The catalog
608,253 rows, by stacks then stars
chetankejriwal/case-interview-coach Skill
0★Run realistic consulting-style case interview prep — growth, profitability, and product-strategy cases. Use when the user is preparing for a case or product interview (e.g. BCG, BCG X, McKinsey, Bain, or PM/strategy rounds), wants to be mock-interviewed, wants an interviewer persona built from a real profile, or asks for sharp critique and scoring on their case solving.
zreed3/codex-conductor/skills/codex-handoff Skill
0★ repoHand off a project or task to the OpenAI Codex CLI with full orchestration — loads the user's Codex config, applies OpenAI's official best practices, builds a tiered multi-agent execution plan, and runs the delegate-and-verify loop. Invoke when the user types /codex-handoff, or asks to hand a task/project over to Codex, run a Codex-orchestrated build, or delegate substantial work to their OpenAI tokens.
manman1414/frontend-refactor-skills/skills/behavior-preserving-refactor Skill
0★ repoPerforms behavior-preserving frontend refactors in React, Vue 2/3, and TypeScript without changing UI or runtime semantics. Use when renaming components, extracting hooks/composables, simplifying JSX/templates, deduplicating props logic, inlining or extracting functions, or when the user asks for a safe refactor with no behavior change.
nusantara-ventures/exchangerate-skills/skills/exchangerate-dev Skill
0★ repoUse the exchangerate.dev API correctly for anything involving foreign-exchange rates — fetching live or historical currency rates, converting amounts between currencies, building FX time-series, or wiring the exchangerate.dev MCP server into an agent. Use this skill whenever the user mentions exchange rates, currency conversion, forex/FX data, "USD to EUR", multi-currency features, or needs a rates API — even if they don't name a provider. Works keyless out of the box (no signup needed to try it).
dimeazza/sonnet--elevation/skill Skill
0★ repoProtocolo de elevación para que un modelo de trabajo diario (p.ej. Sonnet) opere lo más cerca posible del nivel de un modelo frontier comprando profundidad con cómputo de inferencia. Usar SIEMPRE en tareas L3-L4 - decisiones con trade-offs, arquitectura, sprints multi-archivo, análisis de riesgo o compliance - y cuando el usuario escriba "ELEVA", "ultrathink" o "analiza a fondo". Los cartuchos de juicio destilado se generan con references/prompt-destilado.md y se guardan en references/.
nubasu/Pseudo-Fable-Framework/.claude/skills/agent-framework-doctor Skill
0★ repoStatic health check for an agent framework (pseudo-fable family) installation in a target project — component inventory by version signature, exclusivity violations, duplicate appends, skills placement and frontmatter mismatches, harness hooks / settings / line-ending checks, version drift against the store. Reports PASS/WARN/FAIL with a one-line fix each, then the manual smoke-test checklist. Use after agent-framework-setup, after a manual install or upgrade, or when an install misbehaves (skills not listed, hooks not firing).
cozren/claude-code-setup/skills/audacity-check Skill
no license0★ repoCritiques app ideas for "Audacity" and "Taste," preventing generic AI-generated "slop" and providing unique, scroll-stopping engineering pivots.
surendranb/loadout/skills/mac-health-check Skill
0★ repoMonthly macOS health check and performance optimization for Apple Silicon and Intel Macs. Measures memory, storage, compute and thermals, battery, SSD wear, and startup load; diagnoses the actual bottleneck (not symptoms); proposes ranked, reversible fixes; never deletes without explicit approval. Use for "check my Mac's health", "optimize my Mac", "why is my Mac slow", "free up disk space", "monthly Mac maintenance", or any Mac performance or longevity request.
