Most popular Claude skills · page 371

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 17761–17808

  1. 17761MCP VulnerabilitiesJasonTheDeveloper/owasp-skillsOWASP MCP Top 10 (2025) vulnerability knowledge base for identifying, assessing, and remediating security risks in Model Context Protocol environments.9
  2. 17762Meituan Living Assistantpuzige/meituan-living-assistant-skill美团生活助手——一键领美团优惠券、搜附近团购美食并下单。当用户提到领券、领优惠、省钱、羊毛、团购、今天有什么活动、附近有什么好吃的、想吃什么(火锅/烧烤/日料/咖啡/奶茶等)时触发;也用于美团账号扫码登录、定时自动领券、取消提醒等场景。5
  3. 17763Memory CompactionArchive228/lab-skillsOperating procedure for keeping a long-running agent coherent using the OpenAI Agents SDK memory and compaction primitives: three ways to trigger compaction (automatic, threshold-based, forced checkpoint), exact rules for what working state to preserve through a compaction, and what belongs in cross-run memory versus the reviewed output artifact. Trigger when building or operating an agent whose session spans many turns or evidence batches and risks context overflow, when deciding what to persist across sessions, or when wiring Compaction()/Memory() capabilities into a SandboxAgent.10
  4. 17764Meta Analysis Systematic Reviewmaydengximin-sketch/meta-analysis-systematic-review-skill元分析与系统综述(Meta-analysis / Systematic Review + PRISMA)专项方法学助手,聚焦"用 PRISMA 规范做一篇可复制的系统综述,并在合适时把定量结果用元分析合并"的完整链路。当用户要做系统综述或元分析的任何环节时使用:判断"我该做叙述性综述、系统综述、还是元分析、数据够不够同质来合并"、写可检索的研究问题(PICO/PICOS)与预注册协议(PROSPERO)、设计检索策略(数据库、检索式、灰色文献、纳入排除标准)、按 PRISMA 2020 画流程图并双人筛选(标题摘要→全文)、数据提取与调节变量编码、选并计算效应量(Cohen's d / Hedges' g / 相关 r / OR / RR / 及其方差与换算)、固定效应 vs 随机效应模型的选择与加权、异质性评估(Q 检验、I²、τ²)与亚组分析和元回归、发表偏倚检测(漏斗图、Egger 检验、trim-and-fill、p-curve)、研究质量与偏倚风险评价(RoB2 / Newcastle-Ottawa / GRADE)、用软件(R metafor/meta、CMA、RevMan、Stata)做森林图并按 PRISMA 报告、把结果写进论文并应对答辩。触发词包括"元分析""荟萃分析""meta-analysis""系统综述""系统评价""systematic review""5
  5. 17765Minimal Patch with Subagentskargnas/skillsMinimal patching workflow that debates fix options across parallel independent subagents and applies the smallest safe diff. Use only when you want risk-free code, and to code real minimal that only needs to fix the issue.9
  6. 17766Minimax H3 Promptkuronzzhan-droid/minimax-h3-prompt-skill按 MiniMax-H3 的两种有效格式撰写视频生成提示词(时间轴风格 / 官方结构化风格),覆盖 T2VA 文生视频、I2VA·FL2VA·L2VA 首尾帧、full-reference 参考生视频 R2V。只要用户想用本地 ComfyUI 的 H3 出视频、要求写或改 H3 提示词、提到 MiniMax H3 / ref2va / fl2va、给参考图或音色让角色说话唱歌、或抱怨 H3 出片"角色不像/台词乱语/声音不对/动作没跟上节拍",都应使用本技能——它带官方规范原文、两种风格的实战范例和本机显存实测约束。5
  7. 17767MjmlJayOram/MJML-ai-knowledgeAuthor, compile, debug, and refactor MJML (Mailjet Markup Language) responsive email templates. Use this skill whenever the user is working with MJML — writing or editing .mjml files, building or fixing a responsive HTML email, using mj-* tags (mj-section, mj-column, mj-button, mj-hero, etc.), compiling MJML to HTML via the CLI or the mjml2html Node API, setting up shared partials with mj-include, or asking why an email renders wrong in Outlook/Gmail. Trigger it even when the user says "email template," "newsletter HTML," or "responsive email" without naming MJML explicitly, since MJML is usua5
  8. 17768Ml VulnerabilitiesJasonTheDeveloper/owasp-skillsOWASP Machine Learning Top 10 (2023) vulnerability knowledge base for identifying, assessing, and remediating security risks in machine learning systems.9
  9. 17769Mobile VulnerabilitiesJasonTheDeveloper/owasp-skillsOWASP Mobile Top 10 vulnerability knowledge base for identifying, assessing, and remediating security risks in mobile application environments.9
