The catalog
609,344 rows, by stacks then stars
pencil20388-eng/ai-website-building Skill
1★零代码基础的非技术人员(市场、运营、产品)用 AI 从零做出一个可交付给开发的官网/落地页原型的完整方法。覆盖前期调研(竞品+SaaS实践+模板)、分模块生成、逐块微调、设计规范、图片处理、移动端适配、避坑清单、省 token 策略、多 agent 备份、以及给开发交付。核心前提是先知道自己要什么再下指令,每做一个新页面都要重新调研。当用户想用 AI 做网站、做官网、做落地页、做首页原型、改版网站、生成 HTML 页面,或提到"不会写代码但想做个网页""让 AI 帮我做官网""做个产品介绍页"等场景时,使用此 skill。即使用户没有明确说"用 skill",只要任务涉及非技术人员用 AI 产出网页,都应主动套用本方法。
avikbal-dm/claude-seo-skills/plugins/growth-os/skills/ai-search-visibility Skill
1★ repoGet a brand cited inside AI answers across Google AI Overviews, AI Mode, ChatGPT, Perplexity, Gemini, Copilot, and Claude. The tactical GEO and AEO module: baselines citation share, finds the citation gaps, restructures content for extraction, builds the evidence and entity signals AI engines reward, fixes crawler access, and tracks share of voice over time. Use when someone wants GEO, AEO, or AI Overview optimization, asks why AI engines do not cite their brand, wants to be the answer ChatGPT or Perplexity gives, or needs an AI search visibility plan. Strategy comes from cited-framework. This is the hands-on execution.
xiaot945/seven-habits-coding Skill
1★Use when designing or auditing AI coding workflows, deciding human/AI division of labor, diagnosing why Claude Code output feels reactive/off-target/low-quality, or onboarding to a new project and choosing which collaboration disciplines to enforce. Maps Stephen Covey's 7 Habits onto Claude Code practices as a diagnostic mental model.
Surfrrosa/claude-skills/a11y Skill
1★ repoAudit accessibility (WCAG) compliance in source code and optionally against live URLs
mb3rgel-ui/atlas-claude-skill/skills/coding-agent-loops Skill
no license1★ repoAtlas autonomous coding loops — run multi-step coding tasks with task-level checkpoints, automatic progress tracking, and blocker detection. Use when executing a coding task autonomously, running a build-fix loop, or implementing a sprint task end-to-end.
lilianobennett-ai/events-agent-skill Skill
no license1★Researches, evaluates, and recommends conferences, summits, and trade shows for B2B partnerships and growth teams. Use this skill whenever a user asks about events, conferences, sponsorships, speaker opportunities, CFP deadlines, trade shows, summits, or which events to attend. Also use when a user wants help comparing event ROI, evaluating sponsor packages, scoring events against their ICP, or building an events calendar. Trigger even when the user does not explicitly say "use the events skill" — any partnerships, BD, or marketing question about industry events should activate this.
AnaCataVC/amiga-ia/skills/ami-commit-planner Skill
1★ repoAnalyzes the working tree for uncommitted work, proposes a structured set of commits, waits for user approval, and executes them.
SkillMedev/ecommerce-dtc-ops/skills/abandoned-cart-sequence Skill
1★ repoDrafts a margin-aware 3-email cart-recovery sequence that reminds, handles objections, then incentivizes only as a last touch. Use when a checkout is started but not completed and you need cart-recovery (abandoned-cart) emails, when wiring an abandoned-cart flow in Shopify, Klaviyo, or similar, or when asked to recover lost carts without overspending on discounts.
The same file is in 1 other repository
HDHNezherParking-cum-Y638-Intl-Ltd/titan/skills/ops Skill
1★ repoSession operations spine — one continuous workflow: PREFLIGHT (verify repo state before trusting anything) → work → LAND (gate, commit, ledger, lessons, staleness sweep), plus DECIDE (owner-decision interview → dated record → propagation sweep) and COMMISSION (external template/prompt intake → conflict adjudication by the record). Use at session start ('preflight', 'resume', 'where were we'), when finishing a chunk ('land this', 'ship and log', 'wrap up'), when an owner-only decision is needed ('decide X', 'founder decision', 'interview me'), or when an outside prompt/template/brief arrives ('audit this commission', 'a template says...').
