agentsclimarketplace

The catalog

608,253 rows, by stacks then stars

  • Feature architecture

    LaoitdevOpen/laoitdev-skills/skills/frontend/feature-architecture Skill

    0★ repo

    Feature folder structure and architecture for React + TypeScript admin apps. Use this when creating a new feature, adding a major section, or when asked how to organize a feature's files. Covers the canonical folder layout (components, hooks, services, types, schemas, constants, utils), what goes where, and index export conventions.

  • Salesforce architect navigator

    ayanme/salesforce-navigator-suite/skills/salesforce-architect-navigator Skill

    0★ repo

    This Navigator researches Salesforce architecture patterns, integration design, and enterprise guidance from official architect documentation. Use when the user asks how to design or evaluate Salesforce architecture: integration patterns, reference architectures, scalability, security design, governance, identity strategy, enterprise trade-offs, Agentforce architecture, Data Cloud architecture, Marketing Cloud architecture including data extensions, send architecture, subscriber data models, and Marketing Cloud Personalization, CRM Analytics architecture, MuleSoft, and API-led connectivity.

  • Interview guide builder

    SkillMedev/ux-research-discovery/skills/interview-guide-builder Skill

    0★ repo

    Writes a non-leading user-research discussion guide with warm-up flow, open core questions, an attached probe bank, time budgets, and a pre-field bias audit. Use when someone asks "write my interview guide", "what should I ask users in discovery interviews", "review my questions for leading language", or is preparing generative or evaluative user interviews. Do NOT use for hiring-loop questions with competencies and scoring anchors - use interview-question-kit instead. Do NOT use for sourcing deep domain knowledge from subject-matter experts with laddering - use expert-interview instead. To analyze the notes afterward, use interview-synthesis.

    The same file is in 1 other repository

  • Ab test analyzer

    SkillMedev/data-analyst-toolkit/skills/ab-test-analyzer Skill

    0★ repo

    Analyzes an A/B experiment to a defensible verdict - sample-size and minimum-detectable-effect math, two-proportion significance testing with confidence intervals, and checks for the traps that fake a win (peeking, sample ratio mismatch, multiple comparisons). Use when someone asks "is this test significant", "did variant B win", "how long should I run this experiment", "what sample size do I need", or shows experiment results and asks whether to ship. Do NOT use for logging and organizing ML training runs - use experiment-tracking instead; for causal questions without a randomized experiment use causal-inference; for general funnel or metric investigation use funnel-analysis or product-analytics.

    The same file is in 2 other repositories

  • Alert tuning

    SkillMedev/incident-response-command/skills/alert-tuning Skill

    0★ repo

    Reduces alert noise by making alerts actionable, symptom-based, and tied to SLOs. Identifies and kills flappy, duplicate, and cause-based alerts. Use when alert fatigue is degrading on-call response quality.

    The same file is in 1 other repository

  • Ats resume

    ericbrck/ats-resume Skill

    0★

    Claude skill that rewrites your resume to clear automated hiring agent screening. Built on actual hiring agent source code.

  • Cloudcost doctor

    takeaseatventure/cloudcost-doctor Skill

    0★

    Audit infrastructure-as-code (Terraform, CloudFormation, CDK) for cloud cost anti-patterns BEFORE deployment. Finds overprovisioned instances, expensive storage defaults, idle resources, missing lifecycle policies, and 45+ more — no AWS credentials required. Use when reviewing or cost-optimizing IaC.

  • Secure development

    siam-hossain9/secure-development-skill/plugins/secure-development/skills/secure-development Skill

    0★ repo

    Security best practices for building and reviewing software, web apps, APIs, and infrastructure. Use whenever writing, designing, modifying, or auditing code — especially anything that handles user input, authentication, authorization, sessions, secrets, cryptography, databases, file uploads, network/HTTP requests, APIs, LLM/AI features, realtime/WebSockets, payments, PII, deployment/cloud/containers, or when reusing/pasting code (including AI-generated or copied Stack Overflow snippets) — to prevent vulnerabilities (injection, XSS, SSRF, CSRF, IDOR/broken access control, auth flaws, secret leakage, prompt injection, misconfiguration) by design rather than patching them later. Also use for security reviews, threat modeling, and pre-ship hardening.

  • Scrum

    fsgreco/ai-agent-plugins/scrum/skills/scrum Skill

    0★ repo

    Log daily standup entries to ~/Desktop/scrum/. Supports inference mode (suggests an entry based on conversation context), direct logging, and listing today's entries.