  10. 17770Monorepo AgentsArchive228/lab-skillsOperating procedure for running coding agents on large codebases and multi-million-line monorepos: agentic search over indexing, hierarchical CLAUDE.md layering, noise exclusion via .claudeignore and permissions.deny, LSP for symbol-level navigation, subagents for exploration/editing splits, and enterprise rollout patterns. Use when working in, configuring, or deploying Claude Code (or a similar agent harness) on a repo too large to hold in context — many services, hundreds of top-level folders, or millions of files.10
  11. 17771Oss Finderkargnas/skillsFinds battle-tested open-source repos, libraries, frameworks, CLI tools, or code on GitHub, ranked by README polish-days instead of stars. Also the shared GitHub code-search backend toolkit — rotating PAT pool, grep.app, Blackbird web index, BigQuery/GHArchive, and the code-search fallback chain. Use for 'find a library/framework/tool for X', 'battle-tested repo', GitHub-wide code search, or when `gh search code` rate-limits. Finding installable SKILL.md agent-skill packages goes to the skill-finder skill (it delegates its GitHub sweep here).9
  12. 17772Oss VulnerabilitiesJasonTheDeveloper/owasp-skillsOWASP Open Source Software Top 10 vulnerability knowledge base for identifying, assessing, and remediating security risks in open source software dependencies.9
  13. 17773Paper Research DownloaderHPSummer/paper-research-downloaderSearch, resolve, download, parse, batch-process, audit, and ingest research papers for Codex or Claude. Use when the user wants paper discovery, literature search, DOI/arXiv/PMID/PMCID resolution, open-access PDF download, paywall-aware lawful access plans, user-mediated institutional access through the user's own browser, local PDF ingestion, mixed identifier batch download, full-text parsing, PMC XML fallback, BibTeX/CSV/RIS/CSL-JSON export, Zotero duplicate checks, dependency diagnostics, resumable cached runs, duplicate-aware Obsidian literature notes with YAML frontmatter, tags, and wiki 5
  14. 17774Paper Translate ZhZhiheChen1/paper-translate-zhTranslate an academic paper into a polished, academically-styled Chinese PDF. Use this skill whenever the user wants to 翻译论文 / 把论文翻成中文 / translate a paper, manuscript, preprint, or any scholarly work into Chinese, produce a Chinese version (ZN.pdf / 中文版), or read a foreign-language paper in Chinese. Trigger even when the user only drops a paper PDF, gives an arXiv link/ID, or says "翻译一下" / "做个中文版" / "translate this to Chinese" without naming LaTeX. Two source paths: if LaTeX source is available (arXiv e-print, or user-provided .tex) translate the source directly (highest fidelity); otherwise e5
  15. 17775PDF Look Scannedvladmdgolam/agent-skillsMake PDF documents look like they were scanned on a physical scanner. Applies realistic effects: grayscale conversion, Gaussian noise, slight rotation, blur, edge shadows, and random offset. Optionally extract real handwritten signatures from a source PDF (or user-provided images) and replace digital signatures on specific pages. Use when the user asks to: make a PDF look scanned, give a PDF a scanned appearance, replace digital signatures with real/handwritten ones, fake a scan, add scan effects to a document, or make a document look printed and scanned.9
  16. 17776Phd Application Advisoralex-yimingyang/phd-application-advisor大龄非科班转AI申请海外PhD的全流程顾问。覆盖RA申请、选方向选校、套磁、文书、面试、推荐信、时间规划等所有环节,专门针对30+在职、非CS背景、想转AI方向申博的人群提供策略建议。 当用户提到以下任何场景时使用此skill:大龄读博、非科班申博、转行申PhD、30+申博、在职申博、工作后读博、非传统背景申请PhD、AI方向博士申请、美国博士申请、海外PhD、申博规划、申博咨询,或任何涉及"工作几年后想读博不知道怎么开始"的问题。即使用户没有明确说"非科班",只要描述了类似背景(非CS本科、工作多年、想转AI/ML方向读博),也应触发此skill。5
  17. 17777Planner Evaluator HarnessArchive228/lab-skillsMulti-agent harness pattern (planner / generator / evaluator) for long-running application builds, distilled from Anthropic's engineering post on harness design. Use when a build will run for hours or sits beyond what the current model ships reliably solo: covers sprint contracts, skeptical-evaluator calibration, hard-threshold QA grading via browser automation, context resets vs compaction, and how to strip the harness down as models improve.10