Apify logistics and delivery routes
johnisanerd/claude-skill-logistics-and-delivery-routes/apify-logistics-and-delivery-routes Skill
no license0★ repoPlan and price logistics and delivery routes with the Apify Google Maps Directions API Actor (johnvc/google-maps-directions-api). Run one lane at a time (a depot to a stop, a technician to a job site, a store to a customer) and get distance, ETA, per-mode travel times, and turn-by-turn steps back as JSON, then loop lanes into a travel-time table, compare a depart-at against an arrive-by window, or refresh every corridor you watch on a schedule. Use when the user asks about logistics and delivery route planning, delivery ETA estimates, drive-time or travel-time matrices, field-service dispatch windows, service-area coverage checks, courier lane costing, or transit analysis for a commute. Pay-per-route billing, MCP-ready for Claude and other AI agents.
Anonymousyz/ai-launch-red-team Skill
0★AI 上线否决卡:对“AI 功能或 Agent 准备上线”的方案做结构化红队评审,扫描 8 条否决条件, 按七个维度追问缺口,输出可带进评审会的否决卡。Use when the user wants to review, challenge, or red-team an AI launch, pilot, or deployment plan (AI 上线评审 / 就绪度检查 / 方案红队 / launch readiness review), or pastes a proposal claiming an AI system is ready for production.
mythren/git-fence/skills/archaeology Skill
0★ repoInvestigate why code exists before changing it, using indexed git history (commit -> PR -> issue). Use when a git-fence warning fires, when the user asks why code exists or whether it is safe to delete, before removing a check/workaround/special case that looks unnecessary, or when simplifying old code.
88plug/cynefin/skills/cynefin Skill
no license0★ repoUse before choosing how to solve a problem, make a decision, plan work, diagnose a bug or incident, or pick between approaches — whenever the response should depend on what KIND of problem it is. Triggers on "how should we", "what's the best approach", "which option", deciding/planning, root-cause and incident work, design/architecture/refactor calls, and any "I'm stuck / this is uncertain / nobody's done this". The move: read the system by its constraints, place the Cynefin domain (Clear / Complicated / Complex / Chaotic — or admit Disorder), and apply the matching response — sense-making, never sorting into a 2x2. For the Complex domain, design a safe-to-fail probe portfolio, not a solution. Reach for it by default on non-trivial decisions; skip it for mechanical single-answer tasks.
Thilina099/rubysky-skills/skills/hipaa-marketing-check Skill
0★ repoUse when a healthcare organization (medical practice, clinic, hospital, dental, therapy, med spa, telehealth, senior care) wants to check its website, analytics, and advertising for tracking-pixel and patient-privacy risk. Symptoms include Meta Pixel or Google tags on appointment or portal pages, retargeting ads following patients, uncertainty about the OCR tracking-technology guidance, or concern about the wave of pixel lawsuits and settlements against providers.
MrEmanAhmad/yt2skill/examples/example-skill Skill
0★ repoA hand-written sample showing the shape yt2skill produces. Reach for the real thing when you need to turn a tutorial video or a manual into a skill an agent can follow.
LunaAI519/motion-skill Skill
0★Motion风格动画生成:参考图 → Nano Banana 生成关键帧 → Seedance 2.0 生成视频。触发词:/motion、动画、把图动起来、motion动画、图生视频。
brandon-haugen/proctor-skill/.claude/skills/proctor Skill
0★ repoComprehension quiz that ensures the user understands branch changes before pushing, merging into a protected branch, or continuing after a periodic checkpoint. Invoke this skill when the proctor hook blocks a git operation, or when the user wants to review their understanding of changes. Accepts an optional argument with operation context (e.g., "push from branch 'feature/foo'", "merge 'feature/bar' into protected branch 'develop'", or "periodic checkpoint on branch 'feature/foo'"). Also accepts "summary" or "stats" to show quiz history.