  • Daily briefing

    mohitkhandelwal242/ai-pm-operator/.claude/skills/daily-briefing Skill

    no license0★ repo

    The morning-habit orchestrator — one command produces a single, concise, proactive digest of everything a PM needs to know today: board health, what's newly on your plate, metric movement, and competitor deltas. Degrades gracefully — only runs the sections whose data and credentials exist. Use when asked for '/briefing', 'morning briefing', 'monday briefing', 'daily briefing', '/standup', 'what needs me today', 'catch me up', or as the first thing each morning.

  • Claude latex skill

    indigoHatter/claude-latex-skill Skill

    no license0★

    Governs how Claude writes, edits, reviews, and gives advice about LaTeX. Use this skill for ANY task involving .tex files — no exceptions. This includes: producing new .tex files of any type (worksheets, formula sheets, handouts, reports, problem sets, exams, multi-file projects); editing or auditing existing LaTeX source; reviewing someone's LaTeX for correctness or style; and giving LaTeX advice or recommendations without producing a file (e.g. "should I use align or equation here?", "what's the right way to typeset units?", "how do I structure a multi-chapter project?"). Trigger whenever the user mentions LaTeX, .tex files, pdflatex, XeLaTeX, LuaLaTeX, Overleaf, TeX Live, MiKTeX, compiling a document, or asks Claude to write math, tables, or structured technical documents in LaTeX. Does NOT encode opinions about information density, whitespace, or document class — those belong in project-level philosophy files.

  • Brevity

    mehdiforoozandeh/skills/skills/brevity Skill

    0★ repo

    Concise-and-clear response mode that maximizes the reader's understanding per word: maximize understanding, then minimize words — in that order. Keep full grammatical sentences (not clipped fragments), technical precision, and every fact; cut only filler, hedging, preamble, and recap. Use when there's a question to answer and the user wants it dense, clear, and scannable. Triggers: /brevity, "be concise", "keep it short", "no fluff", "tl;dr", "get to the point", "stop padding".

  • Skill auditor

    SkillMedev/skill-builder-studio/skills/skill-auditor Skill

    0★ repo

    Use when reviewing, grading, auditing, or improving a whole existing skill or pack - judging whether a skill is good, fixing one that misfires or won't activate, or driving one or many skills to a quality bar. Audits to an absolute A+ bar and hands back ship-ready SKILL.md rewrites, not a report the user must act on. Do NOT use when tightening only a description or trigger in isolation - use skill-description-writer instead; do NOT use when authoring a brand-new skill from scratch - use skill-creator instead.

    The same file is in 1 other repository

  • Burndown

    bordumb/recurve/.claude/skills/burndown Skill

    no license0★ repo

    Launch the unattended claims burndown for recurve — sequential fresh agents close RED gaps under the fleet gate until done, capped, or parked out

  • Geo content brief

    1marcelserrano/geo-content-brief/skills/geo-content-brief Skill

    no license0★ repo

    Engine de briefing para conteúdo de era-IA — produz briefs que ranqueiam no Google E são citados por AI Overviews, ChatGPT, Perplexity, Gemini e Copilot (GEO/AEO/LLMO). Bimodal: modo ESTRATÉGIA (diagnóstico de intenção + PAA→H2 + edge + brief entregável) e modo PRODUÇÃO (answer block, seções autocontidas, schema/llms.txt, gate de pré-publicação). Use quando o usuário pedir: brief de conteúdo, otimizar para AI Overviews, GEO, AEO, ser citado por IA, ranquear no ChatGPT/Perplexity, content brief, SEO de IA, answer engine optimization, llms.txt, schema para IA, aparecer em busca generativa, otimizar artigo para busca, AI search, generative engine optimization, citação de IA, geo brief, content brief para IA. Genérica e vendor-neutral — aplicável a qualquer pessoa, marca ou negócio.

    The same file is in 1 other repository

  • Nem parece ia

    1marcelserrano/nem-parece-ia/skills/nem-parece-ia Skill

    no license0★ repo

    Revisão editorial em português do Brasil para remover marcas de escrita artificial, vícios de IA, lero-lero corporativo, falsa profundidade, muletas retóricas e cadência robótica. Use ao escrever, reescrever, revisar ou diagnosticar textos pt-BR para torná-los mais naturais, específicos, diretos e adequados ao registro.