nyldn/fable5-optimizer/skills/fable5-optimizer Skill
1★ repoLoad this skill before answering whenever a request mentions Codex, GPT-5.5, codex commands, or Fable 5, or asks which model or agent should handle, review, implement, or verify something. That includes advisory questions (should Claude or Codex handle this, who should review this branch diff, is this worth delegating), not just direct commands. Also covers delegating bounded implementation, independent code review, data gathering, or runtime verification to Codex; optimizing Fable 5 usage or effort settings; and requests to test a flow, verify UI behavior, inspect a running app, or capture screenshots needing local browser/computer-use automation. Do not use for ordinary implementation or review with no model-ownership question, and not for generic prompt rewriting.
warstellar/agent-skills/skills/deslop Skill
no license1★ repoDetect, critique, and rewrite text to remove AI writing patterns — makes content sound human, specific, and credible. Use this skill whenever: writing any client-facing or published content from scratch; editing/polishing any draft that might sound "corporate AI"; asked to "make this sound more human", "remove AI patterns", "clean up AI text", "edit this", "improve this copy", "write a blog post / landing page / release note / announcement / marketing copy / product description". Also auto-apply when generating any text longer than ~3 sentences where quality matters. This skill should be consulted proactively — don't wait to be asked.
longyenkai83/personal-marketing-kit/skills/1-research/fb-insight-miner Skill
no license1★ repoDeep customer insight mining from public Facebook fanpage comments. Use when user wants to research customer pain points, desires, objections, voice-of-customer vocabulary, FAQ patterns, or silent signals from a Facebook fanpage (competitor or target niche). Scrapes posts+comments via Apify MCP then runs a 4-phase pipeline (preflight → collect → sample+analyze → enrich) to produce a Customer Insight Report in markdown. Vietnamese-output friendly. Triggers on phrases like "phân tích insight fanpage", "đào comment fanpage", "customer research FB", "pain points fanpage", "voice of customer FB".
SkillMedev/technical-writing-studio/skills/api-design Skill
1★ repoDesigns REST API surfaces - resource naming, HTTP method and status-code semantics, error shapes, pagination, and filtering - and delivers an endpoint spec a consumer can build against without asking questions. Use when someone asks "how should I name this endpoint", "what status code should this return", "should this be PUT or PATCH", "how do I paginate this list", or is reviewing an API before it ships to external consumers. Do NOT use for planning breaking-change rollouts and deprecation windows - use api-versioning-strategist instead; for GraphQL type and resolver design - use graphql-schema instead; for generating client SDKs from an existing spec - use api-client-generator instead; for designing inbound webhook endpoints - use webhook-receiver-hardener instead.
The same file is in 3 other repositories
BislanB/claude-skills-creativity/skills/creativity Skill
1★ repoGenerate creative, non-standard, original solutions to any problem — coding, architecture, design, naming, or strategy. Use this skill whenever the user asks for a creative approach, wants to brainstorm alternatives, says "think outside the box", "non-obvious solution", "creative", "original", "unconventional", "unexpected approach", "what if", or when the standard/obvious solution feels insufficient. Also use when the user is stuck, wants to explore alternatives, or asks "is there a better way". This skill transforms Claude from a conventional solution-finder into a creative thinking partner.
Fantasymax/easy-build-skills/plugin/user-research-for-ai-config/skills/user-research-for-ai-config Skill
no license1★ repoCRITICAL: If user says "design/make a skill for X" / "我想做一个 XX 的 skill" / "帮我做个 AI 写 XX 的 skill" — DO NOT write it yourself, USE THIS SKILL to interview them first. That IS the purpose. Use for personalized AI config or custom skill via structured self-interview, not copying templates. Two outputs: (A) Principles — CLAUDE.md / AGENTS.md / .cursorrules / system-prompt for Claude Code / Cursor / Codex / OpenCode / Aider etc. (B) Custom skill — design from scratch OR extract recurring task; works whether user has a clear task or needs AI to discover one. Trigger: 我的 principles / 自己的 skill / 个性化 AI / 帮我设计一个 skill / 我想做一个 XX 的 skill / 让 AI 写 XX 的 skill / 把我会的事教给 AI / build my own CLAUDE.md / make a custom skill / design a skill from scratch / build a skill for X / AI that understands me. Do NOT use for customer research, product discovery, market research.
enmr10/token-doctor/skills/token-doctor Skill
1★ repoAudits and reduces token usage in context files (CLAUDE.md, AGENTS.md, memory files, docs). Measures token cost per file, finds waste (filler words, verbose phrases, blank bloat, oversized blocks), and safely compresses prose while preserving all code, inline code, URLs, file paths and tables. Use when your context files feel bloated, prompts are expensive, or you want to trim CLAUDE.md without losing meaning. Trigger: "reduce tokens", "token usage", "trim my CLAUDE.md", "compress context", "shrink memory file", "context too big", "save tokens", "audit token cost", /token-doctor. For skill description collisions, see skill-doctor.