the-ai-alchemist/skill-loop/skills/skill-loop Skill
0★ repoSelf-growth loop for your agent's capabilities. Detects a repeated pattern (via a Pattern Tally — cross-session counting, not vibes), dedup-checks your skill registry AND the pruned graveyard, and if genuinely new WRITES + INSTALLS + SELF-TESTS a new skill on its own, then announces it in a Birth Ledger for your after-the-fact review. Growth by default, hygiene by check. Trigger with /skill-loop, /skill-loop tally <pattern>, /skill-loop review, /skill-loop prune <name>, or automatically: the moment you notice a repeated task-shape, the user repeating an instruction, or a cross-project-reusable procedure. Do NOT use for refining an existing skill (edit it directly) or for one-off procedures (they don't earn a slot).
sumitake/agent-collab/plugins/agent-collab/skills/agent-readiness Skill
no license0★ repoUnified dynamic-host agent collaboration policy and signed-runtime client
Kakabhushundi/Meeting-Intelligence-Stack Skill
0★Use this skill whenever the user wants to extract insight, knowledge, decisions, or patterns from meeting transcripts. Triggers include: 'analyze this meeting', 'extract learnings', 'what did we decide', 'build a decision log', 'do a pre-mortem on this', 'AAR', 'after-action review', 'who's talking too much in our meetings', 'what tribal knowledge came up', or any request to make meeting content more useful and searchable. This skill routes to one of six specialist sub-prompts based on what the user wants to extract.
Heng-xiu/portfolio-forge Skill
0★把個人資訊鍛造成美感極佳的個人網站/作品集。內容文檔當唯一真值 → taste-skill 生 section 參考圖 → 對抗式逐張評審迭代 → Codex Frontend App Builder 高保真複刻 → headless 逐段 QA → Cloudflare Pages 可逆部署。當使用者說「做個人網站」「做作品集」「personal website」「portfolio site」「把我的資訊做成網站」「幫我做個 landing」時觸發。
mahesh-tws/first-customer-finder-claude/first-customer-finder Skill
0★ repoTurns a startup URL, repo, or product idea into a qualified, evidence-backed shortlist of potential first customers using recent PUBLIC signals only -- demand, pain, workaround, switching, and timing signals found via web research. Defines the ideal customer profile, scores fit and timing, links every prospect to its public source, drafts respectful source-based outreach openers, and builds a polished standalone HTML report. Never sends outreach automatically and never enriches private contact data. Use this whenever the user asks to find first customers, potential customers, design partners, early adopters, prospects, or leads, or wants a customer-discovery / prospecting report for a startup, product, or pilot program -- even if they don't use the word "prospecting."
johnisanerd/claude-skill-baidu-search-api/apify-baidu-search-api Skill
no license0★ repoGet structured Baidu search results without an official API key or Chinese account using the Apify Baidu Search Scraper Actor (johnvc/Baidu-Search-Scraper). One query returns one dataset item per SERP page with nested organic_results (position, title, link, plus displayed_link, rich_snippet, and sitelinks when Baidu shows them), related_searches, people_also_search_for, and top_searches, filtered by device, Simplified or Traditional Chinese, and time period. Use when the user wants a baidu api, a baidu search api or baidu serp api, Baidu search results as JSON or CSV, to scrape Baidu, structured baidu data for research or AI agents, or to see what ranks on baidu.com for a query. Pay-per-page billing, MCP-ready for Claude and other AI agents.
MorrisMorrison/reef/skills/reef Skill
no license0★ repoUse when the user runs /reef or asks to walk through, gate, or review the code changes they made this session — an interactive hunk-by-hunk review where they approve, reject, or comment on each hunk.
SkillMedev/freelancer-consultant-os/skills/client-onboarding-system Skill
0★ repoRuns a first-14-days client onboarding procedure - kickoff agenda, asset and access collection checklist, a written communication contract, and the first-quick-win rule of shipping something visible in week one. Use when a freelancer or consultant says "new client just signed, now what", "how do I kick off this engagement", "set up my client onboarding", "the project stalled waiting on client assets", "client keeps Slacking me at 10pm", or "how do I start a retainer on the right foot". Do NOT use for onboarding a new employee into a role - use onboarding-plan-builder instead; for in-product user onboarding copy, use onboarding-copy.
