The catalog
608,119 rows, by stacks then stars
codezelat/codezela-web-skills/skills/codezela-project-orchestrator Skill
0★ repoUse when a user asks for broad production web work, full feature delivery, repo readiness, end-to-end audit, CMS/admin/public-site implementation, or a pipeline from brief through verification.
rico2035/claude-skill-status/status Skill
0★ repoGive a TLDR session status — what was done, what was committed (with hashes), what is pending, and the next concrete step for the user or for you. If everything from the conversation is finished and nothing is in flight, output exactly "Nothing pending. Ready for new task." and stop. Use when the user types /status, "give me an update", "what's the status", "TLDR what just happened", "where are we", "what did we ship", or returns after a break and needs to re-orient. Distinct from /recap (longer prose) and /checkpoint (saves state to disk). Always concise, always action-oriented.
george4data/agentic_html_doc/skills/agentdocs Skill
0★ repoAuthor and validate HTML-first, agent-readable documentation following The Source-Complete Standard. Use when creating or updating repository docs (architecture, subsystem contracts, API references, data models, UI/wireframe specs, runbooks, or the docs front-door index) that AI agents are meant to read, or when checking existing HTML docs for conformance. Triggers on intents like "write agent-readable docs", "document this for agents", "source-complete HTML docs", "validate these docs against the standard", "faceted data-* tags", "data-source/data-verified provenance", "CSS-only tabs", "front-door index".
heart-wcl/agent-browser-guide Skill
0★Use when a task involves browser automation, website navigation, screenshots, web pages, clicking, forms, scraping, page content, login, CAPTCHA, anti-bot, URL inspection, DOM elements, Chrome, Chromium, Playwright, Puppeteer, Selenium, browser MCPs, or web tests.
JuzhengSi/draft-goal-skill/skills/draft-goal Skill
0★ repoDraft and refine agent goal prompts through clarification before finalization.
cloud-prg/lin-yuan-perspective Skill
no license0★林园的投资思维框架与表达方式。基于公开采访、现场演讲报道、私募材料、产品争议报道等约15个来源的调研, 提炼5个核心心智模型、8条决策启发式和表达DNA。 用途:作为投资思维顾问,用林园的视角分析公司、行业、市场机会和持有纪律。 当用户提到「用林园的视角」「林园会怎么看」「林园模式」「林园 perspective」「林园式投资」时使用。 即使用户只是说「帮我用林园的角度想想」「如果林园会怎么做」「切换到林园」也应触发。
hhushhas/mobile-skills/mobile-screenshots Skill
0★ repoGenerate and upload App Store and Google Play listing media — screenshots, icons, feature graphics, previews — from simulators and emulators, no physical device needed. Use when creating or updating store screenshots, fixing wrong-size or rejected listing graphics, or when an uploaded icon or screenshot isn't showing.
roziscoding/conventional-comments/skills/conventional-comments Skill
0★ repoUse whenever commenting on a pull request or merge request, writing PR review feedback, creating Conventional Comments badge markdown, or choosing blocking/non-blocking comment decorations.
clawSean/openclaw-x-twitter-kit/skills/x-twitter-kit Skill
0★ repoUse this single agent-facing Twitter/X kit when monitoring known public accounts with Peeper, searching/researching through xAI x_search, reading exact tweets with xurl, configuring OAuth/bearer access, diagnosing capability, or handling X posting safety.
1openwindow/open-foundry/.agents/skills/open-foundry Skill
no license0★ repoHelps a user deploy their existing coding-agent repo (pi, GitHub Copilot, or OpenAI Codex) to Microsoft Foundry Hosted Agents via a thin azd-compatible layout. Use when the user wants to add Foundry deployment to a local coding-agent repo, configure azd env settings, deploy with azd deploy, verify remote invocations, or debug deployment, session, and streaming issues.
