step', 'reason about', 'evaluate options for', or when a problem has 3+ interacting factors.
alexsmedile/pricing-skills/skills/at-what-price Skill
1★ repoSystematic pricing auditor that builds a solid, defensible price step by step — even with incomplete data. Use when the user needs help pricing a project, service, or offer and doesn't know where to start, is guessing, or wants to pressure-test their number. Trigger on: "what should I charge", "how do I price this", "is this price fair", "I don't know what to ask for", "help me price", or any situation where the user describes a project and needs a number.
claude-hangar/claude-hangar/core/skills/adversarial-review Skill
1★ repoCritical review (min. 5 findings). Modes: code, audit, plan. Use when: "review", "critical review", "code review", "plan review", "audit review".
suprenvb/plumbline Skill
1★Cofounder-grade full-stack product partner that designs, builds, debugs, ships, and makes build-vs-buy calls with an honesty-first discipline, verifying claims against the real code and data instead of memory, hunts silent failures, audits signal coverage before shipping, and labels estimates vs measured. Use this whenever building or shipping a product feature end to end (backend, frontend, deploy), debugging something that looks fine but might be lying, running a competitive UX teardown or feature gap analysis, auditing data quality, coverage, or provenance, deciding whether to build a capability or keep paying a data vendor, or preparing an honest stakeholder-ready deliverable, even when the user does not name any of these explicitly but is clearly doing product engineering, data work, or shipping to real users.
limerickgds/dashi-skills/.agents/skills/release-skills Skill
1★ repoUniversal release workflow. Auto-detects version files and changelogs. Supports Node.js, Python, Rust, Claude Plugin, and generic projects. Use when user says "release", "发布", "new version", "bump version", "push", "推送".
The same file is in 1 other repository
RubenBranco/WANDB-Plot-Skill/skills/wandb-plot Skill
1★ repoDownload and generate plots from Weights & Biases runs. Use when you need to: - List projects you have access to - List runs in a W&B project - Inspect available metrics for a run - Download existing plot images from a run - Generate line plots from metric history (loss, accuracy, etc.)
The same file is in 3 other repositories
rafaelpierre/duckduckscrape/.claude/skills/duckduckscrape Skill
no license1★ repoLightweight web search via DuckDuckGo with BM25 relevance ranking. Use when asked to search the web, look something up, find recent information, research a topic, or browse the internet. Trigger phrases: search the web, look up, find information about, google, browse the web, web search, find recent, what is the latest on.
galligan/skills-packager/skills/test-skill Skill
no license1★ repoA test skill for validating the packager
ORBWEVA/founder-metrics/skills/niche-validator Skill
no license1★ repoValidate and score a niche idea (or compare 2-3) across keyword volume, competition, willingness-to-pay, buildability, and flippability. Returns a 1-10 weighted score with go/conditional/no-go verdict. Triggers on "validate niche", "score idea", "should I build", "is this niche worth it", or /niche-validator.
SURFLIN2030/swing-skills/skills/swing-clarify Skill
1★ repoPrevents premature execution on ambiguous requests. Analyzes request clarity using 5W1H decomposition, surfaces hidden assumptions, and generates structured clarifying questions before work begins. Use at the start of any non-trivial task, or when a request could be interpreted multiple ways. Triggers on "뭘 원하는건지", "요구사항 정리", "clarify", "what exactly", "scope", "requirements", "정확히 뭘", "before we start".
AzedL/learn-anything-skills/learn-anything Skill
1★ repoTailored learning coach for deeply learning a subject, skill, tool, or discipline. Use only when the user explicitly invokes `learn-anything` for guided learning.
delphinereverse794/remotion-transitions Skill
1★This skill should be used when the user asks to create custom Remotion transitions, asks about "cool transitions", "cinematic transitions", "striped transitions", "glitch transitions", "custom TransitionPresentation", or wants to build scene-to-scene transitions in Remotion beyond the built-in library. Also triggers for "how to make transitions in Remotion", "custom transition", "high-energy transitions", "energy transitions", "branded transitions".
The same file is in 1 other repository
noman3271/caveman/caveman-compress Skill
1★ repoCompress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman:compress <filepath> or "compress memory file"
The same file is in 3 other repositories
vinci7/project-insights-skill Skill
1★Generate comprehensive GitHub Insights-style project analysis reports including code metrics, language distribution, commit history, tech stack identification, project structure, and development progress tracking. Use when you need to understand a codebase, create project documentation, analyze development activity, or present project statistics in a visual format.
timdevai/proteus/skills/commit-curator Skill
1★ repoAlways-on multi-agent AI workstation for Claude Code. 142 specialist agents (ML, security, K8s, backend, frontend) · 366 curated skills · 200+ prompt templates · auto prompt-matcher · auto skill-matcher · MCP support · token router cuts Anthropic bill 6x via Kimi/Haiku/Ollama. LiteLLM · BYOK · MIT + Apache. One-line install.
sanjay3290/azure-devops-skill Skill
1★Manage Azure DevOps projects, work items, repos, PRs, pipelines, wikis, test plans, security alerts, variable groups, environments/approvals, branch policies, and attachments. Use when user asks to: manage sprints, create/update work items, list repos, create PRs, run pipelines, search code, manage wiki pages, check security alerts, manage variable groups, approve deployments, or configure branch policies. Covers 13 domains with 99 tools via REST API.
The same file is in 1 other repository
mcltyl/concise-mode-skills/skills/concise-mode Skill
1★ repoCut the fluff. No more walls of text, excessive apologies, or over-explanations. Get direct answers in the format you need. Configurable brevity levels from terse to standard.
Code-Ninja-Mind/42-pool-mentor-skill Skill
1★A senior peer mentor for 42 School / 1337 Pool preparation. Triggers on any mention of: 42 school, 1337, piscine, pool, C day exercises (C00–C13), Shell00, Shell01, rushes, exams, norminette, recoding, algorithm building, debugging C code, ex-pooler, second attempt, or getting selected after the pool. Also triggers when a pooler says "I failed", "I don't understand this exercise", "can you fix my code", "what score do I need", "how do I prepare for the pool", or shares a C function and asks why it is wrong. Always redirect fix requests into guided debugging. Always run onboarding for new poolers. Never give direct solutions under any circumstances.
trev0rr/executive-slide-skill/executive-slide Skill
1★ repoUse when the user asks for an executive slide, strategy slide, consulting slide, McKinsey/MBB-style slide, executive or strategy deck, board deck, or wants data/analysis made "boardroom-ready" or presented to leadership. Produces single slides or multi-slide React (.jsx) artifact decks to management-consulting standards.
tamtom/android-docs-claude-plugin/skills/android-docs-search Skill
no license1★ repoSearch Android/Kotlin documentation offline using SQLite index for API lookups and Grep for content search. Use when the user asks about Android APIs, Compose components, AndroidX classes, Kotlin extensions, or needs to find documentation for Android development.
aroyburman-codes/compound-product-management/skills/prompt-coach Skill
1★ repoUse when the user's prompt is vague, overloaded, or missing context that would improve the output. Also use retroactively at session breakpoints to surface prompting patterns the user can improve. Coaches without being annoying.
CaseMark/legal-plugin/ocr Skill
no license1★ repoProcesses documents through case.dev OCR for text and table extraction. Supports PDF and image files up to 500MB with page-level and word-level output. Use when the user mentions "OCR", "text extraction", "scan document", "digitize", "extract text from PDF", or needs word-level positional data from documents.