The same file is in 2 other repositories
tanav-ai/claude-plugin/skills/tanav-security-check Skill
0★ repoUse whenever the user asks about the security of a GitHub repo, MCP server, Claude skill file, agent config, or wants to know if something is safe to install/connect. Governs how to sequence the Tanav tools and how to present results — plain security-analyst framing, not marketing copy.
AceyTracy/creator-vetting Skill
no license0★Vets a YouTube channel for Blotato sponsorship fit. Input is a channel URL or handle. Pulls current stats, computes the weighted ROI score against the partnerships rubric, flags risks, writes a scored row to the Creators table in Airtable via MCP, and drafts a first-touch outreach email in the house voice — then stops for human review. Use this skill whenever evaluating any new creator, community, newsletter, or influencer as a potential partner, whenever someone asks "should we sponsor X", "vet this channel", "score this creator", or pastes a YouTube link in a partnerships context, even if they don't say the word "vet".
kpab/mercilint Skill
0★Brutally roast the user's uncommitted changes — every insult maps to a severity-ranked, concrete fix. Use when the user says /roast, "roast my code", "roast this diff", or asks for a merciless / brutal code review.
ldenson1120/job-search-os/skills/cover-letter Skill
0★ repoThis skill should be used when the user says "write a cover letter", "cover letter for [company or role]", "I'm applying to [company]", "help me apply to [role]", "draft a cover letter", or shares a job description and wants help writing application materials.
rasagy/idea-skill-creator-skill Skill
no license0★A meta-skill that builds bespoke ideation-coach skills for any creative domain — writing, visual art, music, design, research, or anything where someone captures rough ideas and wants structured help developing them. Use whenever the user wants to create a brainstorming/ideation/concept-coaching skill for a specific creative practice, update an existing generated coach (changing its philosophy, adding references), or duplicate one with variations. Trigger on phrases like "build me a brainstorming coach for X," "I want an ideation skill for my poetry," "help me make a skill that coaches me on collage ideas," "add these references to my writing coach," or "make a variation of my leadership-articles coach." Do NOT trigger for building the creative work itself, or for creating non-ideation skills (that's skill-creator's job).
iamtural/overkill/skills/overkill Skill
0★ repoAudit real Claude Code (or any agent CLI) usage for effort/model waste — not just what you spent, but whether the spend matched the actual work. Use when the user asks "where is my spend going," "am I wasting tokens," "check my usage," "run an overkill report," "was that task overkill," or wants a cost/effort efficiency review of recent sessions. Reuses ccusage for raw usage data — does not duplicate it — and adds the layer ccusage structurally cannot: reading what a task actually was and judging whether the effort/model spent on it was justified. Produces a scannable report with concrete, personalized routing fixes, not generic advice.
seattle78/claude-skills/skills/auto-orchestrate Skill
no license0★ repoGoal-based development pipeline for Claude Code.
hyacinthhh/paper-digest-skill Skill
0★论文阅读室:读取工作目录里新加入的论文(PDF),外语论文自动翻译成中文, 提炼摘要、核心思想、方法、亮点,并生成中文全文,统一汇入一个带左侧菜单栏的 精美 HTML 页面(paper-digest/index.html),每处理一篇就增量加入。 触发场景:用户说"处理论文"、"读论文"、"总结论文"、"翻译论文"、"更新论文库"、 "有新论文"、"paper digest"、"summarize this paper",或往目录里丢了 PDF 论文 让你读/总结/翻译时。不适用于写论文、改论文、文献检索。
goingli0324/multi-perspective-panel Skill
0★Reviews any decision, plan, proposal, or open question from four independent thinking angles — critical, creative, communication, and interaction — either as a parallel panel or as an adversarial red-team/blue-team debate. Use this whenever the user asks to "從多角度想", "組隊思考", "壓力測試這個決定", brings a decision or plan and wants it reviewed for blind spots, is stuck seeing a problem from only one angle, or is doing scenario/strategy analysis (including dissertation-level CLA or futures-scenario work) that would benefit from multiple independent lenses rather than a single take. Trigger proactively even without the user naming the skill — any single-angle answer to a real decision or plan is a missed opportunity to surface blind spots the user can't see from where they're standing.