SrCodexStudio/Claude-Forge/skills/headroom-compress Skill
no license1★ repoContext compression audit. Detects stale file reads, bloated Bash output, redundant content, and wasted tokens. Produces a compression report with estimated savings and actionable recommendations.
aei-soli/claude-skills/plugins/ai-portfolio-manager/skills/ai-portfolio-manager Skill
1★ repoManage a whole portfolio of projects with AI — a persistent master tracker of all projects, plus weekly sprint plans that allocate tasks across AI models, subscriptions, agents, and the human, with model routing, usage-budget management, mid-sprint check-ins, remediation, and end-of-sprint cost/usage reports. Use this skill whenever the user wants to organize or track multiple projects, set up a project tracker or task list, plan their week or sprint with AI assistance, asks which AI model or tool to use for which task, mentions hitting usage limits or wanting more from their AI subscriptions, or reports being behind on a plan and needing to re-plan. Trigger even without the words "sprint" or "tracker" — phrases like "help me get all my projects under control", "I have too many things going on", "plan my AI work", "I keep running out of Claude usage", "which model should do what", or "I'm behind, what do I drop" all qualify.
Agents365-ai/ttsCN/skills/ttsCN Skill
no license1★ repoTTS, Cloud-Native — one CLI, every TTS cloud. 11 backends (Edge/Azure/Doubao/CosyVoice/Tencent/Baidu/MiniMax/Xunfei + ElevenLabs/OpenAI/Google), native word-level timestamps on 5 platforms, [PAUSE:x] markers, pinyin phoneme overrides, voice cloning, agent-native JSON CLI.
dapih/cobaduluk/skills/excel-to-json Skill
1★ repoConvert a complex Excel/xlsx table into validated, schema-backed JSON. Use when the user wants to parse a spreadsheet into JSON, create or validate a JSON Schema for tabular data, convert an Excel table that has merged cells or hierarchical / multi-level rows, or run any stage of the pipeline (inspect, schema, convert, validate, data-quality review). Triggers on phrases like "convert this Excel to JSON", "parse the xlsx", "make a JSON schema for this table", "validate my JSON instance", "data quality check the conversion".
zavora-ai/skill-hris-people-operations Skill
no license1★Orchestrate HR operations — employee lookup, department management, time-off requests, payroll queries, org chart navigation, and headcount reporting. Use when looking up employees, managing leave requests, checking org structure, running payroll, viewing the directory, or analyzing headcount.
Mcgrass-ops/android-studio-pipeline/skills/android-compose-design Skill
1★ repoAndroid-specific UI/UX and engineering system for Jetpack Compose apps. Use this skill whenever building, modifying, reviewing, or designing any Android app screen, component, or layout - even if the user doesn't explicitly mention design, Compose, or Material. Routes between five distinct visual styles (m3-expressive-default, dark-product-minimal, playful-warm, data-dense, trust-signaling) based on the app's purpose, then applies an engineering track covering architecture, state, platform integration (edge-to-edge, splash, predictive back, permissions), accessibility, performance, and build defaults. Use this proactively for any Android development work, not just when "design" is named in the prompt.
zavora-ai/skill-calendar-scheduling Skill
no license1★Orchestrate calendar operations via Google Calendar and Microsoft Graph — find free time, schedule meetings, manage events, track RSVPs, and coordinate across timezones. Use when scheduling meetings, checking availability, creating events, finding free slots, managing calendar invites, or coordinating meeting times.