KongZhen/carry-forward/skill Skill
0★ repoResume, take over, or hand off a software project across AI coding-agent sessions by reading repo-local state docs, handoff notes, decisions, validation evidence, git status, branch/upstream state, recent commits, and relevant diffs before continuing. Use when the user says continue, resume, take over, 接管, 继续开发, 继续, read AGENTS.md/CURRENT_STATE/HANDOFF/DECISIONS/PROJECT_PLAN, sync with GitHub, create a handoff, preserve context, or avoid starting from zero.
ltorresu82/skills/skills/decision-memory Skill
0★ repoMaintain durable repository memory for architecture and technical decisions using ADRs, decision candidates, and update/supersede checks. Use when reviewing architecture changes, service boundaries, API contracts, runtime choices, security/deploy decisions, technical-debt policies, or when a user asks whether something should become an ADR or durable repo memory.
whjstc/agent-skills/product-brand-naming Skill
no license0★ repoProduct, startup, SaaS, AI app, API, devtool, and digital-product naming workflow for market-informed brand naming. Use this whenever the user asks to name or rename a product or company, choose a domain, validate brand-name candidates, compare product names, check domain availability, research competitor naming patterns, do obvious same-name search, or perform preliminary trademark/conflict screening before launch.
nbsp1221/wayrail/template/.agents/skills/wr-plan Skill
no license0★ repoUse when converting a ready wayrail spec.md into an implementation plan.md. Reads a selected spec item, checks Planning Handoff readiness, performs bounded repository research, and writes only plan.md. Do not use for code implementation, verification evidence, review conclusions, creating tasks.md, or editing spec.md.
Flutter adaptive design system
abdouldotdev/flutter-adaptive-design-system Skill
0★Platform-adaptive Flutter design system generating native-quality UI for iOS (Cupertino) and Android (Material 3). Use when: (1) Creating adaptive widgets that render natively per platform, (2) Building Flutter UI that looks like a real iOS or Android app — not a generic cross-platform hybrid, (3) Generating Cupertino/Material widget pairs with consistent API, (4) Implementing adaptive navigation, dialogs, forms, inputs, or layouts, (5) Setting up a Flutter project's design system foundation with platform detection. Triggers: "adaptive widget", "cupertino material", "platform adaptive", "ios android widget", "design system flutter", "native look flutter", "platform widget", "cupertino", "material design", "adaptive UI"
nyuta01/folio/skills/add-derivation-ai Skill
0★ repoWire up a Folio `kind: ai` derivation — the YAML file under `derivations/`, the prompt template (or `prompt_ref`), `output: text` vs `output: json` with `output_schema`, and a one-row materialize smoke. Invoke when the user asks to "have an LLM fill a column", "auto-classify", "summarize each row", or anything that maps a free-text field to a structured value via Claude/OpenAI/etc.
mychaelconnolly/continuity-skill/skills/continuity Skill
0★ repoUse when the user asks to preserve work state for later, including "continuity", "continuity log", "log work", "save state", "continue later", "resume note", "session clearing", "history clearing", "memory clearing", or "save critical context" — or asks to pick work back up from a saved record, including "pull up <project>", "resume <project>", "resume work on <project>", "where were we", "pick up where we left off", or "continue <project>". Create concise project-local continuity records so a future agent session can resume accurately, and resume from them on request.
m00kk/agent-skills-playbook/skills/a2a-agent-delegation Skill
0★ repoDesigns agent-to-agent delegation using A2A-style handoffs: task envelopes, capability cards, and async responses. Use when multiple agents collaborate, Google A2A, cross-framework agents, or delegating subtasks between services.
xuluoforcainiao/xms-wait-optimization/xms-wait-optimization Skill
no license0★ repoXMS system wait-time optimization strategy for browser automation. Provides a 10-second wait + verification pattern after every critical action to handle slow web application responses, including Chrome startup flags, empty-table retry logic, download-center validation, and Chrome security popup handling. Use when XMS export fails due to timing issues, when adding wait/verification steps to browser automation workflows, or when optimizing interactions with slow-loading internal systems.
christian-beep383/carryfeed-agent-tools/skills/carryfeed-twitter-tools Skill
0★ repoUse the CarryFeed CLI to resolve public X/Twitter profiles, posts, article-style links, image, video, and GIF media for agent workflows. Use when an agent needs source-preserving public X/Twitter context, profile metadata, post text, media candidates, or download URLs without browser login flows or CarryFeed internal implementation code.
