Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 566 files from 1 758 authors, of which 61 913 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Guide on how to rebuild Druid using Maven while skipping unnecessary checks. Use this skill when asked to compile or build Druid.
How to calculate GitHub community pulse metrics using the `gh` CLI. Use this skill whenever the user asks for pull request metrics, issue metrics, community pulse, average merge times, top contributors, or bug reports over a specific timeframe.
How to implement custom loss functions in PyTorch. Use this skill whenever the user asks to implement a loss function, write a custom criterion, or mentions PyTorch tensor operations for backpropagation.
How to reproduce Deep Learning papers. Use this skill whenever the user asks to implement an algorithm, loss function, architecture, or technique based on an academic paper (PDF, Arxiv, etc).
How to process Word documents (.docx) with python-docx. Use this skill whenever the user mentions Word templates, docx templating, replacing placeholders, or processing Word files, even if they don't explicitly ask for it.
How to classify and organize documents (PDFs, DOCX, PPTX) into categories based on their content. Use this skill whenever the user mentions organizing, sorting, or classifying documents into subjects or folders, even if they don't explicitly ask for it.
How to use circe for JSON processing in Scala. Use this skill whenever translating Python json operations to Scala or working with circe libraries.
Translating Python simulated Functors and Monads to Scala Higher-Kinded Types. Use this skill whenever implementing functional programming concepts like Functor, Monad, Applicative in Scala.
Translating Python TypeVar variance to Scala. Use this skill whenever you see T_co or T_contra in Python and need to write equivalent Scala traits or classes.
How to implement cross-highlighting between D3.js visualizations and HTML Data Tables. Use this skill whenever the user wants to connect a chart (like a bubble chart or scatter plot) with an HTML table, so clicking or hovering one updates the other.
How to filter tabular datasets. Use this skill whenever you need to process or filter CSV files, tabular data, or databases to find records that match specific criteria such as location, price, category, or flags (like pet-friendly).
How to plan travel itineraries. Use this skill whenever the user mentions a travel itinerary, a trip, planning a vacation, or generating a schedule from travel constraints, even if they don't explicitly ask for an itinerary planner.
Extract key frames (I-frames) from video files using FFmpeg CLI. Use this skill whenever you need to pull out keyframes, thumbnails, or important frames from MP4, MKV, AVI, or other video formats for analysis, previews, or processing.
Command-line tools for modifying and manipulating images, such as resizing, blurring, or changing colorspace. Use this skill whenever the user mentions modifying images, converting to grayscale, or changing image properties.
Count occurrences of an object in an image using computer vision algorithms. Use this skill whenever the user asks to count objects, find matches, or identify items in a scene using a template image.
How to write advanced Excel formulas (INDEX/MATCH, XLOOKUP, VLOOKUP, SUMPRODUCT, Percentiles, and other statistical functions). Use this skill whenever you need to populate Excel cells with advanced lookup or statistical formulas, or when calculating weighted averages in Excel.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Compose Chinese five-character and seven-character regulated verse under a strict modern Mandarin rule set. Use this Skill when the user asks for five-character or seven-character regulated verse, wants a poem written in a disciplined regulated-verse form, or wants an existing regulated poem revised to fit strict line-count, character-count, 平仄, rhyme, title quality, thematic coherence, and poetic depth requirements. This Skill uses modern Mandarin tones for 平仄, Mandarin finals for rhyme, allows polyphonic characters if any non-neutral reading fits, ignores neutral tone unless no non-neutral reading exists, and emphasizes a fitting title, unified theme, meaningful progression, balanced middle couplets, and a resonant conclusion.
Analyze geospatial data using geopandas with proper coordinate projections. Use when calculating distances between geographic features, performing spatial filtering, or working with plate boundaries and earthquake data.
Multi-hop search over enterprise artifacts to find key reviewers, approvers, feedback contributors, authors, product reports, competitor insights, and demo URLs. Prevents cross-product leakage and prevents treating meeting participants as reviewers.
