The catalog
608,253 rows, by stacks then stars
PJuniszewski/context-guard/skills/guard Skill
0★ repoAnalyze and prepare prompts with JSON for safe context submission
The same file is in 1 other repository
dceoy/github-cli-agent-skills/skills/gh-issue-close Skill
0★ repoClose GitHub issues with gh CLI, choosing completed vs not planned and optionally adding a closing comment.
heyimjames/nikita-bier-consumer-apps Skill
0★A comprehensive AI advisor skill that packages Nikita Bier's complete playbook for building viral consumer iOS/mobile apps. Covers viral loops, shareability mechanics, onboarding optimisation, gamification, social network effects, launch strategy, App Store optimisation, iOS platform hacks, monetisation, push notification strategy, retention, and product psychology. Use this skill whenever the user is building, designing, reviewing, or planning a consumer mobile app — especially social apps, community apps, or any app targeting network effects and organic growth. Also trigger when the user mentions: viral growth, user acquisition without ads, K-factor, invite loops, onboarding funnels, App Store conversion, consumer social, teen/Gen-Z audiences, product-led growth for mobile, cold start problem, shareability, or referral mechanics. Even if the user just says "review my app idea" or "how do I make this spread" — use this skill.
okturan/claude-plugins/plugins/files-organizer/skills/generate-file-map Skill
0★ repoThis skill should be used when the user asks to "generate a file map", "create an HTML dashboard", "visualize my files", "create a file map HTML", "update the file map", "build a storage dashboard", "map my folders", "scan my files into a dashboard", or "create a file structure report". It produces a self-contained HTML file visualizing file structure, storage usage, and organization recommendations.
frankxai/infogenius/.claude/skills/infogenius Skill
no license0★ repoResearch-grounded infographic and knowledge-visual generation for Claude Code. Use when the user asks for /infogenius, infographics, visual explainers, technical diagrams, educational images, or image prompts that should be factually grounded before generation. Uses Google Search/WebSearch plus a Gemini image MCP such as nano-banana.
dr-rompecabezas/django-scaffold-skill/skills/django-scaffold Skill
0★ repoScaffold a new Django project following Felipe's established patterns
chatmaterials/catalysis-analysis Skill
0★Use when the task is to analyze catalysis-relevant quantities from DFT results, including adsorption energies, d-band center estimates, reaction barriers from NEB images, mode-specific catalyst-set ranking, adsorption or pathway selectivity comparisons, and compact markdown reports from finished calculations. Supports VASP, QE, and ABINIT-style energy inputs.
ledjay/skills/_template Skill
0★ repoOne-line description with trigger phrases. Use when the user asks for X, Y, or Z.
yborunov/ghostledger/skills/accounting Skill
no license0★ repoAgentic AI accounting and tax reporting based on the plain text double entry accounting system Ledger
nanami7777777/env-config-safety Skill
0★Use this skill when working with environment variables, configuration files, API keys, secrets, or .env files. It provides rules for secret management, .env file patterns, .gitignore configuration, and prevents accidental exposure of credentials in code, logs, or git history. Triggers when creating .env files, configuring API keys, setting up deployment, or handling sensitive data.
The same file is in 1 other repository
lighteternal/jury Skill
0★Evidence-grounded decision and problem-solving council that combines user-provided materials with mandatory fresh internet research. Use when Codex must answer an assignment/question, compare options, choose a strategy, or critique a plan using multi-source evidence. Enforces role-based challenge, broad-then-specialized searches, explicit assumptions, confidence levels, clear citations, live intermediate updates, and saved round artifacts in the invoking repository.
sashazykov/dexranger-skill Skill
no license0★Check crypto tokens for rug pull risk and scams using DEX Ranger. Use when the user wants to check a token's trust score, safety, warnings, or red flags on Ethereum (ETH), Solana (SOL), BSC, or TON. Also use when the user provides a token contract address and wants to know if it's safe, a scam, or a rug pull.
b12k/obey/skills/obey-code-naming Skill
0★ repoApply concise code naming conventions when generating, reviewing, or refactoring code identifiers. Use for naming variables, constants, enum-like dictionaries, classes, errors, data shapes, functions, events, booleans, nullable/defaulted values, temporal values, collections, and conversion functions in any programming language.
nicoladevera/pm-agent-kit/.claude/skills/alignment-memo Skill
0★ repoDrafts internal alignment artifacts — frameworks, standards, operating memos, and lightweight program proposals. Use when asked to "draft a framework", "write a memo on how we should think about X", "create a standard for Y", "propose a hackathon", or "write an operating memo".