meggiepham06-smile/session-audit-skill/session-audit Skill
0★ repoEnd-of-session audit that scans the conversation for corrections, preferences, decisions, and new context that were never saved, then proposes where each belongs in the user's memory files (CLAUDE.md, MEMORY.md, or a memory/ folder). Use whenever the user says "audit this session", "session audit", "what did we miss", "end of session check", or asks to capture what was learned before closing a session. Adapts to whatever memory structure the workspace already has, and proposes a simple one if none exists.
Shawn1993/ship-appstore/skills/appstore Skill
no license0★ repo当用户提到 iOS/macOS App 的任何 App Store 事务时触发——上架、提审、审计/preflight、审核被拒、TestFlight、ASC 填写、元数据/截图/文案、关键词与 ASO、排名监控、评论管理、编辑精选、内购订阅配置、数据分析,以及开发者账号注册、ASC API Key 申请、中国区 App 备案办理。Make sure to use whenever the user mentions 上架、提审、App Store、ASC、TestFlight、ASO、拒审,即使只给了一个网站或 App 名。不适用:Android 各商店上架、App 功能开发本身。
fevra-dev/Subrosa/skills/consent-language Skill
0★ repoGenerates legally compliant privacy notices, consent flows, cookie banners, and data subject rights disclosures for products and services. Use when user says "write a privacy policy", "privacy notice", "cookie consent", "GDPR consent flow", "data subject rights page", "at collection notice", "CCPA disclosure", "PIPEDA privacy statement", "opt-in consent copy", "cookie banner text", "legitimate interests notice", "generate consent UI copy", or when launching a product or feature that collects personal data and needs compliant disclosure language. Produces layered notices (short/full), jurisdiction-specific variations, UI copy for consent flows, cookie categorization text, and rights exercise mechanisms. Grounded in GDPR Arts. 13/14, PIPEDA Clause 4.8, CCPA § 1798.100, Quebec Law 25, COPPA, ePrivacy Directive, and PIPL Art. 17.
CripterHack/ig-downloader-skill Skill
0★Download Instagram profile media (reels MP4, photos JPG, full carousel multi-image JPG) via sessionid (instagrapi), Apify dataset fallback, or interactive setup wizard. No password sharing required.
Shawnchee/design-scan/skills/design-scan Skill
no license0★ repoScans a live website and produces design.md — a replication-grade spec of its look and motion. Runs a bundled Playwright crawler that template-dedupes and visits up to ~6 pages, captures screenshots at 3 breakpoints plus full-page and scroll frames, and extracts structured design data: CSS custom properties, fonts, computed typography, a color palette with usage counts, CSS @keyframes, Web Animations API animations with real keyframes/durations/easings, transitions, :hover rules, animation-library detection (GSAP, Framer Motion, Lottie, AOS, Lenis), layout metrics, and a component inventory. Claude then reads the screenshots plus JSON and writes design.md. Trigger on "design scan", "/design-scan <url>", "replicate this website's design", "scan <url> and make a design.md", "clone this site's look", or "extract the design system from <url>".
SamsShow/formulary-claude Skill
0★Quality-first playbook for prompting Claude models and choosing the right model per task, built from Anthropic's official prompt engineering guidance. Use when writing or reviewing a system prompt or agent prompt for Claude, deciding between Fable, Opus, Sonnet, and Haiku, setting effort or thinking parameters, fixing a Claude app that is too verbose, ignores tools, overengineers, fabricates progress, stops early, or ships generic frontend design, migrating prompts from older Claude models, or tuning agent harnesses and code review pipelines. Not for prompting non-Claude models (OpenAI GPT, Gemini, Llama), account or billing questions, or coding tasks that involve no prompt writing.