    The same file is in 1 other repository

  • Pdf metadata filler

    eUmeda/pdf-metadata-filler Skill

    0★

    論文PDFの Title/Author/DOI を自動補完する。「PDFのメタデータを埋めたい」「論文PDFにメタデータがない」「PDFのメタデータ補完」「PDF走査して補完」「/pdf-meta」「/pdf-metadata」で使用。ファイル名DOI→本文DOI→OpenAlex→CrossRef→CiNii(和文紀要)→OCR→LLM(Gemini/Groq)の多段で書誌を取得し pypdf/exiftool で書込。

  • LLM prompting bestpractice

    eUmeda/LLM-prompting-bestpractice Skill

    0★

    外部 LLM サービス (Anthropic Claude, OpenAI GPT, Edison Scientific Kosmos, Elicit, Perplexity 等) に投入するプロンプトを 3 ベンダー統合 best practice で設計・最適化する。XML タグ構造化・5 コンポーネント (role/task/context/format/constraints)・outcome-first 指示・Kosmos 用 single-objective 設計・Anti-pattern 検査を整合的に適用する。Triggers on: プロンプト最適化, prompt optimization, prompt engineering, Kosmos プロンプト, Edison プロンプト, GPT プロンプト, Claude プロンプト, XML タグ, prompt 設計, prompt review, 外部 LLM 投入, /LLM-prompting-bestpractice

  • Milky way idle

    Octau/milky-way-idle-skill/skills/milky-way-idle Skill

    0★ repo

    Answer questions about the idle/incremental game Milky Way Idle (milkywayidle.com, also on Steam). Use this skill WHENEVER the user asks about Milky Way Idle game mechanics, skills, items, monsters, combat, or strategy — including milking, foraging, woodcutting, cheesesmithing, crafting, tailoring, cooking, brewing, alchemy, enhancing, combat, the combat stats (stamina, intelligence, attack, melee, defense, magic, ranged), monsters and drop tables, zones, bosses, combat tiers, abilities, equipment stats, buffs, teas, coffees, houses/house rooms, the dairy barn/forge/observatory etc., loadouts, experience formulas, enhancement success rates, or what to train next. Trigger this even when the user just names a game term (e.g. "what drops Holy cheese", "how does enhancing protection work", "best tea for combat") without saying "Milky Way Idle" explicitly, as long as context points to this game. Do NOT use for unrelated games or real-world dairy/astronomy questions.

  • Researcher agent

    maverickgao8848/researcher-agent Skill

    0★

    2 Agent 并行深度调研系统。当用户需要深度调研某个话题、生成专业扎实的调研分析文章时激活。 触发词:深度调研、研究报告、research、调研报告、专题研究。 架构:Claude(协调+写作)→ 2 个 Research Agent(并行搜索)→ 综合写作 → 可选 Mermaid 配图。 输出:实用主义视角的调研分析文章,只说有用的关键内容,输出到 output/{topic}/research/article.md。

  • Vibeguard

    edilkoke/vibeguard Skill

    0★

    Use when building, reviewing, or hardening a web application with AI assistance — especially "vibe-coded" apps on Next.js + Supabase. VibeGuard enforces secure-by-default code generation and reviews output against a catalogue of the 21 most common AI-coding vulnerabilities (exposed secrets, broken access control, injection, weak auth, missing privacy controls, vulnerable dependencies). Trigger on: "build an app", "add auth", "is this secure", "review my code", "harden", "deploy", or any handling of payments, identity, logins, or customer data.

  • Contract review

    sanjibani/paid-skills/examples/contract-review Skill

    0★ repo

    Reviews a contract clause for risk and proposes redlines. Use when the user pastes a contract, NDA, MSA, or SOW and asks for review, redlines, or "what should I worry about". Triggers on phrases like "review this contract", "redline this", "what's risky here", "give me redlines".

  • Womenai cohort cards

    ruthless-coder-ai/womenai-cohort-cards Skill

    0★

    Turn WoMen AI Lab founding-cohort survey responses (exported from the cohort "build in public" survey as CSV/JSON, or pasted in) into ready-to-post 小红书 / Xiaohongshu / Instagram carousel cards that follow the WoMen AI Lab visual system, then render them to 2160×2880 PNGs. Use this whenever the user wants to make social-media cards, 小红书图, carousel slides, or "build in public" posts from a member's survey answers — including phrasings like "把某位成员的回答做成卡片", "generate cohort cards", "做几页适合发小红书的内容", or when they hand over a survey export and want it turned into shareable graphics. Also use to tweak copy, change the 栏目名/日期, add/remove pages, or re-render an existing card set.

  • Anthropic dev loop

    nishimoto265/anthropic-dev-loop/skills/anthropic-dev-loop Skill

    0★ repo

    Use when the user wants to run, document, or reuse an Anthropic-inspired Claude Code development loop, including planning interviews, Fixture/Invariant/Probe verification, main/sub-agent implementation, PR review evidence, and post-merge harness updates. Trigger on phrases like Anthropic DevLoop, Claude Code development loop, harness-driven development, evals, verification loop, or multi-agent implementation flow.