akiyax/skills/skills/grill-me-visual Skill
no license0★ repoGenerate a single-file HTML questionnaire with side-by-side visual previews — UI mockups, CSS animations, Mermaid diagrams, font/typography samples, layout variations, code rendering comparisons — so the user picks from rendered options in the browser instead of describing choices in chat. Use for any visually-shaped design decision: layout, motion, typography, color, diagram shape, icon style, content rendering rules ("show me, don't tell me"). Useful for design reviews, design-system exploration, UI prototype direction, and surfacing ADR-worthy decisions. Ships with English and Chinese templates. Fire PROACTIVELY whenever you're about to ask the user 3+ visual-trade-off questions in chat, OR 2 questions where seeing options side-by-side would meaningfully change the answer — don't wait for them to ask.
marukaz/skills/skills/dice Skill
no license0★ reporoll a die
Chakraphol/nui-skills/skills/html Skill
0★ repoPersistent HTML-output mode for Claude Code. Once toggled on (via /html or "html on"), Claude appends substantive answers and plans to a single session HTML file you keep open in a browser beside your chat — rendered with real SVG / Chart.js visuals, tables, and cards instead of plain terminal text. Click a sticky Refresh button to see new entries. Stays active across every turn until you say "html off" or toggle /html again. Output follows your chat language by default, or a fixed language if you append one (e.g. /html Thai). Use when the user invokes /html or says "html on", "html mode", or the equivalent in any language (e.g. "เปิด html").
SDV-G-Deploy/ant-skills/skills/ant-compact Skill
0★ repoCompact plain-language communication layer for AI coding agents. Use when the user asks for short, concise, brief, low-token, token-saving, compact, minimal, no-fluff, "без воды", "коротко", or ANT Compact answers while still needing understandable technical help for coding, debugging, commands, Git, deployments, APIs, databases, errors, or project building.
sb-arnav/dorveille/plugins/dorveille/skills/dorveille-recall Skill
0★ repoUse to recall something from a PAST Claude Code session — when the user says "did we discuss", "what did I say about", "last time", "a while back", "you helped me with X before", "remember when", or references earlier work not in the current context. Searches every past session transcript (FTS5, zero-LLM) and returns the matching conversation with enough surrounding context to act on.
OMouta/scopeguard Skill
0★Turn specs into traceable tasks and prevent agents from drifting out of scope.
brunovgprado/engineering-agent-skills/dotnet/dotnet-unit-test-generator Skill
0★ repoGenerates standardized Xunit and Moq unit tests for .NET/C# solutions by mirroring existing architecture, directory layout, naming, mock patterns, and coverage conventions. Use only when the user explicitly invokes this skill via slash command or attaches it. Triggers include .NET solutions, C# unit tests, Xunit, Moq, a single named class, repository-wide test gap analysis, and test project scaffolding.
TOPY-AI-LTD/TOPY-AI-CEO-Skills/skills/topy-ai-ceo-core Skill
0★ repoGeneral CEO decision advisor for strategy, prioritization, organizational design, OKRs and KPIs, fundraising, M&A, crisis response, stakeholder management, competitive analysis, debiasing, and quantitative trade-off analysis. Use when the user needs executive-level help that does not fit a narrower TOPY skill.
robertomarchioro/goldmarktplace/plugins/hello-world/skills/greet Skill
0★ repoGreet the user with a friendly, personalized message
ldchaowin/duxinshu-skill/skills/duxinshu Skill
0★ repoUse this skill when the user wants to infer another person's likely intent, behavioral pattern, reliability, or relationship risk from chats, emails, screenshots, images, behavior descriptions, timelines, or situational context. This skill prioritizes protective, evidence-based judgment: it gives a concise default answer, supports deeper evidence-chain expansion on request, and avoids unsupported certainty, diagnosis, harassment, manipulation, or privacy-invasive guidance.
Zyc-Bryce/ECD/skills/ecd Skill
0★ repo演进约束开发 (Evolutionary Constraint Development, ECD)——将模糊的用户需求通过"发散→收敛→约束求解"的严格闭环,转化为可运行的高质量代码。触发词:ecd、ECL、演进约束、pre-plan-code-achieve。
Alpha-Park/character-ai-skill Skill
no license0★A modular GenPark AI Agent skill that interacts with Character.AI to create, manage, and converse with human-like AI characters, enabling deep roleplay, creative writing, and voice-enabled interactions.