  18. 17778Planning Before Create SkillthePlannerIvan/planning-before-create-skill创建或升级 Skill 时使用的设计与验收准则。明确目标和好坏判据,按需沉淀工具与专业经验;升级时依据真实问题修正、验证并清理失效内容。5
  19. 17779Problem Miningsidneyswift/skillsInterview-driven discovery that surfaces profitable problems hiding in your own experience. Walks the user through a structured 1-question-at-a-time interview across four phases — achievements, problems overcome, desire mapping (money/time/status), and root-cause reframing — then synthesizes validated product ideas from the extracted signal. Use when someone wants to find a product to build, doesn't know what problem to solve, or says "I have skills but no product idea.9
  20. 17780Prompt Cache OptimizationArchive228/lab-skillsMaximize OpenAI prompt-cache hit rate to cut time-to-first-token latency by up to 80% and input token cost by up to 90%: prefix-stability rules, cache-aware prompt layout, prompt_cache_key routing, allowed_tools, Responses API vs Chat Completions, Flex vs Batch, extended 24h caching, and Realtime retention_ratio. Use when designing or reviewing prompt/message layout for any repeated OpenAI API workload, when cached_tokens is low or zero, when TTFT or input spend is high at scale, or when choosing truncation/compaction strategy for long conversations. Scope: models before GPT-5.6 (per the sourc10
  21. 17781Prompt Engineering CanonArchive228/lab-skillsCanonical prompt-engineering operating procedure distilled from Google's 68-page Prompt Engineering whitepaper (Lee Boonstra, Feb 2025): when to use zero/few-shot, system/contextual/role prompting, chain-of-thought, step-back, self-consistency, ToT, ReAct, output-format control, and exact temperature/top-K/top-P starting values. Trigger whenever writing, reviewing, or debugging a prompt for an LLM, choosing sampling configuration, or deciding which prompting technique fits a task.10
  22. 17782Red Tide Algal Bloom Monitoringdungnotnull/red-tide-algal-bloom-monitoring-agent-skillRed Tide (Harmful Algal Bloom) Monitoring & Early Warning - HAB Monitoring & Aquaculture Safety analysis & decision-support harness. Use this skill whenever the user asks about red tide, harmful algal blooms, HAB monitoring, aquaculture safety, marine water quality, algal toxin detection, shellfish safety, marine biological monitoring, satellite chlorophyll analysis, coastal water management, or needs analysis of marine bloom events. This includes queries about bloom detection, toxin risk assessment, aquaculture impact, early warning systems, environmental triggers, species identification, or 5
  23. 17783Resume Generatortanbiralam/claude-resume-generator-skillGenerate a fully tailored, ATS-optimized LaTeX resume from an uploaded PDF or DOCX resume and a job description. Use this skill whenever the user uploads a resume (PDF or DOCX) and wants to tailor it to a job, create a new version, improve ATS score, or generate LaTeX output. Also trigger when the user says things like "tailor my resume", "make my resume ATS friendly", "generate a resume for this JD", "rewrite my resume", "convert resume to LaTeX", or pastes a job description alongside a resume file. Always use this skill — don't try to wing resume generation without it.5
  24. 17784Reverse Engineer Jsvladmdgolam/agent-skillsReverse-engineer minified or obfuscated JavaScript bundles. Primary tool: humanify (humanifyjs) — uses an LLM to rename mangled identifiers back to meaningful names. Default model: gemini-3.8-flash. Use when the user says 'deobfuscate this bundle', 'humanify this', 'rename minified vars', 'reverse engineer this JS', 'what does bundle.js do', or is working in a project with a deobfuscated `og/` or `modules/` folder fed by humanify. Covers humanify CLI invocation, the pseudo-TTY workaround for cursorTo crashes, single-module extraction from a bundle, and chaining with beautifiers.9