  • Npm package release hardening

    SSBrouhard/npm-package-release-hardening Skill

    0★

    Use when releasing or publishing a JavaScript/TypeScript npm package or CLI publicly — making a package public-ready, reviewing package.json or tarball contents, setting up GitHub CI, Dependabot, security settings, or branch protection, triaging dependency-update PRs, or when an agent-built package may overstate the Node runtime it supports.

  • Genesis core 000

    CaptainAIIA/Omniplex_Genesis_Laws/genesis-core-000 Skill

    0★ repo

    Omniplex Genesis Core 000: THE BINDING SEAL. Master lock for all 12 Genesis Laws. Triggers on public deployment, verification requests, "verify genesis", "check integrity", "genesis seal". Contains SHA-512 cryptographic hashes of every Genesis Law — individually and as a combined binding seal. Canonical hash registry is also published at tha.istanbul. Any modification to any Genesis Law breaks the seal. MOTTO: "The laws are sealed. The seal is public. Truth cannot be forged."

  • Vibe model router

    Sambhram-Gaonkar/vibe-model-router Skill

    no license0★

    Stop burning tokens on the wrong model. Open-source skill for vibe coders to pick the right AI model for every subtask.

  • Gtd capture

    blu3mo/gtd-cosense/skills/gtd-capture Skill

    0★ repo

    Zero-friction GTD capture into the Cosense inbox. Use the moment the user starts brain-dumping — rattling off things on their mind, worries, ideas, "これやらなきゃ", "メモっといて", "頭の中出したい", rapid-fire thoughts. Appends everything as raw lines and asks NOTHING (clarifying is a separate mode — gtd-clarify). Part of the gtd skill bundle.

  • Humanizer

    Hiirocchi18/humanizer Skill

    no license0★

    Remove signs of AI-generated writing from text, and write in a human voice when producing new text. Use when the user says "humanize", "make this sound human", "rewrite this so it doesn't sound like AI", "fix the AI writing", "clean up AI text", or anything similar. Also applies when editing or reviewing text to make it sound more natural and human-written. This is an always-on style skill: once activated in a conversation, apply it to everything written going forward — not just rewrites. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, passive voice, negative parallelisms, filler phrases, and reflexive summary openers.

  • System wright

    EthanQC/SystemWright/system-wright Skill

    0★ repo

    Turns a vague goal, messy repeated workflow, AI adoption problem, or product/operations idea into a reusable AI work system built from Prompt, Context, Harness, and Loop, with a plain-language brief, human-approval gates, and a small trial run. Use when the user wants to productize a recurring way of working with an agent (Codex, Claude Code, Gemini CLI, Cursor, or compatible) rather than get a single answer. Do not use for one-off rewrites, pure definitions, temporary checklists, or ordinary code review unless productizing a reusable workflow.

  • Necl content poster

    adjacentai/necl-skills/necl-content-poster Skill

    0★ repo

    Turn one draft into three platform-tuned posts: Telegram (RU), LinkedIn (EN), Threads (EN). 8 hook formulas, anti-AI-marker rules, per-platform structures. Use when the user wants posts across channels — 'write a post', 'cross-post', 'превратить в пост'.

  • Branch

    valasubramanian-kr/wallet-web-developer/skills/branch Skill

    no license0★ repo

    Claude plugin orchestrating spec-to-code automation workflow, enabling developers to leverage Claude Skills for productivity.

  • Manuscript canon ledger

    dinaf2026-web/manuscript-editorial-suite/manuscript-canon-ledger Skill

    0★ repo

    Living, versioned canon ledger for any book or series — the persistent source of truth the continuity pass reads before it audits. Holds canon as STATE (per character/place/timeline fact, marked STABLE, DISPUTED, or EVOLVING) plus a DELTAS changelog of intentional changes tagged to book + chapter + reason, and OPEN QUESTIONS for unresolved canon disputes. Stored per project under .manuscript/canon-ledger.json. Use when the author says "canon ledger", "update the ledger", "record a canon change", "is this canon", "what's the canon for X", "add a delta", "resolve open question", or "seed the ledger from book N". It maintains the ledger and renders a human .xlsx view; it does NOT audit a manuscript (continuity-audit does that, consuming this ledger), rewrite prose, or judge mystery logic.

    The same file is in 1 other repository

  • Claude api

    Drvivek34/Skill-Bazaar/ai-ml/claude-api Skill

    no license0★ repo

    Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).