The same file is in 1 other repository
humbledcoffee/super-harness/skills/super-harness Skill
0★ repoUse when converting coding projects into reusable multi-agent workflows with AGENTS.md rules, role cards, task packages, independent review gates, and learning-oriented comments.
Venorium/external-causal-workspace Skill
0★Use when a task is complex, ambiguous, architectural, debugging-oriented, refactoring-heavy, strategic, causal, performance-sensitive, security-sensitive, multi-file, high-impact, or likely to suffer from hallucinated verification. Builds a disk-backed causal workspace before answering, planning, or modifying files; avoid for trivial edits, simple formatting, and direct factual answers.
mischacoster/image-skill Skill
0★Dual-provider image generator (OpenAI GPT-Image-2 + Google Gemini Nano Banana). Use this skill for all image creation unless the user explicitly invokes a different skill or MCP. Detect whether the user is exploring conceptually (--concept, dual, ALWAYS with diverse prompts), wants a final asset (--hq), text-rich content (--text), wants to place a product in a setting (--reference), or is iterating on a previous result (--session). When the user attaches images: automatically use edit mode.
xuluoforcainiao/analytics-data-analysis/analytics-data-analysis Skill
no license0★ repoImplement analytics, data analysis, and visualization best practices using Python, Jupyter, and modern data tools.
spartan-hieuvo/claude-skills Skill
0★Agent skills for publishing engineering artifacts to uselink — repo summaries, PR digests, changelogs, API docs, onboarding guides, reports, and specs. Each skill gathers data, generates HTML, and publishes via the uselink CLI.
TeamZaobi/co-scientist-hypothesis Skill
0★多智能体假设锤炼系统,复现 Google DeepMind Co-Scientist (Nature, 2026-05-19) 的完整架构。通过 Generation → Reflection → Ranking (Elo Tournament) → Evolution → Proximity → Meta-Review 六个专业 Agent 角色的迭代协作,对科学研究假设进行生成、辩论、淘汰和进化。支持 scientist-in-the-loop 反馈、test-time compute scaling、文献锚定和假设谱系追踪。当用户需要"锤炼假设"、"假设进化"、"hypothesis tournament"、"研究假设生成"、"多智能体辩论"、"Co-Scientist 式假设"、"假设锦标赛"时使用。
SandyCodfish/youtube-feed-declutter Skill
0★Use when someone wants to clean up or reset polluted YouTube recommendations by splitting one account's mixed interests into separate single-topic channels (e.g. a dedicated "study", "film", or "music" channel) — migrating curated subscriptions and seeding each channel's algorithm so its feed stays on-topic.
wuxiiing/agent-guide Skill
0★Audit and losslessly simplify persistent AI-agent instruction files such as AGENTS.md, CLAUDE.md, GEMINI.md, and project rule files. Use when reviewing, comparing, rewriting, or rebuilding these instructions; preserve original intent, account for every meaningful rule, route content to the right layer, and regression-check the result. Do not use to verify whether MCP servers, hooks, plugins, permissions, or other runtime integrations actually work, or for ordinary application-code editing.
Focus-GTS/firefly-services-skills/plugins/firefly-services/skills/firefly-batch-pipeline Skill
no license0★ repoThe end-to-end production reference architecture for high-volume generative campaign workloads on Adobe Firefly Services — SQS-fronted intake, Lambda worker pool with per-credential token-bucket pacing, Step Functions orchestration for multi-stage PSD composition, DynamoDB job state, S3 result persistence, DLQ replay, and webhook-driven customer notification. Use whenever the user mentions "batch pipeline", "campaign at scale", "thousands of images per day", "generative pipeline", "campaign assembler", "asset factory", "production-grade pipeline", or designs a system that combines Firefly generation with Photoshop composition at volume. Stitches `firefly-services-rate-limits` and `photoshop-api-composition` into a single deployable blueprint.