Generate conventional commit messages skill
ultimatile/generate-conventional-commit-messages-skill Skill
no license0★Generates commit messages in Conventional Commits format based on staged changes (git diff --staged). Use this skill whenever the user asks to generate a commit message, create a commit, write a git commit, or format a commit. Also trigger when the user says things like "create a commit message", "what should my commit message be?", "help me commit this", or mentions "conventional commits". Even if the user just says "commit" without additional context, consider using this skill to produce a well-formed message.
PeytonLi/skills/resume-builder Skill
0★ repoAdd, edit, and polish resume bullet points with strong action verbs, business-impact metrics, and bolded technologies. Use when the user wants to write resume bullets, improve a resume, add metrics to experience, shorten bullet points, bold keywords, or format bullets following the action-verb → method → metric → result formula.
Perdolique/workflow/skills/code-review Skill
0★ repoPersonalised workflow, tools, agents, skills and other stuff in one place
putdotio/skills/skills/frontend/frontend-dev Skill
0★ repoDevelop, review, and standardize put.io frontend applications and packages. Use when asked to review put.io frontend code, build a feature, model state or errors, create components, capture repo-local `.patterns/`, improve top-level docs, set up CI or delivery, wire up a test harness, configure local secrets, or prove behavior in a browser, native app, TV, emulator, simulator, or device. SDK client and API contract design and put.io CLI consumer operations are outside this skill.
facultymemberunwieldiness454/app-store-preflight-skills Skill
0★Scan an iOS/macOS Xcode project for common App Store rejection patterns before submission. Use when preparing an app for App Store review, after receiving a rejection from Apple, or when auditing metadata, subscriptions, privacy manifests, entitlements, or design compliance. Integrates with the asc CLI for metadata inspection.
The same file is in 1 other repository
tomekness/get-skills-skill Skill
0★OpenCode only. Use this skill when the user wants to install, add, or get a skill in OpenCode — either globally (~/.config/opencode/skills/) or locally in the current project (.opencode/skills/). Always asks global vs local if not specified. Triggers on: "install the skill X", "add the skill from this repo", "get the skill X globally", "add skill X to this project", "install skill from URL", or any request to install an OpenCode skill.
narainio/context-daemon/skills/context-daemon Skill
0★ repoOpinionated product development pipeline. Use when the user wants to take an idea from inception to shipped product through a structured process — Research, Strategy, Gauntlet, Design, PRD, Build, Ship. Triggers on phrases like "start a new project", "take this through the pipeline", "help me ship this", "context daemon", "new idea", "product pipeline", or when a user presents a product concept and wants structured guidance from research through shipping.
changeflowhq/changeflow-skill/skills/changeflow Skill
no license0★ repoMonitor any website and get AI-enriched change intelligence. Use when the user wants to track web pages, create monitoring sources, search their changes, or manage their Changeflow account. Requires CHANGEFLOW_API_TOKEN env var.
longcipher/omni-skill/skills/backend-api-master Skill
no license0★ repoDataset based skill generator
abijith-suresh/skills/skills/commit Skill
0★ repoCreates clean conventional commits from the current diff. Use only when the user explicitly invokes the commit skill. Do not trigger from ordinary requests that happen to involve code changes.
litingyes/skills/.agents/skills/project Skill
0★ repoMaintain project-level metadata and skill registry documentation. Use when users add a new skill under `/skills`, significantly update an existing maintained skill, or need README synchronization for skill inventory and rationale.