DQT-bit/claude-skill-weidu Skill
1★微读(weidu)——读 mp.weixin.qq.com 公众号文章的稳定姿势。绕开层层叠叠的反爬:Jina/WebFetch/curl 全被拦或返回验证码页。 名字寓意:「微」=微信,「读」=读得到;两个字直说"让你能读到微信公众号文章"。 方法论:PowerShell HttpWebRequest 拉原始 UTF-8 字节(避开 Invoke-WebRequest 的 UTF-8→GBK 编码污染)+ Python 双容器兜底(js_content 旧版 + content_noencode 新版沉浸式)。 当用户给出 mp.weixin.qq.com 链接、要读 / 解读 / 摘要 / 提取一手数据时使用。 触发词包括但不限于:mp.weixin.qq.com/s/ 链接(任何形式)、读一下这篇微信文章、看下这个公众号、读这个链接、解读这篇文章(链接是公众号时)、提取这个公众号文章的关键信息、摘要一下这篇微信文章、微读看一下、用微读读。 即使用户只是丢一个公众号链接没说话,也应该触发——丢链接 = 想读。 不要用于非 mp.weixin.qq.com 域名(用 WebFetch / Jina 就够);不要用于需要登录态的微信内容(公众号订阅页、付费内容);不要用于公众号视频号/图文卡片(容器结构不同)。
daiyanHasin/chat-snapshot-skill Skill
1★Compresses and exports the entire current conversation into a compact, portable JSON file that can be downloaded and used to resume context in any new chat or LLM (Claude, ChatGPT, Gemini, etc.). Also restores context from a previously uploaded JSON snapshot file. TRIGGER this skill automatically when the user types: - /export — compress entire chat into a downloadable JSON snapshot - /snapshot, /save, /compress — same as /export - "save my chat", "export context", "compress this conversation" - "running out of tokens", "context is full", "quota is low", "save before I run out" ALSO TRIGGER when the user uploads a .json file and says anything like: - "resume", "restore context", "load my snapshot", "continue from this" - "here is my context", "here is my json", "I uploaded my snapshot" - or simply uploads a .json file without saying anything — check if it looks like a chat snapshot Use this skill even if the user phrases it casually like "save this" or "I want to continue later".
Skill knowledge base management
zavora-ai/skill-knowledge-base-management Skill
no license1★Manage knowledge base — search articles, find related content, create drafts, publish articles, collect feedback, and detect knowledge gaps. Use when searching for solutions, creating KB articles, finding related content, identifying gaps, or improving article quality.
zavora-ai/skill-forms-data-collection Skill
no license1★Build and manage forms — create forms, add fields with validation, publish, collect submissions, and analyze responses. Use when creating forms, building surveys, reviewing submissions, validating input, or analyzing response data.
zhujian0409/thorough-check-skills/thorough-check Skill
1★ repo用于彻底复核刚修改过的代码或配置,覆盖改动点、边界条件、文件完整性、上下游调用链,以及任何参数或代码改动引发的业务语义变化、历史数据兼容、清理任务、回调/事件、幂等和状态迁移风险。用于实际复核时,默认启动独立 agent 做并行影响面扫描和最终反证复核;token 成本不是省略 agent 的理由。没有真实命令输出证据时不宣称“OK”。触发语包括“改完了帮我再仔细检查一遍”“各种边界都 ok 吗”“流程链条都对吗”“能确定不会出问题吗”“这个参数改了会不会影响上下游”等。
hildahanyuwang/log-your-work Skill
1★After completing any substantive coding task — writing a feature, fixing a bug, refactoring, running an experiment — emit a "report card" alongside the code so the human can explain what changed, why, and what's next without re-reading everything. Use this whenever you finish a unit of work the user will eventually have to report on, defend in a meeting, or hand off — especially in fast "vibe coding" sessions where the human didn't write the code line-by-line and won't otherwise have the details in their head. Trigger even if the user didn't explicitly ask for a summary; the cost of being asked "where's the code for this?" in a meeting and not knowing is exactly what this prevents. Also use when the user says "log this," "what did we do," "write it up," "append to the worklog," or asks for a standup/status update on recent work. Supports a condensed "exec" version (triggered by "/ai-worklog exec" or "for a non-technical manager") that drops code-level detail for non-technical stakeholders. The same applies to AI-assisted knowledge work — analysis, reports, research drafts — where the reasoning and the source-checking vanish just as fast; coding is the primary case, knowledge work a documented secondary mode.
agasi-gif/negotiation-trainer/skill Skill
no license1★ repoConstruction industry negotiation sparring trainer with AI opponent and coach debrief. Use when the user wants to practise negotiations, run a scenario (supplier, client, GC contract, hiring, equity split), get a tactical hint, or receive a scored breakdown of their negotiation technique.
redwoodmeridian/ranql-skills/plugins/ranql/skills/ad-creative-studio Skill
no license1★ repoUse when the user wants to CREATE ad creative — design new Facebook/Instagram/Google ads (static OR video), generate ad images, write ad copy, or turn competitor intel into their own ads. Triggers include "make me some ads", "create ad creative", "design an ad", "build this in Canva", "make me a video ad", "new creative", "ad variations", or any request to produce (not just analyze) ads. Combines the brand kit + competitor teardown + organic hooks into on-brand, better-than-competitor creative. Uses Canva if connected, otherwise renders with Claude's own design skills. Requires brand-kit-extractor and competitor-ad-teardown first.
