Most popular Claude skills · page 380

Agent skills for Claude Code, Claude.ai and other agents, ranked by popularity: GitHub stars, forks, and how many curated lists and repos include them.

22,429 skills · showing 18193–18240

  1. 18193SEO DominatorGPire/claude-skills-swarmSEO completo a livello esperto: SEO tecnico, on-page, off-page, local SEO, E-E-A-T, Core Web Vitals, schema markup, semantic SEO, topical authority, keyword research, content cluster, link building, SEO per Webflow, ranking domination, posizionamento siti, ricerca organica, algoritmi Google. Attiva quando l'utente parla di SEO, ranking, posizionamento, Google, keywords, traffico organico, SERP, backlink, domain authority, meta tag, sitemap, robots.txt.8
  2. 18194SingularityGPire/claude-skills-swarmSINGULARITY — Architettura definitiva finale. Mesh Orchestration (non hub-spoke), Self-Assembling Agent Swarm, Speculative Pre-Execution, Character-Level Token Crystallography, Semantic Tensor Decomposition, Cognitive Bandwidth Multiplexing, Research Agent Ultra-Specializzato, Analysis Agent con causal reasoning, Recursive Agent Self-Assembly, Attention Flow Optimizer, Emergent Specialization Protocol, Zero-Latency Pre-computation, Intelligence Gradient Amplifier, Sub-Agent DNA Injection, Async Mesh Communication, Swarm Consensus Engine, Deep Research Orchestrator, Causal Analysis Engine, Toke8
  3. 18195Skill Creatorydnikolaev/antigravity-factoryDefines the philosophy and process for creating high-quality Antigravity skills. Use this skill when asked to create a new skill or standardize an existing one.9
  4. 18196Skill CreatorGPire/claude-skills-swarmCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.8
  5. 18197Skill Factory Expertydnikolaev/antigravity-factoryExpert on the antigravity-factory project. Knows the entire codebase, skill creation workflow, Makefile commands, and project architecture. Activate this skill when working within the factory repository.9
  6. 18198Skill Interviewerydnikolaev/antigravity-factoryCreative partner for ideating and designing Antigravity skills. Conducts interviews, proposes ideas, defines boundaries, and writes specs for skill-creator. Does NOT create skills directly.9
  7. 18199Skill Updaterydnikolaev/antigravity-factoryMaintains and updates existing skills with new patterns, standards, and fixes. Mass rollout of changes across multiple skills.9
  8. 18200SQLthechandanbhagat/claude-skillsWrite SQL queries, optimize database performance, design schemas, and debug SQL issues. Use for database operations, query optimization, and schema design.9
  9. 18201Tech Spec Writerydnikolaev/antigravity-factoryConverts high-level architecture into detailed, human-readable Technical Specifications. The bridge between Architect and Developers.9
  10. 18202Telegram Mechanicydnikolaev/antigravity-factoryExpert in Telegram Bot API, Webhooks, and Mini App Authentication.9
  11. 18203Testthechandanbhagat/claude-skillsGenerate unit tests, integration tests, and test data. Use when writing tests, improving test coverage, or creating test scenarios.9
  12. 18204Tma Expertydnikolaev/antigravity-factoryExpert in Telegram Mini Apps (TMA) using @tma.js/sdk for native Telegram integration.9
  13. 18205Token OptimizerGPire/claude-skills-swarmOttimizzazione ultra-avanzata dei token: prompt engineering al microsecondo, cache dei prompt (Anthropic prompt caching), riduzione token senza perdita qualità, compressione semantica, batch processing intelligente, architettura multi-agente token-efficiente, streaming ottimizzato, context window management, orchestrazione intelligente agenti, risparmio costi API. Attiva quando l'utente vuole ottimizzare i token, ridurre costi API, migliorare prompt, gestire context window, orchestrare agenti.8
  14. 18206Tui Charm Expertydnikolaev/antigravity-factoryExpert in Terminal UI (TUI) using Charm stack (BubbleTea, Lipgloss).9
  15. 18207UI Implementorydnikolaev/antigravity-factoryUI Implementor that converts design tokens into Tailwind, shadcn components, and production CSS.9