th3vib3coder/vibe-science-codex Skill
no license0★Scientific research engine with adversarial review, tree search over hypotheses, and serendipity detection. Turns a coding agent into a rigorous research partner that hunts for artifacts, confounders, and unexpected discoveries. Use this skill whenever the user mentions research, hypotheses, scientific analysis, experimental design, literature review, data validation, quality gates, claim verification, reproducibility, or any task where correctness matters more than speed. Also use when the user wants to explore a dataset scientifically, validate findings against literature, run computational experiments with adversarial review, or hunt for unexpected patterns. Do NOT use for simple Q&A, code editing without research context, or non-scientific tasks.
nilskj/pi-ios-simulator-debug Skill
0★Debug React Native app in iOS simulator. Execute JavaScript functions via WebSocket, tap/swipe UI elements, take screenshots, inspect accessibility tree, control GPS, and manage app lifecycle. Use when testing or debugging the app during development.
lohnim/skills/skills/tailwind-v4-dark-mode Skill
no license0★ repoFix or implement dark mode in Tailwind CSS v4 projects. Use when dark mode colors are wrong, CSS variables aren't switching, utilities show hardcoded colors, or when setting up class-based dark mode with semantic design tokens.
srinandan/apphub-skill/apphub-skill Skill
0★ repoManage Google Cloud App Hub resources and write Terraform configs for App Hub. Use this skill when asked to list applications, register services/workloads, or generate Terraform code for App Hub.
vijpatel7/favorite_skills_and_plugins/.agents/skills/agent-browser Skill
0★ repoAutomates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
agykit/agykit/.agent/skills/brand-guidelines Skill
no license0★ repoApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
The same file is in 37 other repositories
grantmcd/skills/gemini-skill-creator Skill
no license0★ repoUse this meta-skill to design, architect, and objectively evaluate high-quality specialized skills following the Agent Skills open standard. Activate whenever the user wants to 'create a skill', 'automate a workflow', or 'refine an agent capability', even if they don't explicitly mention 'Agent Skills' or 'SKILL.md'. Mandates sandboxed evaluation, objective metrics, and interactive review dashboards.
tdkn/agent-skills/.agents/skills/maintain-translations Skill
0★ repoMaintain this repository's English/Japanese documentation pairs and translation-sensitive catalog entries. Use when working in tdkn/agent-skills on README.md, README.ja.md, any *.md file with a *.ja.md counterpart, adding or materially changing skills under skills/, editing AGENTS.md or public docs, or when the user mentions ja.md, Japanese docs, translations, localization, or mirrored documentation.
hypertopos/hypertopos-skills/gds-analyst Skill
0★ repoGDS anomaly investigation — goal-oriented, reads investigation hints and plans approach around what to find. Use for any investigation task with or without specific anomaly categories. Triggers on "investigate", "find anomalies", "run analysis", "what's anomalous here", "sphere health check", or any anomaly investigation task.
TeaBay/role-play-review Skill
0★Role-based review system with lite mode for fast reviews and council mode for chaired deliberation. Reviewers speak from their own job function, can disagree with reasons, and the chair decides whether to approve, request changes, defer, or veto.
indigokarasu/multipass Skill
no license0★Accomplishes tasks that need tools the agent does not have. Plans approaches, fills capability gaps with sandboxed tools, executes within an isolated session. Disposable identity, parallel discovery, incremental checkpoints, graceful degradation. Output: task result plus replay script. No global installs, no real identity, clean state in and out. Do not use for tasks solvable with installed skills, permanent skill installs, skill builds (use Forge), or general web research (use Sift).