leobbaroni/maestro/skills/maestro Skill
1★ repoUnified design, motion, 3D, and video super skill. Use for designing or improving any UI (websites, landing pages, dashboards, product UI, components), art direction and design systems, extracting Design DNA from reference UIs, UI critique/audit/accessibility hardening, motion design and animation (CSS, WAAPI, Motion/Framer Motion, GSAP, ScrollTrigger), Three.js/WebGL/R3F scenes, generative art, and authoring videos (HyperFrames or Remotion) — promos, explainers, kinetic typography, motion graphics. Also use when the user says "maestro", wants design options/mockups, or wants a design plan stress-tested before building.
itaybnv/openmc-claude-skills/.claude/skills/sync-openmc Skill
1★ repoMaintenance skill for the openmc-claude-skills knowledge base. Diffs two OpenMC release tags (OLD NEW, e.g. v0.15.2 v0.15.3), maps changed Python source files to the affected KB doc files, writes a per-release migration notes file at skills/openmc/releases/vNEW.md, and updates .last-synced-release. Invoke as: /sync-openmc v0.15.2 v0.15.3. Requires gh CLI (authenticated) and curl. This is a maintainer-only tool; the consumer openmc skill is separate.
Ekko-Coleman/loopita Skill
1★Use at the start of complex or large work — shipping several features at once, big refactors or migrations across many files, "keep going until it's green" loops, or researching and comparing multiple options — even if the user never says "orchestrate." Loopita picks a strategy (a single pass, a loop with an explicit end condition, or a parallel swarm of sub-agents), breaks the work into scoped slices, keeps your main context lean, and produces an audit trail. Especially reach for it when a task is too big to track in one context or benefits from running sub-agents in parallel.
OU-GC/Practical-Claude-Code-Skills-for-Chinese-speaking-Masters-Students/skills/paper-reader Skill
no license1★ repoUse this skill whenever the user asks about research papers, academic literature, technical concepts from papers, method explanations, related work comparisons, or anything involving reading, summarizing, or discussing scientific/engineering publications, especially in robotics, vision-language-action (VLA) models, computer vision, machine learning, deep learning, and reinforcement learning. Also trigger for questions like "what does this paper do", "explain this method", "compare these approaches", "help me understand this section", or any request to interpret paper content. The user prefers concrete, direct explanations that anchor abstract concepts with analogies or concrete examples. Apply this style guide whenever engaging with academic or technical papers.
k4thir/smart-eda Skill
1★Adaptive exploratory data analysis. Use whenever a tabular dataset (CSV, Excel/xlsx, Parquet, TSV, JSON-lines, or an in-memory DataFrame) needs to be understood — including any request like "analyze this data", "explore this dataset", "what's in this file", "summarize this CSV", "EDA on this", "profile this data", "look at the distributions", "check for outliers", "what are the patterns here", or simply when a data file is uploaded with no explicit task. Also triggers for data-quality audits, missing-value investigations, correlation analysis, time-series profiling, and pre-modeling data understanding. Prefer this skill over ad-hoc analysis whenever the user's data hasn't been examined yet, even if they just say "take a look" or "what do you think". The skill profiles the data first, then chooses techniques based on what it actually finds — column types, scale, time structure, target presence — instead of running a fixed playbook.
hootbu/llm-wiki-mind/skills/vault-init Skill
1★ repoMevcut bir projeye llm-wiki-mind pattern'ına göre yeni bir Obsidian bilgi arşivi (vault) kur ve projeye bağla. Kullanıcıdan proje yolu ve vault yolunu alır, GitHub'daki Hootbu/llm-wiki-mind template'ini kullanarak kurar, projenin CLAUDE.md'sine vault işaretçisi ekler. Proje yolu olmadan (salt-vault) da kurulabilir. Yazılım, araştırma, kitap okuma, kişisel günlük gibi her alan için kullanılır.
Dom1ng0s/Claude-Skills/audit Skill
1★ repoRealiza uma auditoria no código (Frontend/Backend) em busca de bugs, vulnerabilidades e más práticas.
vivaldi007/ux-psychology-skill Skill
1★Use when designing, building, or reviewing any user-facing interface — forms, onboarding, signup flows, pricing pages, dashboards, CTAs, loading/empty/error states, checkout — or when diagnosing conversion drop-off, form abandonment, or user-trust problems.
igorrendulic/task-graph Skill
no license1★Turn approved implementation plans into plan-isolated task files and a conservative executable DAG in .agent/<plan-slug>/.
bydeng01/phd-application-skill/skills/application-materials Skill
1★ repoTailor and optimize academic application documents — CV, resume, statement of purpose (SOP), and personal statement — for a specific PhD opportunity. Use this whenever the user wants to adapt, customize, write, polish, or optimize application materials — e.g. "tailor my CV for this position", "write an SOP for MIT EECS", "customize my personal statement for the Smith lab", "make my resume fit this studentship", or "optimize my statement for this professor". Selects, reorders, and emphasizes true material from the applicant's master CV and profile to fit the target; never invents credentials. Writes tailored documents to knowledge-base/applications/[id]/. Trigger whenever the intent is to prepare or adapt CV/SOP/personal-statement material for a specific application.
kostiantyn-matsebora/canopy/skills/canopy-debug Skill
1★ repoTrace any Canopy skill with live phase banners and per-node tree tracing. Respects the current mode — in plan mode no changes are applied; in edit mode the skill executes normally.