MrBridgeHQ/kaggle-profile-optimizer/.claude/skills/kaggle-profile-optimizer Skill
0★ repoUse when the user wants to audit, reposition, or improve their Kaggle profile: auditing a profile from a URL, a summary, or structured data; rewriting the Kaggle bio; choosing which notebooks, datasets, and competitions to feature; building a recruiter-ready portfolio narrative; planning notebook, dataset, and competition strategy; creating a Kaggle content calendar; or preparing a Kaggle profile to share on LinkedIn, a CV, or GitHub. Produces a scored audit, positioning options, English-language Kaggle assets, and a 30/60/90-day plan, always ethically (never upvote, medal, or ranking manipulation). Triggers on "optimize my Kaggle profile", "audit my Kaggle", "rewrite my Kaggle bio", "which notebooks should I feature", "Kaggle portfolio", "Kaggle progression strategy", and French equivalents ("analyse mon profil Kaggle", "reecris ma bio Kaggle", "plan 90 jours Kaggle", "strategie Kaggle").
zghanw/hackathon-skills/skills/hackathon-flow Skill
0★ repoRouter for the hackathon pipeline. Looks at what already exists (HACKATHON.md, source code, a deck, a script) and says which skill or command to invoke next. Use when a team isn't sure what phase they're in or what to do next.
LindseyyZhang/lit-interactive-fiction/lit-interactive-fiction Skill
0★ repoTurns any book, play, or story — copyrighted ones included, via a built-in originalization path — into a playable single-file HTML interactive fiction game. Use for interactive fiction, text adventures, 互动小说, 文字互动游戏, or extending an existing literary IF game.
demandintel/demandintel-skills-resource/skills/sales-training-content-skill Skill
no license0★ repoDemandIntel Sales & Customer Success Training Content Skill. Use when the user asks to create, build, or develop a sales, customer success, or support training session, workshop, programme, assessment, or coaching resource on any topic (objection handling, discovery, qualification, cold calling, negotiation, closing, customer success, onboarding, renewals, expansion, support, complaints handling, etc.) or for any role (BDR, SDR, appointment setter, AE, BDM, sales engineer, sales manager, CSM, onboarding specialist, renewals manager, account manager, support agent, technical support specialist, complaints handler). MANDATORY TRIGGERS: DemandIntel training, DemandIntel sales training skill, DemandIntel training skill, training programme, training session, sales training, CS training, support training, workshop, trainer notes, coaching resource, assessment, competency framework, scorecard, role-play, sales enablement, onboarding curriculum, train the team on, build training for, create a session on, develop training, certify the team. This skill: (1) Draws down live contextual intelligence from the client's own DemandIntel account and campaigns via the DemandIntel MCP server (competency scores, QA heatmaps, top objections, coaching plans, call transcripts, league tables), (2) Grounds content in a library of tried, tested, and trusted sales, CS, and support methodologies that mirror the platform's own default frameworks, (3) Builds psychology-based training content (not just scripts or battle cards), (4) Creates trainer notes with timings and delivery instructions, (5) Produces participant handouts, worked examples, exercises, and assessment resources for every role the platform serves.
Skillproofdev/find-tested-skills Skill
0★Finds, installs, and puts to work Claude Code skills that have actually been tested and scored, matched to the user's goal and project. Use whenever the user asks which skills to install, what skills would help their project or task, how to find good skills, whether a skill is any good, or wants help with a goal that a skill could do better (optimize code, add memory, design, SEO, copywriting, translation, testing, docs, data) — e.g. "what skills should I use", "find me skills for this repo", "help me improve my SEO", "is there a tested skill for X". Queries the SkillProof catalog of independently installed-and-run skills (each with a pass/setup/fails verdict and a /10 score), confirms the picks with the user, installs the chosen ones, and then uses them to do the work.
jamartinezpastor/powerbi-motion/powerbi-motion Skill
no license0★ repoGenerate a single landscape MP4 video highlighting the most relevant insights from a Microsoft Power BI report. Use whenever the user wants Power BI data, semantic-model measures, or report KPIs turned into motion graphics, animated summaries, or shareable clips for Slack, email, social, or briefings — even without the word animation. Triggers include animate this report, make a video from these KPIs, motion summary, Power BI to video, or any Power BI model + visual-storytelling request.
vistabylara-dev/vista-claude-skills/skills/ai-visibility-audit Skill
0★ repoFree Claude Skills for AI developers, Shopify experts, marketers, and businesses. Built by Vista by Lara.
