AI Skills Hub - Browse 180,000+ Agent Skills

Crie novas Agent Skills para GitHub Copilot a partir de prompts ou duplicando este template. Use quando solicitado "criar uma skill", "fazer uma nova skill", "scaffold uma skill" ou ao construir capacidades de IA especializadas com recursos agrupados. Gera arquivos SKILL.md com frontmatter correto, estrutura de diretorio e pastas opcionais scripts/references/assets.

Posts content to WeChat Official Account (微信公众号) via API or Chrome CDP. Supports article posting (文章) with HTML, markdown, or plain text input, and image-text posting (图文) with multiple images. Use when user mentions "发布公众号", "post to wechat", "微信公众号", or "图文/文章".

Compresses images to WebP (default) or PNG with automatic tool selection. Use when user asks to "compress image", "optimize image", "convert to webp", or reduce image file size.

Knowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and sequential image generation. Use when user asks to create "知识漫画", "教育漫画", "biography comic", "tutorial comic", or "Logicomix-style comic".

AI image generation with OpenAI, Google and DashScope APIs. Supports text-to-image, reference images, aspect ratios. Sequential by default; parallel generation available on request. Use when user asks to generate, create, or draw images.

电竞经理游戏的日志与错误处理系统。管理前后端日志记录、错误码系统、日志监控台、错误引导弹窗。当需要添加日志、调试问题、修改错误处理、查看日志文件或修改日志/错误相关功能时使用此技能。

按本仓库 FastAPI 三层架构实现功能增量（routers/services/models），遵守异步 I/O、Pydantic v2、统一日志与错误返回。用于新增/修改 API 端点、CRUD、业务流程、数据模型时。

Search academic papers across Semantic Scholar, CrossRef, and DBLP. Returns titles, abstracts, citations, and BibTeX.

Search arXiv papers by keyword, category, or author. Returns abstracts, PDF links, and BibTeX entries.

Manage Apple Calendar events on macOS using AppleScript. Create, list, search, and delete calendar events.

Display HTML content on connected Moltbot nodes (Mac app, iOS, Android).

Edit existing PowerPoint presentations by replacing content in specified shapes using SlideSpeak API

GCP secrets, .env setup, starting servers, and troubleshooting local development

Improve recipes with cooking techniques, timing optimization, equipment-specific instructions, and household dietary preferences.

Weekly review: aggregate daily logs, compute completion rate and time allocation, generate summary, list carry-over items. Triggers: '周总结', '本周回顾', 'weekly review', '运行 weekly-review'.

Weekly plan generator: create day-by-day breakdown from monthly goals and last week's carry-over. Triggers: '生成本周计划', '周规划', 'weekly plan', '运行 weekly-plan'.

Daily todo manager: generate today's plan, reschedule items, add ad-hoc tasks. Triggers: '生成今天的计划', 'today plan', '把X移到周三', '加一项', '明天要', '运行 daily-todo'. (Marking completion is handled by daily-log.)

Planning sync: check consistency between daily/weekly/monthly plans, list discrepancies, batch update after user confirmation. Triggers: '同步规划', '检查一致性', 'planning sync', '运行 planning-sync'.

Extract and read Claude conversation JSONL files with composable filters (discovery: rubber-duck). Evaluate at rubber-duck or at any point in the sesssion when task requires reading conversation history, verifying tool outputs, or auditing session behavior. Use instead of raw Read/grep on ~/.claude/projects/*.jsonl files.

Provides a step-by-step workflow for analyzing and explaining WorldQuant BRAIN alpha expressions. Use this when the user asks to explain a specific alpha expression, what a datafield does, or how operators work together. Includes steps for data field lookup, operator analysis, and external research.

Implements WorldQuant Brain features from an idea markdown file. Downloads dataset and generates alpha expressions defined in the idea.

Verify the syntax of an alpha expression irrespective of field existence. Use when checking if an alpha expression string is syntactically valid, has correct function arguments, and properly matched parentheses.

Read and write the Windows clipboard (text, images, file lists).

Transactions. Reference when using this Prisma feature.

Prisma Accelerate Users

Run `~/code/dotfiles/bin/council.ts review` to perform a multi-model review, evaluate findings, fix valid issues (with tests when possible), add clarifying comments for invalid findings, then run required checks. Use before PR creation or when the user asks for a deep review.

Guide feature development with structured investigation, design, and TDD implementation workflow.

华为云 CodeArts 流水线自动化测试专家。支持一键执行、批量并发、实时监控、自动重试与报告生成。

Use when writing character development scenes or planning character growth - provides real-time guidance on character arcs, transformation tracking, and growth consistency

Keep PennyGPT-STARFRAME-Internal changes aligned with BOUNDARIES.md and AGENTS.md governance. Use when modifying trust-layer architecture, cross-repo interfaces, packaging docs, or any change that could blur cognitive vs hardware execution boundaries.