  16. 18208UX Designerydnikolaev/antigravity-factoryUX/UI Designer specializing in design systems, design tokens, and Figma workflows.9
  17. 18209Webflow MasterGPire/claude-skills-swarmWebflow esperto: CMS, design system, animazioni, interazioni, componenti, ecommerce, multi-lingua, SEO Webflow, ottimizzazione performance, logica CMS avanzata, custom code, embed, finsweet attributes, webflow template, librerie, clonabili, Canva integrazione, gestione asset, form, memberships. Attiva quando l'utente parla di Webflow, siti Webflow, CMS Webflow, animazioni Webflow, design Webflow, componenti, template Webflow.8
  18. 18210Workflow Creatorydnikolaev/antigravity-factoryMeta-skill for designing and creating Antigravity workflows. Interviews user, proposes optimal structure, checks for duplicates, and ensures workflows integrate with existing skills.9
  19. 18211XLSXthechandanbhagat/claude-skillsWork with Excel spreadsheets (XLSX/XLS/CSV) - read data, create spreadsheets, convert formats, analyze data, and generate reports. Use when the user asks to work with Excel files or spreadsheet data.9
  20. 18212Abt Narrative Critiquekangning-huang/science_narrative_skillsEvaluate research proposals and papers using the And-But-Therefore (ABT) storytelling framework from Olson's 'Houston, We Have a Narrative'. Calibrated for environmental science and urban climate research. Use when: (1) User asks to critique or evaluate a research proposal introduction/abstract, (2) User asks to assess whether a paper's framing is compelling for publication, (3) User wants feedback on narrative structure of scientific writing, (4) User mentions ABT framework, Olson, or 'Houston We Have a Narrative'. Provides qualitative critique with severity assessment (fatal vs. improvable),5
  21. 18213Abt Narrative Critique Zhkangning-huang/science_narrative_skills使用ABT(And-But-Therefore,即「而且-但是-因此」)叙事框架评估中文科研项目申请书和论文。该框架源自Randy Olson的《Houston, We Have a Narrative》。专为环境科学和城市气候研究领域校准。使用场景:(1) 用户要求评估或点评中文项目申请书的摘要或引言部分,(2) 用户想评估论文框架是否具有发表竞争力,(3) 用户需要科学写作的叙事结构反馈,(4) 用户提到ABT框架、Olson或NSFC/国家自然科学基金申请。提供定性评估、问题严重程度判断(致命缺陷vs可改进问题)、引文核查和建设性修改建议。5
  22. 18214AI Partner Chathhhh124hhhh/LangGraph-Partner基于用户画像和向量化笔记提供个性化对话。当用户需要个性化交流、上下文感知的回应,或希望 AI 记住并引用其之前的想法和笔记时使用。5
  23. 18215Arch Diagramsawallesalfo/claude-skillsThis skill should be used when the user asks to create a technical architecture diagram, system diagram, pipeline flow, swimlane diagram, flowchart, data flow diagram, or any technical documentation visual. Outputs SVG + PNG. Examples: "draw the ingestion pipeline", "create an architecture diagram", "make a flowchart for X", "explain the system with a diagram".5
  24. 18216Archviz Storyboardfelipealmeidasid/Pack-skills-for-archvizCreate professional architectural visualization storyboards, project storyboard packages, moodboards, architectural detail boards, film-sequence boards, clean keyframe plans, GPT Image board prompts, and Seedance video prompt packages for real estate presentations. Use when the user provides archviz renders, photos, floor plans, real estate assets, approved images, or a create-real-estate-worlds handoff and wants cinematic storyboard boards with strict architectural fidelity. Default project formats are 9:16 for Reels/social and 16:9 for presentations/horizontal films; ask the aspect ratio at 5
  25. 18217Axum Best Practicemaulanasdqn/tanstack-axum-claude-skillsEnforce Axum/Rust backend best practices when writing Rust code5
  26. 18218Create Real Estate Worldsfelipealmeidasid/Pack-skills-for-archvizCreate cinematic real estate world bibles, world databases, visual DNA systems, reference-grounded architectural universes, scene libraries, realistic personas, prompt packs, and handoff packets for architecture, archviz, property launches, luxury homes, apartments, towers, condominiums, resorts, hotels, interiors, amenities, branded real estate campaigns, AI image/video generation, and future world-model systems. Use when the user wants a reusable AI-ready source of truth for realistic real estate storytelling. Ask the aspect ratio at the beginning of each new project and use 9:16 for Reels/s5