Blushyes/skills/skills/agent-cli-design Skill
0★ repo设计与编写命令行工具(CLI),尤其是给 LLM agent 驱动的 CLI —— 选对命令模型、输出形态、 护栏、文件架构。当用户在设计或编写 CLI、新增或重构 subcommand/verb、选 CLI 框架或库、 设计 flags / 寻址 / 批量操作、构建一个会被 agent 调用的工具,或重构一个长烂了的 CLI (上帝文件、纠缠的命令 handler、复制粘贴的 op 构造)时使用。触发词:"写/设计一个 CLI"、 "加个命令"、"CLI 架构"、"agent 友好的工具"、"命令行工具"、"做个我的 agent 能用的工具"、 "梳理我的 CLI 结构" 等 —— 即使用户没说"CLI"这个词、但明显在搭一个终端/命令工具,也应触发。 目前 TypeScript(commander)有完整参考,Go / Rust / Python 参考待补。
skyswordw/skillport/examples/after/changelog-bot Skill
0★ repoSummarize recent git history into a changelog entry. Use when the user wants a changelog generated from recent commits; pass the target version as the first argument to the helper script.
redamoon/skills/skills/blog-workflow Skill
0★ repoブログ記事の品質チェックワークフロー。textlint実行、プラットフォーム別フォーマット確認(はてなブログ/note)、読者目線レビューを一括で実行する。明示的にコマンドを打たなくても、記事の編集完了時にまとめて品質チェックを行う。
specdd/plugin-cline/skills/specdd-adopt Skill
0★ repoUse when Cline needs to add SpecDD to a project or update SpecDD framework files through the CLI before normal SpecDD work begins.
devlooped/vox-populi Skill
0★Generate a one-person-one-vote view of any Polymarket multi-outcome event, optionally filtering wallets by position size and reporting Yes/No voter splits per outcome.
Aetheris-Solutions-LLC/aetheris-claude-skills/plugins/aetheris/skills/aetheris-review Skill
0★ repoMulti-agent PR review with Aetheris ticket integration. Use when reviewing a PR in any Aetheris client project — auto-detects the project from the repo URL, pulls associated tickets and acceptance criteria into the review, posts a tiered PR comment (blockers + before-merge) and per-ticket findings to Aetheris. Triggered by /aetheris-review or /aetheris-review <PR#>.
kkkhushman/x-algo-skill Skill
0★Reason about X's open-sourced For You feed algorithm (xai-org/x-algorithm, May 2026): Phoenix Grok-based transformer with candidate isolation, two-tower retrieval, Thunder in-network store, home-mixer orchestration, candidate-pipeline framework, Grox content understanding, ads safe-gap blending. Use when: explaining how X ranks posts, designing or auditing a feed recsys, building on the For You codebase, comparing 2023 Twitter algorithm vs 2026 X algorithm, or troubleshooting questions about "candidate isolation", "Phoenix scorer", "weighted_score vs score", "two-tower retrieval", or why X's stack has no hand-engineered features.
navintkr/alteryx-fabric-migrator/skill Skill
0★ repoUse this skill when migrating an Alteryx workflow (`.yxmd`) to Microsoft Fabric. Triggers: "migrate alteryx", "alteryx to fabric", "convert yxmd", "rebuild alteryx workflow in fabric", "alteryx in lakehouse", "decode yxmd", "translate alteryx formula", any task that involves a `.yxmd` file or talks about moving an Alteryx workflow onto a Lakehouse / Notebook / Data Pipeline architecture.
aassoiants/thought-tracks Skill
0★At the end of a working session, passively analyze the conversation trace to extract a model of HOW the user reasoned (their method, not the topic), then diff it against the previous stored model to surface deltas. Use this whenever the user asks to "map my thinking", "model how I think", "run thought tracks", "close out this session", do a "reasoning retrospective", "capture this session", "update my model", or wants to track how their thinking is changing over time. Trigger at session end even when phrased casually ("what did you learn about how I think", "diff me against last time"). Do NOT require the user to answer questions or enter data, the session itself is the only input.
tainn03/openjar-cli/skills/openjar-indexer Skill
no license0★ repoQuery the local Maven/Gradle artifact index from the terminal. Use when you see an import but cannot find the class definition in the workspace (it likely comes from a compiled internal library), when you need to read the actual implementation of an internal or non-well-known library, or when you need to find which artifact contains a class, discover implementations of an interface, or inspect proto/resource files inside JARs. Do not use for well-known standard libraries (java.util, Spring core, etc.) that the AI already knows.
hive-intel/hive-skills/skills/hive-build-onboarding Skill
0★ repoUse this skill when the user needs a Hive API key or account — "I don't have a key", "how do I sign up", "I lost my API key", "set up Hive for me" — or needs browser sign-in versus headless/CI dashboard setup, key prefixes, or plan limits. Guide key creation without exposing secrets in chat, logs, screenshots, or committed files. After the key exists, route to hive-mcp or hive-cli to wire it up.