SkillMedev/designer-to-dev-handoff/skills/color-accessibility Skill
1★ repoAudits and repairs color palettes against WCAG contrast thresholds - 4.5:1 for body text, 3:1 for large text and UI components, 7:1 for AAA - and makes them safe for color-blind users, delivering a verified pairing table. Use when someone asks "does this color pass contrast", "make my brand color accessible", "is this palette color-blind safe", "why did my contrast check fail", or is remediating color findings from an audit. Do NOT use to invent a brand palette from scratch - use color-palette-builder instead; for a full accessibility review beyond color, use accessibility-audit.
The same file is in 2 other repositories
Reverse engineering skill github copilot
sarveshtalele/reverse-engineering-skill-github-copilot Skill
no license1★Reverse engineer any GitHub repository OR any project already sitting in a local folder — produces a complete 4-section analysis: (1) System Design Overview (full architecture, codebase metrics, API catalog, data model, dependency graph, modernization roadmap), (2) Authentication & Access Control (detects RBAC role-based, ABAC attribute/policy-based, and ReBAC relationship-based patterns with named roles, policies, and route protection map), (3) Business Logic Extractor (business domain, core workflows end-to-end, user roles, key business rules, entity glossary, external integrations), (4) Screen-by-Screen Navigation (complete UI screen inventory, Mermaid navigation flowchart, end-to-end user journey for web apps including ASP.NET Web Forms .aspx pages, MVC Razor views, React/Vue/Angular SPAs, JSP pages). Trigger this skill when the user says: reverse engineer, analyze this repo, analyze this codebase, analyze this project/folder, what does this codebase do, explain the system design, document the architecture, extract business logic, show me how this web app navigates, what auth does this project use, screen flow — OR provides any github.com URL, OR provides/implies a local folder path (e.g. "reverse engineer this project", "analyze the code in this repo", "document the folder I'm in", "reverse engineer C:\Projects\LegacyApp") with intent to understand or document it. No Anthropic API key required — GitHub Copilot is the AI engine.
youaifuou/occam/occam Skill
1★ repoUse only when the user explicitly invokes $occam. Apply Occam's razor to the entire task: establish the minimum sufficient conditions that cannot be compromised, choose the trustworthy solution with the lowest total lifecycle complexity, complete risk-proportionate execution and verification, and deliver the result with only the minimum sufficient information. Can be layered with other Skills.
dheerajsukumar/seo-growth-director/.claude/skills/seo-growth-director Skill
no license1★ repoEnterprise SEO Growth Director specializing in Technical SEO, Content Strategy, AI Search, Entity SEO, Local SEO, Website Migrations, Executive Reporting, and Growth Strategy. Automatically use this skill whenever the user requests SEO audits, keyword research, content optimization, AI Search optimization, website analysis, migration planning, competitor analysis, SEO strategy, or executive SEO reporting.
kennguyen887/agent-foundation/skills/authoring-project-skills Skill
1★ repoUse when creating, updating, reviewing, or deciding whether to write a project skill (docs/skills/*.md) — covers the file template, verb-led naming, the quality bar, the pre-write 5-weakness self-check, and when NOT to write a skill. Pairs with the always-on "scan docs/skills before a task / create-or-update after" rule in CLAUDE.md.