Fizzokid1/truthful-research/skill Skill
0★ repoA verification-first research protocol and report auditor. Use this skill whenever the user asks to research a factual question, verify or fact-check a claim, check whether something is true, evaluate the reliability of an article or source, or audit/grade an AI-generated research report or answer (e.g. from ChatGPT, Perplexity, or a deep-research tool). Also use it when the user asserts a factual claim and asks for confirmation, or when a research task could be affected by unreliable, AI-generated, or content-farm sources — even if they don't say "fact-check" explicitly.
Shiinama/content-os/skills/content-os Skill
0★ repoThe user's personal content system in one skill, five capabilities sharing one data home and one persona. Use when the user wants to capture an idea or judgment ("capture this idea", "记录这个想法"), save a content structure or visual style as a template ("save this as a template", "把这个存成模版"), produce or adapt platform content ("写篇文章", "turn my idea into a thread", "给这篇配图"), record publishes and performance numbers, or see the whole board (inventory, topic selection "想写篇文章" with no topic, next actions, health check). Not for to-dos or reminders. If the user wants to create or revise their persona profile, use the profile skill instead.
goingli0324/project-guardrails Skill
0★為專案建立「連動禁區」防護段落。自動分析專案程式碼,找出高扇入模組、資料結構契約、部署設定、對外契約與演算法核心等「改 A 會壞 B」的高風險區域,經使用者確認後寫入該專案的 CLAUDE.md,作為日後所有修改行為的防護依據。MANDATORY TRIGGERS:使用者說「建立連動禁區」「設定 guardrails」「init guardrails」「幫這個專案建立防護」「分析哪些程式碼不能亂動」「哪些模組牽一髮動全身」「建立修改防護段落」「把禁區寫進 CLAUDE.md」,或在新專案開始前要求建立修改安全機制時,都要套用此 skill。適用於 Firebase/PWA、GAS、後端服務等各類專案。SCOPE:本 skill 只做分析與(經確認後的)CLAUDE.md 寫入,不修改任何程式碼。本 skill 同時是 agentic-dev-loop 開發迴圈的「前置」階段:當該編排器在 Step 0 發現專案尚未建立連動禁區時會呼叫本 skill;使用者單獨要求分析禁區時仍直接觸發本 skill。
shuangying0001-beep/miniprogram-canvas-verify Skill
0★为微信小程序 Canvas 项目提供本地预览+截图视觉验证工作流:启动静态预览服务(:9099,支持任意根目录/端口)、用 Selenium 对预览页执行 JS 并截图、按场景 YAML 做区域裁剪与回归对比。含 8 项 preview.html 验证清单(白屏/线条/居中/即时重绘/导出/色值/控制台/一致性)。触发词:预览 canvas/截图验证/视觉回归/验证渲染效果/小程序 canvas 验证/起预览服务。纯前端+Python 工具链,零业务依赖。
2000silpeed/meta-prompt-skill Skill
0★타깃 AI 모델(GPT/Codex, Claude, Gemini, Seedance, Higgsfield 등)별 프롬프트 가이드북에 맞춰 사용자의 요청을 최적화된 프롬프트로 변환·생성한다. 트리거 — "○○용 프롬프트 만들어줘", "프롬프트 최적화해줘", "이 요청을 ○○ 프롬프트로 바꿔줘", "프롬프트 잘 써줘", "meta-prompt". 서브커맨드 — "/meta-prompt refresh <model>"(가이드북 갱신), "/meta-prompt add <model>"(새 모델 추가), "/meta-prompt eval <요청>"(원본 vs 변환본 A/B 비교). 단순 문장 윤문이나 한글 자연화는 humanize-korean 소관.