Perform various data analysis on SEC 13-F and obtain some insights of fund activities such as number of holdings, AUM, and change of holdings between two quarters.
This skill includes search capability in 13F, such as fuzzy search a fund information using possibly inaccurate name, or fuzzy search a stock cusip info using its name.
Security considerations for Jackson JSON deserialization in Java applications. This skill covers common attack patterns such as the Empty Key ("") attack vector, polymorphic type handling, nested injection, and duplicate keys, along with their root causes and recommended mitigation strategies. It provides essential background knowledge and is highly useful for addressing related security vulnerabilities. It is always recommended to invoke this skill before working on relevant security fixes.
The gh CLI is GitHub's official command line tool for interacting with GitHub repositories, issues, pull requests, and more. When needs to interact with GitHub repositories, issues, pull requests, and more, use this skill.
Align Python version and repo-declared dependencies (requirements.txt / environment.yml) before installing packages for NLP research code reproduction.
Word document manipulation with python-docx - handling split placeholders, headers/footers, nested tables
Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
Guide for translating Python code to functional Scala style. Use when converting Python code involving numeric formatting, higher-order functions, decorators, closures, generators, or when aiming for idiomatic functional Scala with pattern matching, Option handling, and monadic operations.
Parse scheduling constraints from a email text.
A comprehensive PDF toolkit for advanced data extraction and document analysis. Beyond text and table extraction, this tool is optimized for visual layout reasoning: it can map graphical elements to coordinates (such as determining appointment times based on their position on a calendar timeline) and identify color-coded features (e.g., distinguishing high-priority blocks from flexible blue-colored entries). Use this skill when the task requires interpreting schedule layouts, calculating durations from visual spans, or resolving scheduling conflicts based on the spatial and color properties of a PDF document.
Build deterministic, verifiable data visualizations with D3.js (v6). Generate standalone HTML/SVG (and optional PNG) from local data files without external network dependencies. Use when tasks require charts, plots, axes/scales, legends, tooltips, or data-driven SVG output.
A good starting point for GLM calibration tasks. Use to inspect glm3.nml, confirm how GLM runs, and identify the relevant files before moving on to calibration and output evaluation.
Output-processing guidance for GLM tasks. Especially useful after glm-basics and glm-calibration when you need verifier-matching metrics from output.nc and a final /root/metrics.json.
invoke this skill when you need to perform database search for travel planning. This skill provides some useful pre-packaged tools to look up accommodations, attractions, cities, driving distance, flights, and restaurants from the bundled dataset.
Invoke this skill when performing travel planning. It defines a structured workflow for generating itineraries. Following this workflow is essential to ensure the final plan satisfies user requirements.
Extract key frames (I-frames) from video files using FFmpeg command line tool. Use this skill when the user needs to pull out keyframes, thumbnails, or important frames from MP4, MKV, AVI, or other video formats for analysis, previews, or processing.
Comprehensive command-line tools for modifying and manipulating images, such as resize, blur, crop, flip, and many more.
Count occurrences of an object in the image using computer vision algorithm.
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas
Manually invoked documentation reviewer. Do NOT load this skill automatically. Only load when the user explicitly runs /radar-doc-review. Reviews documentation files for correct format, style guide compliance, and content quality.
Automates the Karpathy LLM Wiki workflow: turns web, GitHub, and YouTube URLs into well-structured, citable, wikilinked pages with automatic linting and sourcing — invoke with /pin-llm-wiki
스타트업·1인 법인 대표용 경영 리포트 자동 생성 스킬. 월별 손익 추이, 현금흐름(일별 net), cash burn rate(최근 N개월 평균 순지출), 비용 구조 분석. 공식 재무제표와 별개로 의사결정용 가공 리포트 제공.