Enforce memryx-mx3-python-shim preflight gates and documentation lockstep. Use before PRs to run required validation profiles and keep README.md, docs/PROJECT_SCOPE.md, and docs/SCOPE_TRACKER.md synchronized with shipped behavior.

Run Windows-local packaging and release validation for VRM-Sandbox. Use when building distributables, fixing packaging regressions, or validating installer/portable outputs without introducing CI workflows.

Discover, triage, and prioritize Codex skills for a repository or workspace. Use when auditing existing skills, identifying missing capabilities, mapping skills to repo workflows, and generating a safe install/admission plan.

Persistent hierarchical memory storage for cross-session knowledge. This skill defines the memory tree structure under .claude/memory/ — a branching folder hierarchy organized by domain > topic > subtopic. Use this skill whenever reading, writing, browsing, or organizing the memory tree. Triggers on: /memory, /memory-status, any direct reference to 'the memory tree', or when other skills (remember/recall) need to interact with storage.

This guide helps users configure Play.fun API credentials for Claude Code integration.

Comprehensive guide for BlazeMeter Private Locations, including Radar Agent, installation (Docker, Kubernetes, Helm), configuration, management, and troubleshooting. Use when working with Private Locations for (1) Installing agents (Docker, Kubernetes, Helm Chart), (2) Configuring Radar Agent for API Monitoring, (3) Setting up environment variables and certificates, (4) Managing private locations and agents, (5) Troubleshooting installation and connectivity issues, or any other Private Location tasks.

Comprehensive troubleshooting guide for BlazeMeter, covering API Monitoring, Performance Testing, general issues, integrations, and security. Use when troubleshooting for (1) API Monitoring issues (Radar Agent auth, SSL certificates, debug tests), (2) Performance Testing issues (high response time, 500 errors, partial load, tests not starting), (3) General issues (delete non-empty project, forbidden domains, Chrome Extension export failures), (4) Integration issues (New Relic reporting), (5) Security issues (Apache Log4j2 vulnerability), (6) Support requests and tickets, or any other troubleshooting tasks.

Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns.

Provides code relationship context from the StreamRAG incremental code graph. Use when asked about code dependencies, what calls a function, affected files, impact analysis, or when working with complex multi-file changes.

Reflective turn-based review of your own PR — explore aspects in dialog, land findings in a work item

Read all PR review feedback and create an implement-ready work item to address it

Execute a spec's plan with a knowledge-aware agent team — spawns workers, tracks progress, captures architectural findings

Extract user context and knowledge from any chatbot export (ChatGPT, Claude, Gemini, or generic conversation logs) into a universal portable format. Version 4.0 adds semantic deduplication, better hyphenated name handling, time decay for confidence scoring, and topic merging. Use when users want to migrate their chatbot history, import conversation context from another AI, extract their profile from chat exports, or preserve their accumulated knowledge. Triggers on phrases like "import my ChatGPT history", "extract my context", "migrate my conversations", "export my memory", or "transfer my profile from [chatbot]".

Convert universal portable user context (from chatbot-memory-extractor) into platform-specific memory formats including Claude preferences, Claude memories, system prompts, Notion pages, Notion databases, and Google Docs. Version 4.0 adds Notion export and Google Docs HTML export. Use when users want to import their context, set up their profile, configure Claude with their history, apply extracted memories, or export to Notion or Google Docs. Triggers on phrases like "import my context", "configure Claude with my history", "apply my extracted memories", "export to Notion", "create Google Doc from context".

Explore codebase, analyze code, review code, assess code quality, evaluate architecture, find callers, measure impact, search semantically, generate documentation, navigate index. Triggers on: dependencies, what calls, who calls, what uses, callers, impact, blast radius, code architecture, find function, search code, explore codebase, analyse code, review code, review documentation, document, create documentation, evaluate, assess, index structure, list symbols, list functions, list classes, how many files, how many lines, codebase stats, inventory.

Analyze and validate meta tags on web pages. Use when users ask to check meta tags, verify SEO tags, audit page titles, check Open Graph tags, verify canonical URLs, or analyze social sharing tags. Detects missing title, description issues, duplicate tags, and Open Graph problems.

Perform accessibility audit on web pages. Use when users ask to check accessibility, audit WCAG compliance, verify ARIA usage, check color contrast, audit keyboard navigation, or analyze screen reader compatibility. Detects ARIA issues, focus problems, contrast issues, and semantic HTML violations.