  27. 18219Godot Csharp APIFortyseven/Godot-Claude-SkillsGodot 4 C# API reference and tutorials skill. Use when answering questions about Godot 4 C# development, class methods, properties, signals, enums, constants, or how-to guides. Provides condensed C#-only API docs for all ~1,065 Godot 4 engine classes plus 347 official tutorials, split into domain-specific files. Do NOT use for GDScript Godot development — use godot-gdscript-api instead.5
  28. 18220Godot Gdscript APIFortyseven/Godot-Claude-SkillsGodot 4 GDScript API reference and tutorials skill. Use when answering questions about Godot 4 GDScript development, class methods, properties, signals, enums, constants, or how-to guides. Provides condensed GDScript-only API docs for all ~1,065 Godot 4 engine classes plus 347 official tutorials, split into domain-specific files. Do NOT use for C# Godot development — use godot-csharp-api instead.5
  29. 18221Grantproofellewangyuan/grantproofSurfaces common writing-style mistakes in federal R&D grant prose — NSF SBIR/STTR, DoD SBIR, NIH SBIR, DOE, DARPA, NASA, NOAA, and similar. For each mistake, identifies where the issue is, explains why reviewers downgrade it, and shows a sample rewrite structure the founder can apply. Use when the user pastes draft writing for an R&D grant pitch or proposal.5
  30. 18222Langgraph Developmenthhhh124hhhh/LangGraph-Partner专业的LangGraph AI应用开发技能,提供从概念到生产的完整开发指导。基于Context7最新调研,涵盖StateGraph设计、多代理协作、RAG系统实现、生产部署等核心场景。使用此技能构建有状态、多参与者、长期运行的AI代理应用。5
  31. 18223Mock Exam Builderaq7zo/mock-exam-builderBuild or update a self-contained HTML midterms/finals mock exam and per-topic practice quizzes strictly from class materials in a sources/ folder, with clickable citations, exam-based mastery tracking, reorderable sections, and incremental updates.5
  32. 18224Motia ExpertCoderMageFox/claude-skills-marketComprehensive Motia backend framework expert. Use when building APIs, background jobs, workflows, AI agents, or event-driven applications with Motia. Covers TypeScript/Python steps, flows, plugins, and configuration.5
  33. 18225Oasham-jadhav03/Claude_SkillsActivates Deep Problem Solver mode when the user types `/oa`. Applies a strict 7-phase framework: Understand → Trap Hunt → Model → Plan → Execute → Verify → Answer. Use for DSA problems, algorithm questions, coding interviews, and any problem where pattern-matching leads to wrong answers. Never skip Phase 1 or Phase 2. Never jump to code before both are complete.5
  34. 18226Playbook Builderumairalipathan1980/Playbook-Builder-SkillGuides users through creating a negotiation playbook skill tailored to their contract type and side — clause by clause, with standard position, fallback tiers, walk-away line, and red flags. Outputs a structured playbook skill definition ready to paste into the skill editor. Use when a user asks to build a contract playbook, create negotiation positions, set up a redline baseline, or customize a playbook for a specific deal type or counterparty side.5
  35. 18227Professional Services Contract Playbookumairalipathan1980/Playbook-Builder-SkillNegotiation playbook storing pre-approved positions and approved language for professional services agreements, consulting contracts, and government procurement agreements. Referenced by flag-issues and fallback skills to baseline clause reviews against organizational positions rather than generic market standards. Contains tiered positions (Preferred → Acceptable → Walk-away) and draft redline language for all major negotiated clauses. Lookup keyword: playbook, approved language, positions.5
  36. 18228Reduce Tokensham-jadhav03/Claude_SkillsActivates compact, high-density response mode when the user types `/reduceToken` or any variant like `/reduceToken 500` or `/reduceToken study`. Apply this skill immediately and hold it for the entire session. Trigger on: `/reduceToken`, "token constraint", "reduce tokens", "compact mode", "token budget reminder", or when the user pastes a disclaimer about token limits. Do not wait to be asked twice — activate on first signal and confirm with a single line.5