  25. 17785Reviewer Response Rebuttalmaydengximin-sketch/reviewer-response-rebuttal-skill审稿意见回应与修回信(Response to Reviewers / Rebuttal Letter)专项助手,聚焦"收到期刊 major/minor revision 决定信后,如何写出一封让编辑与审稿人满意、显著提高录用概率的逐条回应信"的完整链路。当用户要处理修回、回复审稿意见、写 rebuttal 的任何环节时使用:读懂并拆解编辑决定信(区分编辑硬性要求 vs 审稿人建议、必答项 vs 可选项、major vs minor vs reject-and-resubmit)、搭建回应信整体结构(致谢开场 + 逐条编号 + 修改稿定位约定)、写好逐条回应的黄金三段式(复述该条意见→说明如何修改→引用修改后的原文并标注页码/行号)、把握不卑不亢的语气与外交辞令、同意并落实修改时怎么写、礼貌但有据地反驳(push back)不合理意见时怎么写、处理两位审稿人意见相互冲突、应对常见要求类型(补分析/补文献/理论深化/方法澄清/样本与因果质疑/英语润色)、写给编辑的 cover letter、重投前的 tracked changes 与清单核对与时间管理、高频英文回应句式库。触发词包括"审稿意见""回复审稿人""修回""大修""小修""major revision""minor revision""response to reviewers""rebuttal""回应信""修改说明""r5
  26. 17786River Trash Boom Robot Designdungnotnull/river-trash-boom-robot-design-agent-skillAutonomous River Trash-Boom Design & Testing — Production-grade harness for Autonomous River Debris-Boom Robotics & Hydraulics evidence-backed analysis with real-time data aggregation, recognized domain methods, and self-improving knowledge pipeline.5
  27. 17787Rumijoshpuckett/claudeDisplay a random Rumi poem in a beautiful ASCII frame. Use when the user types "rumi" or asks for a Rumi poem, quote, or moment of zen/inspiration.5
  28. 17788Security Reviewer FormatsJasonTheDeveloper/owasp-skillsFormat specifications and data contracts for the security reviewer orchestrator and its subagents - Brought to you by microsoft/hve-core.9
  29. 17789Semantic Compressiontherealmoronto/claude-semantic-compressionApply semantic logic compression (Ovchinnikov method) when crafting prompts for LLMs or describing complex conditional logic. Use this skill whenever the user asks to: write or optimise a prompt for an LLM, compress or rewrite a task description, describe multi-condition business logic (if/and/or/not chains), or asks why an LLM misunderstood their instructions. Also trigger when the user says ‘compress the logic’, ‘write a prompt for’, ‘the LLM doesn't understand’, ‘simplify the conditions’, or similar intents. Also trigger when the user wants to use output modifiers such as →code or →no-meta,5
  30. 17790Serverless VulnerabilitiesJasonTheDeveloper/owasp-skillsOWASP Serverless Top 10 vulnerability knowledge base for identifying, assessing, and remediating security risks in serverless application environments.9
  31. 17791Skill AuthoringArchive228/lab-skillsAuthor, review, and validate Agent Skills (SKILL.md folders) against the agentskills.io spec and Google's Agent Skills whitepaper: frontmatter constraints, naming, description-as-router, progressive disclosure, bundled scripts/references/assets, and evaluation gates. Use when creating a new skill, editing or reviewing an existing SKILL.md, converting a runbook or successful agent trace into a skill, or deciding whether content belongs in a skill vs AGENTS.md vs an MCP server.10
  32. 17792Skill Finderkargnas/skillsFinds and ranks installable SKILL.md agent-skill packages for a task: discovers via the `npx skills` marketplace plus a GitHub-wide sweep, then ranks by real human iteration — semantic polish-days, content depth (production vs toy signals), and optional social review — not stars or install counts. Use for skill discovery: find/search a skill, 'is there a skill for X', task-specific skill lookup, compare skills. Delegates the GitHub search itself to the oss-finder skill; finding general OSS libraries/frameworks/tools (not SKILL.md packages) also goes to oss-finder.9