KeWang0622/balltalk Skill
0★Use this skill when the user asks about basketball — NBA stats, player comparisons, fantasy advice, rules, play design, scouting, or coaching. Triggers: 'balltalk', 'basketball', 'NBA', 'who should I start', 'player comparison', 'fantasy basketball', 'basketball stats', 'is X better than Y', 'explain this play', 'basketball rules'. Pulls real stats via web search, compares players, gives fantasy advice, explains rules, and generates scouting reports. Do NOT use for: other sports, basketball video games, or basketball card collecting.
non4me/session-wizard Skill
0★Full session lifecycle management — analyzes the current session on close, routes knowledge to memory and skills, and passes context to the next session via a handoff file + SessionStart hook. Use this skill whenever the user types /es, "end session", "wrap up", "save session", "session summary", or any variation of closing/ending a work session. Also use when the user asks to save progress, create a session handoff, or prepare context for the next session. This skill should trigger even for short sessions — every session produces at least a state update and a handoff file.
jovd83/acceptance-criteria-designer Skill
0★Generate acceptance criteria from user stories, PRDs, requirements, use cases, business rules, or tickets that have none yet — and refine, normalize, critique, or convert existing criteria. Output testable Gherkin, TDD, or sentence-based criteria, identify assumption/coverage gaps, or return a JSON contract.
cogpros/ghost-hours Skill
0★Use when (1) closing a work session and measuring what AI did for you, (2) logging a single completed task as a Ghost Hours entry, (3) running reports on accumulated sessions, (4) retrospecting an old entry with FW-R, (5) amending a prior entry, or (6) sharing de-identified data. Classifies sessions as speed (faster) or unlock (not possible without AI), with subtypes for restoration, bypass, and augmentation. Pairs objective metrics with Felt Weight of Completion. Research-compatible data format. Your session-close protocol can invoke this skill as its measurement step. Standalone invocation is correct for one-off task logging. NOT FOR: timing in-progress work, capacity planning, billable-hour tracking, pre-close audits of open items, or any use that exposes the agent's silent FW-C score to the user before retro. Cite: Pollock 2026.
yaniv-golan/ytd-skill/skills/youtube-downloader Skill
0★ repoDownload YouTube videos with interactive resolution and subtitle selection using yt-dlp. Use when the user wants to download a YouTube video, save a video from YouTube, get video subtitles/captions, or mentions youtube download, yt-dlp, video resolution, or SRT subtitles from YouTube.
The same file is in 1 other repository
2sem/mobile-team-skills/plugins/mobile-team-skills/skills/appstore-review-cs Skill
no license0★ repoUse when the cs agent needs to fetch App Store reviews or submit responses through the App Store Connect customer review workflow.
psacc/hey-cli/.claude/skills/hey-email Skill
0★ repoInteract with Hey.com email. Use when the user mentions email, inbox, checking mail, reading email, searching email, screening, reply later, set aside, or Hey.com. Trigger phrases: "check my email", "what's in my inbox", "read email", "search email", "show my feed", "what's screened out", "screen this sender", "reply later", "set aside", "mark as read", "approve sender", "reject sender", "hey inbox".
chatmaterials/dielectric-analysis Skill
0★Use when the task is to analyze dielectric and optical-response quantities from DFT results, including dielectric tensors, Born effective charges, optical spectra, high-k versus transparency tradeoff descriptors, application-mode candidate ranking, and compact markdown reports from finished calculations.
xPAlien/AI_code_review_skill/ai-code-review Skill
0★ repoSystematic code review checklist for AI-generated code. Use this skill whenever reviewing code produced by AI assistants (ChatGPT, Copilot, Claude, Cursor, Codex, Gemini, etc.), or when the user asks to review, audit, or harden any code they did not write from scratch themselves. Also trigger when the user says "review this," "is this safe," "check my code," "audit this," "harden this," or pastes code they want evaluated before merging or deploying. If the user mentions vibe coding, shipping AI code, or debugging code they do not fully understand, use this skill.