    The same file is in 1 other repository

  • Deep inquiry

    Aethon-Chrysean/llm-prompt-lab/Skills/deep-inquiry Skill

    0★ repo

    Rigorous problem-solving via bilingual research (Chinese + English), proactive query expansion, and interdisciplinary reasoning. Challenges before confirming, connects distant domains, never fabricates. Triggers on: any request for a solution, explanation, analysis, recommendation, comparison, debugging, architectural decision, or concept clarification. Also triggers on: "how does X work", "why does X happen", "best approach for", "help me understand", "explain X", "compare X and Y", "I'm stuck on", "what am I missing", any problem-solving prompt, or any question where accuracy matters. Triggers on casual phrasing like "what's the deal with X". Does NOT trigger for pure creative writing, simple greetings, or tasks handled by more specific skills (st-formula-explainer, st-framework-to-pytorch, spatial-transcriptomics-validator).

  • Kompas methodology

    Smartin-Martin/smartin-marketplace/smartin-compass/skills/kompas-methodology Skill

    0★ repo

    The Smartin Compass method for checking whether a business idea has real foundations. Use this skill when the user runs /kompas or /kompas-review, asks how to check or work through an idea, a segment, a pricing model, or a new direction, or when the napadovnik skill needs the tile definitions and check protocols to sort fragments or run a step. Holds the six tiles, the A/B/C check depths, the OVĚŘENO and NEOVĚŘENO logic, and the rules for generating workshop documents.

  • Bg text

    AcTePuKc/bg-text/skills/bg-text Skill

    0★ repo

    Bulgarian text quality skill for AI assistants and editor workflows.

  • Bullmq queue

    DIYA73/nestjs-skills/bullmq-queue Skill

    no license0★ repo

    BullMQ job queues, processors, retry logic, and scheduled jobs in NestJS.

  • Skill

    srivtx/solana-superchargers/solana-indexer-skill/skill Skill

    0★ repo

    Build custom Solana indexers end-to-end. Geyser gRPC plugins, backfill strategies, Postgres schema design, real-time streaming, cost optimization, testing with LiteSVM/Surfpool, and production operations. Use when designing a new indexer, choosing between Geyser/WebSocket/webhooks/polling, designing a schema, planning a backfill, reducing RPC costs, or operating an indexer in production.

    The same file is in 1 other repository

  • Eighty twenty

    bispeklolik/optika/skills/eighty-twenty Skill

    0★ repo

    Принцип Парето 80/20 для планирования и разработки. Раскладывает любую работу так, чтобы найти те 20% усилий, которые дают 80% результата, и выдаёт визуальный план приоритетов: с чего начать сейчас, что даёт максимум здесь и сейчас, что отложить. Ведёт продукт к MVP кратчайшим путём. Применять, когда пользователь планирует продукт или фичу, добавляет новую функциональность, спрашивает «с чего начать», «что в первую очередь», «приоритеты», «доведи до MVP», «что отложить», или говорит «80 на 20», «80/20», «Парето», «pareto».

  • Examforge

    SamDozer/Exam-Forge/skill/examforge Skill

    0★ repo

    Turn a student's own course material into a two-in-one deliverable: a study guide AND a prediction of what the exam will actually ask, optimized for marks. Use this skill whenever the user wants to prepare or revise for an exam, midterm, final, practical, OSPE, or quiz using their lecture slides, professor audio/voice-note transcripts (English OR Arabic), past exam papers, model answers, lab/practical manuals, textbook chapters, or class notes — even if they just say "help me study for X", "predict my exam", "make me a revision guide", or upload lecture files. Built for biology-family courses (biotechnology, biology, biochemistry, bioinformatics, chemistry, microbiology, molecular biology, and related lab sciences) but adapts to the material given. Do NOT use for writing the exam itself, cheating during a live exam, or general tutoring unrelated to a specific upcoming assessment.

  • Book distill

    ohugonnot/claude-skills/plugins/book-distill/skills/book-distill Skill

    0★ repo

    Reads a book (PDF or EPUB) and produces a faithful, pedagogical markdown reading note: maps the book, reads with intent, verifies every citation word-for-word against the text, distills by themes into linked ideas, with a reasoned rating and counterpoints. Use whenever the user provides a book file or asks to summarize or distill a book — "book summary", "distill this book", "reading note", « résume ce livre », « fiche de lecture », « extrais la substance » — even if they never say the word "note".