  33. 17793Skill Managerkargnas/skillsCreates, restructures, merges, and splits agent skills: directory layout, bundled guides/scripts/assets, cross-agent placement under .agents/skills, importing community skills, merging several skills into one so fewer descriptions load into every session, and a sanitization pass that checks model IDs against models.dev. Triggers on 스킬 생성, 스킬 병합, 스킬 분리, 스킬 구조 정리, 외부 스킬 가져오기, 스킬 검증, 모델 업그레이드. Step wording and name/description wording go to skill-prompter; finding published skill packages goes to skill-finder. Confirm with the user before running, with a brief explanation of what this skill will 9
  34. 17794Skill Prompterkargnas/skillsPrompting compliance specialist for AI agent skills — rewrites SKILL.md steps with RFC 2119 wording, explicit tools, VERIFY gates, and dry-run checks; also owns skill name + frontmatter description wording (trigger-surface rules). Use only when the user asks to improve or harden a skill's prompts/steps or to name/review a skill description, and confirm with the user before running since this takes quite long time and need to run a few smoke tests with subagents to check if the skill is perfect. Structural lifecycle work goes to skill-manager.9
  35. 17795Skillssidneyswift/skillsInstall, list, update, or extend Sidney's curated collection of agent skills. Use when asked to install all of Sidney's favorite skills, bootstrap an agent from this collection, or add a skill repository to the collection. This is an installation gateway, not a skill-authoring or general skill-search workflow.9
  36. 17796Slack API Readonlykargnas/skillsScrape Slack read-only via Web API (user token) into markdown for LLM. Use to FETCH Slack conversation directly — by channel, thread permalink, or search — without copy-paste. Real names, mrkdwn unwrapped, emoji/reactions kept, tz configurable; --files downloads images/attachments. Stdout-only otherwise. Formats pasted Slack text with the bundled cleaner.9
  37. 17797Social Postlp1688/skill-social-post學習使用者的 Facebook/Instagram/YouTube/Threads/X 語氣與受眾,規劃內容、撰寫平台化貼文、經確認後發佈;並作為所有流量、演算法、留存與轉化學習的唯一結構化帳本,做跨平台/跨篇/跨集比較、實驗設計及規則升降級。使用者說「發文」「幫我寫」「用我的口氣」「排貼文」「查流量」「演算法」「分析 Reels/Shorts」「把數據訓練進去」「記錄成效」「比較這幾篇」「優化 pattern」「review」時使用。5
  38. 17798Solar Adsorption Cooling Systemdungnotnull/solar-adsorption-cooling-system-agent-skillSolar Adsorption Cooling System Design & Operation — Solar Adsorption Cooling & Refrigeration Engineering evidence-backed analysis harness. Use this skill whenever the user asks about solar adsorption cooling systems, adsorption chillers, solar thermal cooling, refrigeration system design, adsorbent pair selection, COP optimization, or any solar cooling engineering analysis. This includes sizing systems, selecting adsorbent/adsorbate pairs, analyzing cooling capacity, evaluating thermal sources, or comparing solar cooling technologies.5
  39. 17799Spec Coachboxabirds/spec-coachActivate when the user is writing, editing, or discussing software requirements, specifications, acceptance criteria, user stories, or feature definitions. Also activate when the user asks to build, implement, or create a feature and no specification or requirements document has been referenced or exists in the conversation. Do NOT activate for bug fixes, refactoring, documentation, or tasks where requirements are already clearly defined in the conversation.5
  40. 17800Spec Driven DevArchive228/lab-skillsOperating procedure for spec-driven development (SDD) with AI coding agents: treat code as disposable and the specification as the durable, versioned asset, then run the Constitution → Specify → Plan → Tasks → Implement loop (GitHub Spec Kit) with behavior-driven Gherkin-style specs. Trigger whenever building software meant to outlive a prototype — production features, multi-session or multi-agent work on one codebase, or legacy regeneration/migration — instead of vibe-coding straight to code.10