PayEz-Net/vibesql-skills/claude/vibe-mail Skill
no license0★ repoSend and read agent mail — collaborate with your AI team through vibesql-mail
CobraChickenAI/tml-capture-kit/skills/tml-capture Skill
0★ repoEnd-to-end architecture capture. Takes a context dump and/or conversation, produces an architecture map, inferences document, changelog, agent brief, and opportunity analysis. Orchestrates tml-extract, tml-interview, tml-infer, tml-map, tml-so-what, and tml-hygiene in one seamless experience. The user sees one flow; the skills compose underneath. This is the primary entry point — invoke this skill, not the sub-skills directly.
ph3on1x/relamo/skills/relamo Skill
0★ repoThis skill should be used when the user asks to "process large codebase", "recursive language model", "RLM", "explore entire codebase", "analyze codebase", "REPL loop for code", "context as variable", "chunk and process codebase", or needs to programmatically explore a codebase too large for the context window using iterative Python-based exploration.
SzTk/openl-tablets-tool/skills/openl-tablets-create Skill
0★ repoUse when creating a new OpenL Tablets Excel file from scratch through an interactive interview (API output fields → calculation logic → master data), generating and round-trip validating JSON before exporting to Excel.
artyom-88/codex/skills/code-review Skill
no license0★ repoReview git changes in the current repository or a specified branch, pull request, merge request, commit, or diff range. Use when the user asks to review code, review changes, analyze a branch, inspect a PR or MR, assess regression risk, or identify correctness, API, data-flow, security, performance, or test-coverage issues.
chatmaterials/qe-analysis Skill
0★Use when the task is to analyze completed or partially completed Quantum ESPRESSO results, including extracting total energies, convergence status, force summaries, comparing multiple QE runs, and summarizing pw.x output directories.
sanjeevneo/sparkey Skill
0★Time-limited, self-destructing SSH access for AI agents. Four-layer defense-in-depth: certificate TTL, OS account expiry, command-restricted dispatch, and automated cleanup. Zero session artifacts survive.
zhou-xingxing/my-skills/markdown-stats Skill
0★ repo为 Markdown 文件统计字符数和预估阅读时间,支持三种阅读类型(技术文档、普通阅读、快速浏览),并将统计信息以提示框格式插入文件头部。用于处理需要添加阅读统计信息的 markdown 文件,支持中文(每个汉字算1单位)和英文(每个单词算1单位)的混合统计。
bryanp/agent-skills/code/audit Skill
no license0★ repoAudit the codebase for consistency and style
Pratiyush/agent-catalog/skills/skill/code-quality Skill
0★ repoAnalyze Java source files for code quality issues including style violations, complexity warnings, and common anti-patterns. Use when reviewing Java code, running quality checks, or preparing for code review.
LeoStehlik/visual-dna Skill
0★Extract visual identity into reusable Design DNA JSON, then apply it to generate faithful UI from references.
tgexpo/play-fixai-game/skills/hello-gallery Skill
no license0★ repoMinimal test skill for debugging Gallery URL loading.
Dirosaki/skills/skills/doc-yet Skill
0★ repoBuild and maintain high-signal project documentation inside `.agents` for almost any repository, then expose that documentation to Cursor, Claude, Codex, and Gemini through lightweight bridge files. Use whenever the user wants to document a codebase, improve an existing `README.md`, map architecture, explain a monorepo, capture feature boundaries, document a frontend design system or design tokens, create onboarding material, or keep project docs synchronized with the code.
metaKosmos/agent-skills/ecommerce-returns-optimizer Skill
0★ repoDiagnose and reduce ecommerce return rates using technology. Virtual try-on, 3D visualization, AR, size recommendation. Industry benchmarks, root cause analysis, ROI calculators, diagnostic report generators. Use for: reduce ecommerce returns, return rate optimization, reverse logistics cost, product visualization, purchase confidence, fashion returns problem, beauty returns, furniture returns, ecommerce conversion, customer experience optimization, ecommerce trends 2026 2027, return prevention technology, attribution analysis, devoluções e-commerce, taxa de devolução.
jcdentonintheflesh/claude-code-cheatsheet/skills/guide Skill
0★ repoInteractive Claude Code guide for beginners. Helps users discover commands, shortcuts, workflows, and features. Use when someone asks how to do something in Claude Code, needs help with commands, is confused about features, or says things like "how do I", "what command", "how to", "help me", "I don't know how to", "what's the shortcut for", "can Claude Code".