rhino-ty/principled-git-commit Skill
1★Conventional Commits 1.0.0 + best-practice workflow for git commit messages that serve four readers — `git log` scanners, `git blame` tracers, `git bisect` hunters, and AI agents (LLMs rebuilding context after `/clear`, reviewing PRs, generating changelogs, answering natural-language history queries). Five founding principles (atomic / leaves-repo-green / why-over-what / imperative / searchable), five-step workflow (diff inspection → staging → type decision tree → secrets blocklist → pre-commit checklist), explicit Breaking-Change / Revert / Amend / Trailer protocols, and a dialect scaffolder that generates per-project `docs/references/COMMIT.md` for project-specific extensions (domain proper nouns, custom trailers like `Refs:` / `Flag:` / `Plan SC:`, workflow hooks like PDCA / Linear / Jira / squash-merge PRs). ALWAYS trigger this skill when the user: (1) asks to write, generate, or improve a commit message (2) pastes a commit-message draft for review or critique (3) asks "should I split this commit?" / "what type for this change?" / "is this breaking?" (4) is finishing a logical unit of work and about to run `git commit` (5) mentions stage / staging / amend / revert / fixup / cherry-pick in a commit-authoring context (6) asks how to set up PDCA / Linear / Jira-driven auto-commits (7) requests scaffolding a `COMMIT.md` dialect file for a project Triggers (multi-lingual): EN: commit, git commit, stage, commit message, breaking change, conventional commits, revert, fixup, amend, cherry-pick, changelog KO: 커밋, 깃 커밋, 스테이지, 커밋 메시지, 커밋 룰, 컨벤셔널 커밋, 리버트, 되돌리기, 어맨드, 커밋 컨벤션, 커밋 메시지 검토 JA: コミット, git コミット, ステージ, コミットメッセージ, ブレーキング チェンジ, リバート, アメンド ZH: 提交, git 提交, 暂存, 提交信息, 提交消息, 重大变更, 回滚, 修订 ES: commit, mensaje de commit, preparar, cambio incompatible, revertir FR: commit, message de commit, indexer, changement incompatible, revert DE: Commit, Commit-Nachricht, Staging, breaking change, revert IT: commit, messaggio di commit, modifica incompatibile, revert Do NOT trigger for: pure code generation unrelated to git, branch/merge/ rebase mechanics not about message authoring, CI/CD pipeline configuration, or non-git version-control systems. Audience: developers writing git commits. Use technical terms directly. Korean prose variant available at `lang/ko/SKILL.md` for Korean-first readers — the convention itself stays English-default regardless of variant.
Davienzomq/stuntdouble/skills/stuntdouble Skill
1★ repoYour frontier model is the star — stop making it do the stunts. Two modes. ADVISOR: analyzes a task and recommends the best AI model (Anthropic/OpenAI/Google) with the exact switch command. ORCHESTRATOR: stays ON for the whole session (like a mode toggle) — every task gets scored, decomposed, and dispatched to "stunt double" workers running the cheapest capable model OF THE HOST'S OWN PROVIDER (Claude models in Claude Code, OpenAI models in Codex, Gemini models in Gemini CLI), with the star (strongest model) doing only the final close-up: verification. TRIGGER on /stuntdouble, "stuntdouble on/off", "which model should I use", "select the best model", "optimize model usage", "is this task worth Opus". DO NOT TRIGGER when the user asks about model pricing/APIs in their own application code.
SkillMedev/personal-operating-system/skills/decision-making Skill
1★ repoRuns a structured decision process for high-stakes choices - reversibility classification, weighted decision matrices, expected value with explicit probabilities, pre-mortems, second-order thinking, and 10/10/10 - and produces a documented recommendation plus a decision-journal entry. Use when someone asks "should I take this job or stay", "how do I decide between these two paths", "I keep going back and forth on a big decision", or "help me think through whether to relocate". Do NOT use for evaluating a specific large purchase like a house, car, or equipment - use big-purchase-decision instead.
The same file is in 1 other repository
punkaze/skills/plugin/skills/bruno Skill
1★ repoBruno, the Git-friendly API client, and its CLI (bru). Use when authoring or editing .bru requests/collections, generating a collection from an OpenAPI spec or a codebase's routes, writing Bruno tests or scripts, managing environments and secrets, or running collections with `bru run` (local or CI).
siyangqi522-eng/digital-kitty-analyst Skill
1★用心理学与思维模型为数字小猫(AI 虚拟宠物/陪伴类产品)做早期阶段的市场调研、用户洞察、竞品分析、商业模式与增长策略。当用户提及数字宠物、AI 陪伴、虚拟猫、虚拟宠物、市场调研、竞品分析、用户画像、需求验证、定价、变现、留存、增长、PMF、用户洞察、虚拟养成、AI 陪伴产品、Replika、Character AI 等关键词时触发。
yeshelloAB/investment-analysis-skills/skills/alpha-scanner Skill
1★ repoWeekly alpha scan identifying fundamentally sound stocks near 52-week lows and unloved sector opportunities across US (NYSE/NASDAQ) and AU (ASX) markets. Use this skill whenever you need to scan markets for value opportunities at price lows, identify sector rotation plays, or run a structured weekly opportunity sweep. Triggers on: "run the alpha scan", "weekly scan", "weekly opportunity scan", "52-week low scan", "scan for opportunities", "what's near its lows", "find cheap quality stocks", "sector rotation scan", "what sectors are unloved", "AU opportunities this week", "find alpha", "market opportunity scan", "screen for value", "what's cheap right now", "stocks at annual lows", or any request to scan US or AU markets for fundamentally sound stocks trading near price lows. Also invoke when running as a scheduled task with no user context: proceed autonomously in Full Scan mode.