  41. 17801Spec Goalssidneyswift/skillsUse when someone asks 'help me write a /goal', 'turn this into a goal', 'draft a goal for Codex', 'spec this for /goal', 'is this a good goal', or 'sharpen this objective'. Turns a defined, durable objective into a ready-to-paste Codex `/goal` with a measurable outcome, verification surface, constraints, boundaries, iteration policy, and blocked-stop condition. If the outcome, evidence, constraints, or approach still contains load-bearing unknowns, use flex-finding-unknowns first. Do NOT use this skill to execute the work.9
  42. 17802Speclj Structure Checkunclebob/speclj-structure-checkUse after every spec file edit to catch Speclj nesting errors before running tests5
  43. 17803Startup Application Coachbetahope/startup-application-coachHelp founders write stronger applications to startup programs, accelerators, incubators, and pre-accelerators. Use when a founder is drafting, reviewing, critiquing, or getting unstuck on any accelerator application question, or working on a founder, team, or demo video. Triggers include answering an application question, reviewing a draft, framing traction, describing a problem or solution, planning a video, or any mention of a startup program application. Use even when no specific program is named, as long as the context is a startup program application. Also triggers when the user mentions 5
  44. 17804Three Loop Workflowcaohaotiantian/three-loop-workflowImplement non-trivial code or contract-rule changes through Plan, Build, and Close. Also use for pre-landing review. Exclude questions, exploration, and obvious small edits.5
  45. 17805Threejs Perf Loadingvladmdgolam/agent-skillsPerformance and loading patterns for real-time Three.js/WebGL/WebGPU sites, based on modern approaches and best practices explored from top-notch studios and developers (Ivress brand site, Threejspunk cyberpunk-rain demo, igloo.inc, Noomo Agency showcase) plus live production profiling, rather than generic advice. Use when eliminating the loading-spinner-to-scene freeze/jank, hiding shader/pipeline compile cost behind a loading screen, designing an adaptive-quality or perf-budget system (including hardening it against false-positive degrades from transient stalls), attributing unexplained slow9
  46. 17806Time Lensvladmdgolam/agent-skillsAnalyze and visualize time spent on software projects by combining data from multiple sources: WakaTime coding time, git commit session detection, Claude Code usage, Codex CLI usage, and Cursor IDE usage. Produces both an interactive HTML dashboard (dark-themed, Chart.js) and a Markdown report with ASCII charts. Use when the user asks to: analyze work hours, calculate time spent on a project, generate a work hours report, visualize coding activity, create a project time breakdown, or summarize development effort across date ranges.9
  47. 17807Tool DesignArchive228/lab-skillsDesign and iterate on tools (MCP or direct API) that agents actually use well: prototype-then-evaluate loops, agent-assisted tool optimization, consolidated workflow tools, namespacing, high-signal responses, and token-efficient outputs. Use when writing or refactoring tool definitions, building an MCP server, debugging why an agent misuses/ignores tools, or reviewing tool schemas and descriptions.10
  48. 17808Trop Image Promptsabsolument-ai/tropWrites AI image prompts with a strong, recognizable art-direction signature (raw, human-first, trend-driven, typography-led) for Midjourney, ChatGPT/GPT Image, Gemini, Flux, Ideogram and similar. Use whenever the user asks for an image prompt, a visual, a poster, a key visual, an ad image, a moodboard prompt, a "prompt Midjourney", or wants an idea turned into an AI image — even a one-line brief.5