한국 종합소득세·법인세 신고 준비를 위한 서류 체크리스트 자동 생성 스킬. 개인사업자(일반·간이·면세)·프리랜서·1인 법인·겸업·성실신고확인대상 5가지 유형별로 필요 서류 목록을 제공하고, korean-jangbu-for에서 자동 생성 가능한 항목을 표시한다. 2026년 기준 기한표(토·일 자동 이연 반영) 포함 — 종소세 일반 2026-06-01, 성실신고 2026-06-30.
원본 재무 데이터(엑셀·은행 CSV·카드 내역 CSV·영수증 이미지·세금계산서 PDF·카드명세서 PDF)를 표준 거래내역 13개 필드로 변환하는 스킬. PaddleOCR 로컬 처리로 영수증·세금계산서·카드명세서에서 거래 자동 추출, Level 2 민감정보 마스킹 적용.
세무용 재무제표(재무상태표·손익계산서) 자동 생성 스킬. 국세청 표준계정과목 매핑, 일반기업회계기준(K-GAAP) 간소화 버전. 분류 완료된 거래내역을 기간 지정해 BS·PL로 집계하고 JSON·CSV 파일로 출력.
표준 거래내역에 계정과목을 매핑하는 스킬. 룰 기반 분류 우선(80%+), 실패 건만 LLM fallback(마스킹 뷰), 사용자 확인 루프. 한국 거래처 100개 시드 룰 포함, 내부 계정 ↔ 국세청 표준계정 이중 구조.
한국 스타트업·1인 법인 대표·프리랜서·개인사업자를 위한 장부 자동 생성 진입점 스킬. 호출 시 5개 하위 스킬(jangbu-import·jangbu-tag·jangbu-tax·jangbu-dash·jangbu-jongso)을 번호·문자 메뉴로 제시하고, 입력 즉시 해당 스킬 인터뷰로 직행한다. 엑셀·5대 은행 CSV·7대 카드사 명세서 PDF·영수증·세금계산서 지원, macOS Vision/PaddleOCR 로컬 처리, Level 2 민감정보 마스킹.
홈택스·은행·카드사 데이터를 자동 수집하기 위한 CODEF API 자격증명 발급·설정 가이드 스킬. 사용자가 직접 CODEF(developer.codef.io)에 무료 가입해 받은 Client ID/Secret을 로컬(macOS Keychain 또는 ~/.jangbu/credentials.env)에 저장. BYOK(Bring Your Own Key) 방식, 외부 서버 전송 없음. 2026년 4월 기준.
This skill should be used when the user asks to "build", "design", "scaffold", "architect", or "plan" any system, feature, service, app, agent, pipeline, connector, or tool — especially when the request is short, vague, or underspecified. It should also be used when the user asks to "review this architecture", "what am I missing", "ask me the right questions", "poke holes in this", or requests a design review before implementation. The skill interrogates the design silently across the relevant engineering domains (requirements, frontend, backend, data, API, security, infra, testing, observability, AI/LLM, mobile, product, cost, compliance, maintenance), resolves what the codebase and engineering defaults can answer, and surfaces only the decisions that require the user's authority.
Create beautifully designed travel guidebook PDFs from trip itineraries. End-to-end workflow from deep research to Playwright PDF export, featuring zero AI-generated images, Tabler Icons, inline SVG decorations, and Claude's warm parchment aesthetic. Use this skill whenever the user mentions 路书, 旅行指南, travel guidebook, 行程手册, trip planner, 自驾游攻略, itinerary book, 攻略, 出行指南, 旅行计划, 行程规划, or wants to turn trip notes into a printable guide. Also triggers for multi-day travel planning, route guides, road trip planners, 旅行攻略制作, 旅行PDF, or converting travel research into a professionally designed document.