  37. 18229Revise Questionsaq7zo/mock-exam-builderRevise questions in an existing mock exam built by mock-exam-builder: pick a topic, subtopic, single question or the whole coverage, review each question with its choices, then rewrite it at a different cognitive level (Recall / Understand / Apply / Analyze, or to a sentence the user writes) and/or convert its format (single-answer multiple choice, multi-select, True/False). Use it whenever the user wants to change, rewrite, re-level, harden, simplify or convert questions in an exam that already exists, even if they don't name the skill.5
  38. 18230Screenshotsawallesalfo/claude-skillsCapture a full-page screenshot of any public URL using Playwright's headless Chromium browser. Use this skill whenever the user provides a URL and asks to take a screenshot, capture a page, grab a visual snapshot, or see what a website looks like. Also trigger when the user says things like "screenshot this", "capture this page", "show me what this site looks like", or "get a screenshot of [URL]". Works on GitHub, Docker Hub, dev.to, npm, PyPI, and any public website. No API key required — uses a local headless browser via Playwright.5
  39. 18231Stealth Browserzippoxer/claude-skillsStealth browser automation with anti-bot bypass and persistent page state. Use when users need to navigate Cloudflare-protected sites, fill forms, take screenshots, extract web data, or automate browser workflows on sites that block regular automation. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "bypass cloudflare", or any browser interaction request on protected sites.5
  40. 18232Subcodexzippoxer/claude-skillsCollaborate with Codex (GPT-5.2) via named sessions. Trigger: user asks to work with Codex, use Codex, ask Codex, involve Codex, etc. CRITICAL: Use subcodex CLI via Bash, NOT the Task subagent tool.5
  41. 18233Tanstack Best Practicemaulanasdqn/tanstack-axum-claude-skillsEnforce TanStack frontend best practices when writing React/TypeScript code5
  42. 18234Windmill ExpertCoderMageFox/claude-skills-marketComprehensive Windmill workflow platform expert. Use when building scripts, flows, apps, or managing resources in Windmill. Covers TypeScript/Python/Go/Bash scripting, multi-step workflows, UI apps, schedules, webhooks, and API integration.5
  43. 18235Blogger Trackermiaqu766520-a11y/ai-line-skills开源博主追踪系统:默认用 browser-act 真实浏览器免费抓 B站/抖音博主最新视频;TikHub 付费 API 为备用引擎(大批量/全历史回填时才启用)。本地 JSON+Markdown 存储,增量发现新视频,生成追踪报告;可选回写飞书多维表。当用户说「加博主」「追踪这个博主」「更新追踪」「谁更新了」「博主追踪报告」「盯一下这个 UP主」「博主最近发了什么」「开源博主追踪」「回填博主历史视频」时触发。依赖 browser-act skill。区别于 douyin-downloader(下载视频本体)与 xiaohongshu-creator-analytics(自己账号后台数据)。9
  44. 18236Bozai Scriptmiaqu766520-a11y/ai-line-skills把用户口述(文字或录音)整理成符合用户个人风格的口播稿——整理模式保真改写(信息零新增、口头禅保留、去AI味),共创模式辅助写稿(事实数字标存疑)。当用户说「整理成口播稿」「我口述你整理」「把这段顺成稿子」「写个口播稿」「口播稿」「帮我把这段话变成能念的稿」时使用。也用于把改稿反馈回流风格档案(迭代机制)。9
  45. 18237Bozai Storyboardmiaqu766520-a11y/ai-line-skills口播稿 → 视频生产线之间的「分镜表」中间产物:接已定稿的口播稿/配音稿, 按口播线/演示线模板产出 Markdown 分镜表 + 同内容 JSON(Remotion 等组装层数据可直接消费), 用户在分镜表上审完改完确认后,才进画面组装/录制生产线—— 把审阅点从成片(贵)前移到分镜表(便宜)。 当用户说「分镜」「分镜表」「脚本运镜」「制作脚本」「拍之前先出个表」「先列个镜头表给我看看」 「storyboard」时触发。区别于写稿类 skill(产出口播稿)和成片组装类 skill(生产线)。9
  46. 18238Cheat Bumpmiaqu766520-a11y/ai-line-skills提议并执行 rubric 或 bucket 升级。两种模式:**完整 rubric bump**(最高风险动作,5 步强制 + 跨模型审核)和 **--bucket-only 轻量重校**(只换 bucket 边界,不动 rubric 公式)。**Phase 2 强制走 cheat-score-blind sub-agent 给校准池重打分**——不接受 self-scored fallback。触发词:"升级 rubric"/"bump rubric"/"更新公式"/"我想加一个维度"/"调整权重"/"重校桶"/"recalibrate bucket"。9
  47. 18239Cheat Initmiaqu766520-a11y/ai-line-skillscheat-on-content 的首次 onboarding 与脚手架创建器。统一流程——所有用户都走相同 5 阶段闭环,唯一区别是"发过视频的人"会在 init 时多一步:抓取已有视频建立历史 context(用于后续 cheat-seed 给更贴合的选题、更准的 baseline)。触发词:"初始化"/"init"/"首次使用"/"我是新用户"/"setup cheat-on-content"。**必须在用户第一次会话执行;其他子 skill 在 .cheat-state.json 不存在时自动路由到此。**9
  48. 18240Cheat Learn Frommiaqu766520-a11y/ai-line-skills从对标账号导入 script + 数据 → 拆 pattern + 派生 base rubric 信号 → 写到 benchmark.md / script_patterns.md / rubric_notes.md。**这是工具最早期信号的来源**——cold-start 用户没自己历史时全靠对标,发过历史的用户也建议至少 1 个对标做 sanity check。触发词:"学这个账号"/"拆这几个对标视频"/"learn from"/"导入对标账号"/"找对标"。9