btmoriarty/pherkad/skills/pherkad Skill
0★ repoValidate or draft prose in the user's own voice rather than generic or flattened writing. Validation mode triggers on a voice check, voice audit, tone check, "does this sound like me," or a draft submitted to check whether it sounds like them. Authoring mode triggers when the user asks to write, draft, or rewrite prose in their voice, or wants text they will send as themselves (emails, posts, papers) to come out in their voice. Also triggers to build or update the voice profile from samples. First run builds the profile; later runs draft from it and validate against it.
Enterprise sales context interview
Giving-Back-Studio/growth-agent/skills/enterprise-sales-context-interview Skill
no license0★ repoInterview an enterprise owner and save accurate sales context in Earth Care Network. Use when brand voice, offer, ICP, buying triggers, proof, objections, response policy, or CTA context is missing, stale, or producing generic outreach.
dorelysm/naturalizacion-texto-es/.claude/skills/naturalizacion-texto-ia Skill
0★ repoNaturaliza texto en español generado por IA aplicando 11 técnicas lingüísticas para mejorar la calidad editorial y naturalidad comunicativa. Produce el texto reescrito y un informe con diagnóstico cuantitativo.
Einherjar99/bggg-skill-taotie Skill
0★Skill 进化器(饕餮)— 通过"吞噬"并分析其他 skill 的优势来强化目标 skill。 当用户想要:整合两个 skill、用一个 skill 优化另一个、对比分析两个 skill 的优劣、 把某个 skill 的优点提炼到另一个 skill 中、或者说"把 X 喂给 Y"、"用 X 来优化 Y"、 "整合这两个 skill"、"吃掉这个 skill"、"skill 进化"、"skill 升级"、"合并 skill" 等意图时,必须触发此 skill。即使用户没有明确说"饕餮",只要涉及到两个 skill 之间的 能力迁移、对比分析、或优势提取,都应该使用此 skill。
roman-rr/roman-cyber-garage Skill
no license0★Dark cyberpunk design system with complete theme reference — colors, typography, components, modals, tables, cards, badges, buttons, and layout patterns. Use this skill when building dark-themed dashboards, admin panels, trading UIs, or any cyberpunk-aesthetic web interface. Production-tested on real SaaS products.
gigayaya/DAA-Master/plugins/DAA-Master/skills/daa-architect Skill
0★ repoUse when designing a new automation testing framework, scaffolding project structure, or planning test architecture following DAA principles
baagad-ai/code-surgeon Skill
0★Analyze, plan, review, and optimize any codebase across 4 modes: Discovery (understand architecture and risks), Review (validate changes and detect breaking changes), Optimization (find bottlenecks and vulnerabilities), Implementation Planning (generate step-by-step guidance). Works with React, Django, Rails, Go, Rust, and 30+ frameworks. Use when analyzing codebase structure, assessing feature safety, finding security issues, planning implementations, or discovering performance problems.
24111999/claude-skills/slide-studio Skill
no license0★ repoCreate and modify PowerPoint presentations (PPTX) through direct XML manipulation. Use this skill when: (1) Creating presentations from scratch, (2) Adding/editing/deleting slides, (3) Inserting images or custom shapes, (4) Applying POTX templates for consistent branding, (5) Editing existing PPTX files, (6) Working with slide layouts and placeholders, (7) User asks to make a "presentation", "slides", "deck", or mentions ".pptx". Supports all 11 standard Office slide layouts.
goldiacogitative647/claude-plugin-weixin/skills/access Skill
no license0★ repoManage WeChat channel access — approve pairings, edit allowlists, set DM policy. Use when the user asks to pair, approve someone, check who's allowed, or change policy for the WeChat channel.