victoriacheng15/dev-toolchain/adr-gen Skill
0★ repoGuides the creation and management of Architectural Decision Records (ADRs) with immutable indexing.
taniiicom/visual-in-the-loop/skills/visual-in-the-loop Skill
0★ repoGenerate a single diagram (Nano Banana Pro / Gemini 3 Pro Image) of whatever you are about to ask the user to review or decide, and show it BEFORE you ask. USE PROACTIVELY whenever you are about to call AskUserQuestion, ExitPlanMode, or otherwise request a human decision on a multi-step plan, an ambiguous spec, an architecture choice, a UI mockup, or a set of options. Pipe the ACTUAL text of the plan or question into the skill verbatim — do not rewrite, summarize, split, or art-direct it; the model turns the real text into one diagram. Call this FIRST, then present the question. Humans review decisions far faster with a picture — do not just describe a diagram in text and skip this skill.
iustin-nita/plan-grill/skills/plan-grill Skill
0★ repoPlan, design, scope, or pressure-test work WITH the user before building. This is the DEFAULT skill for any planning request — use it proactively whenever the user says things like "let's plan…", "let's make a plan for…", "let's think about how to…", "plan how to migrate…", "how should we approach…", "help me plan/scope this", "what's the best tool/approach for…", "what do you need to know first", "give me options with tradeoffs", "grill me", or otherwise wants to settle open decisions before implementation. Explicitly covers migration planning and tool-choice decisions, AND still applies when the request also involves research or benchmarking first (do the research, then bring the findings into the questions). Reach for this instead of silently planning on your own, jumping straight to code, or treating it as a pure research task. It surfaces the real decision forks and resolves them through structured multiple-choice questions (via the AskUserQuestion tool) — concrete options, honest tradeoffs, and a recommended answer with reasoning — then synthesizes the choices into a concrete implementation plan. Do NOT use it when the user has already decided and just wants the change built, for pure debugging or code explanation, for plain ship/release checklists with no design forks, or for non-engineering planning (e.g. a marketing campaign) or grilling that isn't about the user's own build (e.g. prepping someone for an interview).
samariafar/agents/skills/code-style Skill
0★ repo🤖 agents 🧠 skills 🔌 mcp
tsaijamey/slide-whitespace-audit/skills/slide-whitespace-audit Skill
0★ repoThis skill should be used when auditing slide HTML files (1280x720 or other fixed-viewport layouts) for the common design anti-pattern of excessive whitespace and insufficient information density. It computes a quantitative whiteRatio by rasterizing all visible content elements (text nodes, images, SVGs, canvases, videos) onto a coarse grid and calculating the uncovered fraction of the viewport. Use after an LLM or sub-agent generates slide HTML to catch under-filled layouts before review. Trigger phrases: whitespace audit, slide design audit, coverage ratio, information density check, slide layout review, check slide for empty space, audit my slides, slide HTML coverage analysis, design density check, layout density audit.
jacobjennings/jj-openscad-skill/jj-openscad-skill Skill
0★ repoGenerate OpenSCAD code for 3D CAD modeling. Use when the user asks to create, modify, or reason about OpenSCAD (.scad) files, 3D models, parametric designs, CSG operations, 2D/3D geometry, extrusion, or solid modeling. Covers all OpenSCAD language features including primitives, transformations, boolean operations, list comprehensions, modules, functions, and advanced patterns. Also use for questions about OpenSCAD syntax, best practices, or parametric design patterns.
whiteknightonhorse/aipush-agent-skills/skills/acp Skill
0★ repoFree, open, security-verified agent skills for AEO (Answer Engine Optimization) — make any site ready for AI agents. Live: aipush.app
JordanChoo/acfs-agent-skills/agent-mail-ops Skill
no license0★ repoDiagnose and recover Agent Mail when agents report "AM is down", MCP Agent Mail is disconnected, or local configs drift away from the managed endpoint. Use when checking `agent-mail.service`, `127.0.0.1:8765`, rogue `mcp-agent-mail serve` processes, or split-brain caused by manual servers.