  • Windows c disk cleaner

    swei99386-alt/windows-c-disk-cleaner Skill

    0★

    Windows C/E disk cleanup and disk-space governance for requests such as C盘满了, C盘清理, Windows disk cleanup, C/E drive cleanup, large files, duplicate files, Downloads, installers, repair backups, or a deletion manifest. Audit, explain, and clean using a recovery-cost-first rule: recommend delete, keep, or move, then execute only after confirmation of exact paths.

  • Optimusprime compact

    aarshsharma2803-stack/optimusprime/.claude/skills/optimusprime-compact Skill

    0★ repo

    Compact the current conversation — preserve decisions, requirements, errors, architecture, and active task state; strip repeated or low-value content; reduce token usage; prepare clean context for Claude. Trigger: /optimusprime-compact, user says "compact", "compress conversation", "clean up context", "too many tokens", or /compact-conversation.

  • Cognitive html doc

    beihai23/cognitive-html-doc Skill

    0★

    将密集、线性的 Markdown 技术/产品文档重构为认知降维的工业级单文件 HTML 文档。核心目标是让读者 3 秒抓核心、30 秒理解全貌、3 分钟查到细节。使用此 skill 当用户:把 markdown 转成 HTML、要求做"漂亮的 HTML 文档"、要求"工业级 HTML"、要"技术文档可视化"、给一份 markdown 蓝图要 HTML 化、需要带 TOC/Mermaid 图表/卡片设计的长文档、提到"降低认知负荷"或"扫视即可获取"。即使没明说"HTML 文档",只要涉及把密集文字降维成结构化、可扫读的形态,就用此 skill。不要用于简单 markdown 渲染(一行命令即可)或纯打印样式 PDF。

  • Pagespeed plan

    tasdeleno/pagespeed-plan Skill

    0★

    pagespeed.web.dev / Google PageSpeed Insights (Lighthouse) ile bir web sitesini otomatik test eder ve PSI'nin gosterdigi TUM bulgulara (firsatlar, tanilar, insights, teknolojiye ozel oneriler) gore onceliklendirilmis, uygulanabilir bir iyilestirme plani (Markdown) uretir. Su durumlarda kullan: "sayfa hizi testi", "PageSpeed testi", "site hiz denetimi", "performans/SEO/erisilebilirlik denetimi", "Core Web Vitals", "Lighthouse skoru", "hiz optimizasyonu plani", "pagespeed skorlarina gore plan hazirla". Hem Cowork'te hem Claude Code CLI'da calisir. Ciktiyi bir .md dosyasina yazar ve sohbette ozetini gosterir. SEO/teknik/erisilebilirlik derinligi YERLESIKTIR (references/); claude-seo gerekmez, kuruluysa opsiyonel ekstra derinlik icin devredilir.

  • Ui ux deploy reviewer

    goingli0324/ui-ux-deploy-reviewer Skill

    0★

    部署前的 UI/UX 總體檢。以全球公認的 20 項 UI/UX 原則(Nielsen 十大易用性啟發法 + 互動心理學定律 + 可及性與適應性)逐項審視網站或 Web App 的前端程式碼與使用者體驗,輸出「依嚴重度排序的問題清單 + 修正建議 + 部署放行檢核表」。MANDATORY TRIGGERS:使用者說「部署前 UI/UX 檢查」「deploy 前跑一次 UI/UX」「上線前幫我檢查 UI/UX」「審查 UI/UX」「用 20 原則檢視」「這個網站好不好用」「易用性審查」「heuristic evaluation」「檢查使用者體驗」,或在準備 firebase deploy / 上線 / 發布前要求做最後檢查時,都要套用此 skill。即使使用者沒明說「UI/UX」,只要意圖是部署前對介面與體驗做整體審視,就觸發。SCOPE:本 skill 審查 UI/UX 與呈現層程式碼品質;資訊安全審查請改用 web-security-reviewer。本 skill 同時是 agentic-dev-loop「Verify 雙閘」的 UI/UX 閘。分流原則:泛泛的「部署前/上線前檢查」(未指明只要 UI/UX)應交給 agentic-dev-loop 走雙閘,以免漏掉安全審查;本 skill 只在意圖明確聚焦 UI/UX/易用性/20 原則時觸發。

  • Hf profile optimizer

    MrBridgeHQ/hf-profile-optimizer/.claude/skills/hf-profile-optimizer Skill

    0★ repo

    Audit and optimize Hugging Face personal or organization profiles, including profile positioning, public repositories, Model Cards, Dataset Cards, Spaces README files, Collections, metadata, licenses, demos, trust signals, and responsible discoverability. Use when the user asks to improve, audit, rewrite, rank, polish, or professionalize a Hugging Face profile or repository page.