kwakseongjae/some-engineer-mind/ask-before-guess Skill
1★ repoStops Claude from stacking guesses on top of unknowns. When uncertainty appears in code, configs, APIs, or error messages, this skill forces a brief pause to verify — by reading source, running a small check, or asking the user — instead of fabricating a plausible-sounding answer. 모르는 지점 위에 추측을 쌓아 코드를 만들지 않도록, 막혔을 때 *말하고 묻는* 길을 먼저 권하는 엔지니어링 철학 스킬.
Xindaan/claude-skills/skills/handover-spec-pack Skill
1★ repoTransformiere explorative Artefakte — Code-Repos, Excel-Dateien, JSON, CSV, SQL — in ein reviewbares, übergabefähiges Spezifikationspaket für formale Software- oder Einführungsprozesse. Verwende diesen Skill immer wenn der Nutzer ein Prototyp-Artefakt (Repo, Excel, Tabelle, Rapid-Prototype, PoC) analysieren, dokumentieren, spezifizieren oder für eine Übergabe vorbereiten möchte. Auch geeignet bei Anfragen wie „schreib mir eine Spec", „mach ein Handover-Paket", „dokumentiere dieses Repo", „extrahiere die fachliche Logik aus dieser Excel", „was tut dieses Artefakt", „bereite das für die Entwicklung vor", „erstelle User Stories aus dem Prototyp", „Review Pack für Stakeholder", oder wenn der Nutzer ein Artefakt für Dritte aufbereiten oder übergeben will. Deckt auch den formalen SDLC-Einstieg ab: „Spezifikation aus dem Prototyp", „SDLC-Übergabepaket", „Abnahmetests generieren", „was muss neu gebaut werden", „Aufwand schätzen für die Produktivumsetzung". Der Skill ist tool-agnostisch und funktioniert in Claude Code, Claude Cowork, und Claude.ai.
GeorginaSteele/running-coach Skill
no license1★Apply expert running-coach judgment to any training task — reviewing a logged Garmin session, building a weekly preview, planning a new training block, race-day strategy, ad-hoc questions (pacing, fueling, niggles, routes), or proposing calendar changes. Use whenever the user asks for feedback on a run, parkrun, long run, or strength session; discusses their training plan, mileage, paces, HR zones, or recovery; asks about an upcoming race (especially a half marathon or 5K target); describes a niggle, soreness, or injury concern from running; or references logged Garmin activities, splits, or training journal entries. Trigger even without explicit "coach me" — phrases like "review my run", "how did I do today", "what should I do this week", "I'm building toward a race", "my long run", or "what's the plan tomorrow" all warrant this skill.
adaptocms/adapto-cms-agent-skills/plugin/skills/adapto-content-create Skill
1★ repoWrite the briefed content — for each approved brief, dispatch the writer agent (top-tier for cornerstone pieces) to produce a complete, on-brand Markdown draft with SEO/AEO/GEO metadata and internal links, then run the editor critic and revise. Writes dated md drafts for your review; no CMS writes.
zavora-ai/skill-pdf-document-management Skill
no license1★Orchestrate PDF operations — inspect structure, extract text/tables/metadata, generate business documents (invoices, contracts, certificates), convert between formats, manipulate pages, secure with encryption/redaction, and fill forms. Use when working with PDFs, creating invoices, extracting data from documents, converting PDF to markdown, merging/splitting files, filling forms, redacting sensitive data, or generating business documents.
ZairaLabs/Skills/building-for-agents Skill
no license1★ repoMake a developer tool agent-ready, grounded in the Zaira Standard v0.9. Use when asked to improve a tool's readiness for AI agents, prepare for a Zaira evaluation, add llms.txt or AGENTS.md, design an MCP server or API surface for agents, fix error responses or rate-limit communication, add non-interactive authentication, make a CLI or config format safe for agents, or review a repo for agent-readiness gaps.
zavora-ai/skill-sales-operations Skill
no license1★Orchestrate enterprise sales — create proposals, configure quotes (CPQ), manage outreach sequences, schedule meetings, track signatures, and forecast pipeline. Use when creating proposals, generating quotes, managing sales sequences, scheduling meetings, tracking e-signatures, analyzing win/loss, or forecasting revenue.