模拟高三英语辅导老师，辅导英语阅读理解、完形填空、语法填空、写作等问题。重语言能力培养、做题技巧、词汇积累。当学生提出英语问题、请求讲解语法、分析阅读题、修改作文时使用。
模拟中国高三理科辅导老师，用渐进式教学方法辅导数学、物理、化学、生物等理科问题。当学生提出理科问题、请求讲解、说"不懂"、"教我"时使用。适用于高考备考、解题辅导、概念理解。
模拟高三通用技术辅导老师，辅导技术设计、结构分析、流程图、算法、简单编程等通用技术问题。重实践操作、设计思维、问题解决能力培养。当学生提出技术设计、结构优化、流程设计、算法问题时使用。
模拟高三文科辅导老师，用启发式教学方法辅导政治、历史、地理等文科综合问题。侧重理解、记忆、分析能力培养。当学生提出文科问题、请求讲解历史事件、地理现象、政治原理时使用。
模拟高三语文辅导老师，辅导现代文阅读、古诗文鉴赏、文言文翻译、作文写作等语文问题。重语感培养、文本解读、写作思维。当学生提出语文问题、请求分析课文、讲解古诗词、修改作文时使用。
>- Maintain openInvest's docs (docs/wiki chapters + docs/wiki/adr) under Google's Open Knowledge Format (OKF). Two jobs. (1) Teach agents to maintain docs the OKF way — every doc carries a small YAML frontmatter block as the single source of truth (type, title, tags, intent, schema_source, documents); schema details link to the authoritative code instead of being copied into prose; no more hand-maintained thousand-line markdown. (2) Look docs up fast — grep the literal term FIRST; only when grep is ambiguous (hits scattered across files / synonym mismatch / zero hits) run find_docs.py to rank the owning doc by frontmatter intent, or resolve a doc's schema_source to the real code. Trigger phrases — "which doc covers X", "find the schema for PortfolioResponse", "where is GET /api/holdings documented", "docs for verdict.risk_profile", "add OKF frontmatter to this doc", "lint the wiki", "scaffold a new ADR/chapter". --repo <path> ...).
Back up / restore openInvest's local state — memory/ (holdings, strategy, user profile, committee records, dream logs) + db/ (trade ledger, job run history, market-data cache) + .env (SMTP/API credentials) + user_profile.json. All of this data is .gitignore'd with no historical versions in git, so a single accidental overwrite (e.g. slipping and running some one-off migration/init script) means real data loss — no git revert available. **Proactive trigger scenarios** — "backup invest data / 备份一下 openInvest 的数据", "my holdings/strategy look wiped / 我的持仓/策略好像被清空了", "invest data is lost / invest 数据丢了", "restore invest backup / 恢复一下 invest 的备份", before any reinstall/migration of the openInvest deployment on this machine, or right before running an unfamiliar migration/init script (back up first, then act).
First-time openInvest installation and onboarding. **ONLY use when** user explicitly says "set up invest" / "init invest" / "帮我初始化 invest", OR when `invest` skill's `doctor` returns `status="needs_setup"`. **NOT for daily usage** — once onboarding is done, the `invest` skill takes over (portfolio viewing, committee analysis, buy/sell tracking). Wraps `run.sh init --from-stdin` with the canonical 5-question flow.
openInvest multi-asset AI investment committee — **daily use**. Read portfolio / live prices / strategy / decision history / adjust positions / run a 4-role LLM committee for an investment verdict. Supports any yfinance symbol (A-share / HK / US / ETF / crypto / commodities) and any currency. **Two paths** — (1) Coordinator, Claude Code spawns 4 subagents, saves DeepSeek tokens; (2) Direct, any agent (Codex / Hermes / OpenClaw / Cursor / Cline / plain script) runs `run.sh run_committee <SYM>` for a one-shot verdict. **Trigger scenarios** — "show portfolio / 看看我的持仓", "how is my P&L / 我现在涨了多少", "should I buy/sell X / 该不该买卖X", "analyze X / 分析一下X", "run committee on X / 跑委员会", "track AAPL / 跟踪苹果", "add/trim a position, log a trade / 加仓减仓记一笔". **First-time install uses a separate skill `invest-setup`** (switch to it when `doctor` returns `needs_setup`). Backend — longsizhuo/openInvest.
Claude Skills — questions
Answers built from the skills we actually parsed.