  • Repo bootstrap

    fpizzuta/repo-bootstrap Skill

    0★

    Clone a GitHub repo, read its own documentation, find and fill the gaps in the local environment, install the project, and verify it actually runs. Use this skill whenever the user gives a GitHub or git URL and wants it set up, installed, running, or tried out locally, and also when they ask "what do I need to run this", "get this working on my machine", "can you set this up", "clone and configure this", or paste a repo link with any intent to use it rather than just read it. Covers Python, Node/TypeScript, and Docker projects on Windows/PowerShell and on Linux containers such as Cowork.

  • Encore lite

    keegan-dotcom/encore-lite/skills/encore-lite Skill

    0★ repo

    Encore Lite is a free end-of-week "I'm feeling lucky" builder. Before the user's weekly usage cap resets, it reads what they've been working on (Claude projects, connected files, repos, recent activity) and produces one speculative bonus deliverable fitted to their actual work — whoever they are. Use this skill whenever the user asks to run Encore, wants their end-of-week bonus or surprise build, says "surprise me based on what I've been working on," mentions using leftover usage/credits before reset, or wants a recurring weekly run set up. Trigger even if the user doesn't say "Encore" but describes this behavior. Also use this skill when the user asks to upgrade Encore, unlock the full Encore, or mentions buying/subscribing to Encore — it handles the whole upgrade conversationally.

  • Tymm acik uclu sinav

    cetin9/tymm/skills/tymm-acik-uclu-sinav Skill

    0★ repo

    MEB yönetmeliğine uygun, açık uçlu / kısa cevaplı ORTAK YAZILI SINAV paketi üretir: konu soru dağılım tablosu + sınav kağıdı + dereceli puanlama anahtarı (ayrı belge); hepsi A4 baskıya hazır HTML. Bir öğretmen "ortak yazılı", "yazılı sınav", "klasik sınav", "açık uçlu sınav" veya "yazılı sorusu" istediğinde kullan — sınıf veya konu henüz söylenmemiş olsa bile, netleştirme sorusundan ÖNCE yükle. Ortak yazılılarda çoktan seçmeli KULLANILAMAZ; öğretmen çoktan seçmeli test/tarama/deneme isterse bu beceri DEĞİL tymm-baglam-testi kullanılır. Desteklenen branşlar: matematik, Türkçe, fen bilimleri, sosyal bilgiler.

  • Qalamlist ops companion

    qalamio/qalamlist-skills/skills/qalamlist-ops-companion Skill

    0★ repo

    Use when working in the QalamList repo and the user asks to deploy, install prerequisites, check setup, run locally, configure Cloudflare, D1, Turnstile, secrets, Wrangler, diagnose deploy errors, or get QalamList running. Use for phrases like "deploy this", "doctor", "prerequisites", "publish", "setup", or "run locally".

  • Fused landing

    sayeediftekhar/Keel/skills/fused-landing Skill

    0★ repo

    Build or restyle landing/marketing pages by fusing a structured workflow (read DESIGN.md → plan sections → build → self-check) with strict token discipline: DESIGN.md tokens only, no ad-hoc hex, one focal point per view, no AI-slop anti-patterns. Defers to keel-v2 tripwires. Use for landing pages, marketing pages, hero sections, and pricing/CTA blocks.

  • Oss research

    NovaKepler513/oss-research-skill/oss-research Skill

    0★ repo

    安全前提下把开源项目读透。用户让你研究/分析/评价任何开源项目、或丢来 GitHub 链接说"看看这个 repo / 怎么实现的 / 值不值得借鉴"时自动使用:云端确认身份+作者全景 Brief → 安全体检(查 install 钩子/危险模式 grep/审配置依赖,安全结论先行)→ --ignore-scripts 保险安装 → 读透架构与核心权衡(结论挂文件:行号)→ 沙箱真机跑通(只绑 127.0.0.1、不喂真实密钥)→ 固定结构研究报告并存档。

  • Plumbline skill

    mightykevster/plumbline-skill Skill

    0★

    Structured spec elicitation — convert a vague design intention into a written, signed spec with verifiable success criteria before iterating on solutions. Use when someone brings a system idea, design question, or "best/most efficient way to X" framing that has no written spec yet, or invokes /plumbline directly. The upstream gate for any improvement loop or design tournament: success criteria and their verifiers live here. Advisory mode produces a lighter question brief for decision and strategy questions rather than system builds.

  • Auto git

    hfjddjksaj/auto-git Skill

    0★

    Set up automatic, per-round git commits for a code project so the user's work is committed every round and never lost. It runs git init, writes a sensible .gitignore, installs a Stop hook that auto-commits each round (and pushes when an upstream is configured), and makes the initial commit — then keeps committing as work continues, and keeps the project's progress files (progress.md, plan.md, and the like) current each round. Trigger it proactively whenever a new code project is being started or scaffolded, even if the user never mentions git: when they describe or kick off building an app, tool, or library, create the first source files, or ask you to write a CLAUDE.md for a codebase. Also trigger on explicit requests such as /auto-git, "turn on auto commit", "set up version control", "commit my changes automatically as we go", or "stop losing my work". Lean toward activating at the start of a coding project rather than missing it. Do NOT trigger for one-off git actions — a single "commit this", "push my branch", "undo my last commit", a rebase or cherry-pick, or merge-conflict help — nor for git how-to questions, since none of those set up the automation. Do NOT trigger for a request that only wants a .gitignore file, for general project tooling like eslint, prettier, or dependency setup, for reviewing or editing existing code, or for non-code work such as writing or research notes.

  • Rubbing to knowledge

    Lx050/rubbing-to-knowledge Skill

    no license0★

    碑帖与拓片研究的可复现证据链工作流。12 个可独立运行的 Skill 组成一条链:材料登记与哈希、确定性图像 baseline、OCR 候选与逐字坐标回链、人工审校交接、文本结构化、文献证据定位、假说反思、诚信审计、知识网络与时间轴/关系路径查询,由主编排 Skill 管理研究状态与阶段门。纯 Python 标准库、完全离线、不需要任何凭证或云服务:一条命令即可复算全部测试(包内实测 12 Skills / 779 项测试 / status pass)。核心差异不在修图或识字,而在把观察 OBS、派生 DER、来源 SRC、推断 INF、假说 HYP 结构性分开:机器与 AI 输出默认只是候选,任何研究主张都必须回链到原图字位或文献定位,失败、冲突、反证与阻断都是正式产物而非被删掉的噪声。当前状态如实说明:知识网络与文本结构化只有合成通道可跑,真人审校未完成,本作品不产出任何历史结论、释文或准确率数字。

  • Starpilot

    gregoirefissore25-tech/starpilot Skill

    0★

    Détecte et intègre automatiquement le meilleur outil open source (repo GitHub, paquet npm ou crate Rust selon l'écosystème) pour accélérer la tâche en cours, en s'adaptant au projet réel en cours (langage, gestionnaire de paquets, dépendances déjà installées détectés depuis package.json/pyproject.toml/Cargo.toml/go.mod...) plutôt qu'à une recherche générique. Utiliser ce skill de manière proactive, SANS que l'utilisateur le demande, dès qu'une tâche de code, d'automatisation, de data, de scraping, d'UI, de parsing, de conversion de fichiers, de trading, d'API ou de build pourrait être résolue plus vite ou mieux avec une librairie ou un outil open source existant. Déclencher aussi quand l'utilisateur dit "trouve un repo", "meilleure librairie", "outil open source", "qu'est-ce qui existe déjà", "top GitHub", ou hésite entre plusieurs librairies. Ne PAS déclencher pour du texte pur, des emails, ou des questions sans composante technique.

  • Buyer nurture sequence

    SkillMedev/real-estate-agent-stack/skills/buyer-nurture-sequence Skill

    0★ repo

    Keeps not-yet-ready homebuyers warm for months with timeline-based segmentation, listing alerts with a why-this-one note, a monthly market-update touch, the pre-approval nudge, and re-engagement triggers. Use when an agent says "keep my buyer leads warm", "these buyers aren't ready yet", "build my buyer drip", or "leads keep going cold and buying with someone else". Do NOT use for generic marketing email drips - use email-drip-builder instead - or for post-open-house first contact, which is open-house-follow-up.

    The same file is in 1 other repository

  • Content multiplier

    CadenceStandard/content-multiplier Skill

    no license0★

    Turn ONE idea, insight, or existing post into a full week of platform-native content — an X/Twitter thread, a LinkedIn post, a short-form video script (Reels/Shorts/TikTok), an Instagram carousel outline, a newsletter/email, a blog outline, a YouTube title+hook set, and 3 standalone quote-cards — each written to that platform's native shape instead of one post copy-pasted everywhere. Use when: "turn one idea into a week of content", "repurpose this post / thread / video", "build a content calendar from one insight", "give me a week of posts about X", "expand this into content for every platform", "multiply this idea", "I have one idea and a blank page", "make this into a thread AND a LinkedIn post AND a Reel", or any time someone has a single message and needs it reshaped across channels. Keyless — pure prompting, zero setup.