Analyze and validate links and buttons on web pages. Use when users ask to check links, verify button hrefs, find empty links, detect javascript:void links, find broken navigation, or audit clickable elements. Detects empty href, javascript:void(0), hash-only links, missing href attributes, and non-accessible buttons.

Analyze and validate HTML heading hierarchy (H1-H6) on web pages. Use when users ask to check headings structure, verify H1 presence, analyze SEO heading hierarchy, find heading issues, or audit page structure. Detects missing H1, multiple H1s, skipped levels, empty headings, and hierarchy violations.

Analyze and validate forms on web pages. Use when users ask to check form accessibility, verify form labels, audit input fields, check form validation, or analyze form UX. Detects missing labels, invalid input types, accessibility issues, and validation problems.

Analyze performance-related HTML issues on web pages. Use when users ask to check page performance, audit resource loading, verify lazy loading, check preload hints, or analyze render-blocking resources. Detects missing optimizations, large resources, render-blocking issues, and Core Web Vitals problems.

Analyze and validate images on web pages. Use when users ask to check image alt tags, verify image accessibility, find missing alt attributes, audit image SEO, or check image optimization. Detects missing alt, empty alt, decorative images without proper markup, oversized images, and missing dimensions.

Automate browser interactions using agent-browser CLI for web scraping, testing, and UI automation. Use when the user asks to interact with websites, capture screenshots, fill forms, scrape data, test web pages, or automate browser tasks.

Patterns and best practices for Effect-TS in the Nuclom codebase. Use when writing API routes, services, or any code using Effect-TS. Covers Effect.gen, error handling, services, layers, and common pitfalls.

Provide progress updates without external services or API keys

Get agent progress updates on iPhone while away from laptop

Playwright MCPを使用したブラウザ自動化。ページ操作、スクリーンショット、フォーム入力のパターン集

malletリンターのルールと設定を適用。コードレビュー・品質チェック時に使用

Wayland環境でのGUI自動化。スクリーンショット取得、テキスト入力、クリップボード操作のパターン集

Creates Scheduled Jobs in Windows Task Scheduler

Comprehensive UX evaluation meta-skill. Use when conducting UI/UX audits, accessibility reviews, user flow analysis, responsive testing, or interaction design evaluation.

Compress verbose prompts & context before LLM processing. This skill should be used when input exceeds 1500 tokens, contains redundant phrasing, or includes unnecessary context. Reduces tokens by 40-60%.

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

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

時間情報（Chronolocation）を扱うスキル。カレンダー変換（エチオピア、ネパール、ペルシャ、イスラム暦）、タイムゾーン変換、太陽位置計算を行う。「この日付をグレゴリオ暦に変換」「ペルシャ暦1401年の日付は？」「影の角度から時刻を特定」などのリクエストで使用。

画像からOSINT情報を抽出するスキル。画像のメタデータ（EXIF、GPS座標、撮影日時）の解析、OCRによるテキスト抽出、画像内の特徴分析を行う。「この画像の撮影場所は？」「画像からテキストを読み取って」「EXIFデータを確認して」などのリクエストで使用。

YouTube動画からOSINT情報を抽出するスキル。動画メタデータ取得、字幕ダウンロード、サムネイル取得、特定時間のフレーム抽出を行う。「この動画の情報を調べて」「字幕をダウンロードして」「サムネイルを取得して」などのリクエストで使用。

動画からOSINT情報を抽出するスキル。フレーム抽出、メタデータ解析、動画内テキストのOCRを行う。「この動画からフレームを抽出して」「動画のメタデータを確認して」「動画内のテキストを読み取って」などのリクエストで使用。

Update a pull request description. Use when asked to update PR description, edit PR body, or refresh PR details.

Query STRING API for protein-protein interactions (59M proteins, 20B interactions). Network analysis, GO/KEGG enrichment, interaction discovery, 5000+ species, for systems biology.

功能完整的計算病理學工具包。用於進階全切片影像（WSI）分析，包括多重免疫螢光（CODEX、Vectra）、細胞核分割、組織圖構建，以及在病理資料上訓練機器學習模型。支援 160+ 種切片格式。若僅需從 H&E 切片進行簡單的圖磚擷取，histolab 可能更為簡便。

Comprehensive biosignal processing toolkit for analyzing physiological data including ECG, EEG, EDA, RSP, PPG, EMG, and EOG signals. Use this skill when processing cardiovascular signals, brain activity, electrodermal responses, respiratory patterns, muscle activity, or eye movements. Applicable for heart rate variability analysis, event-related potentials, complexity measures, autonomic nervous system assessment, psychophysiology research, and multi-modal physiological signal integration.

使用 AI 模型（FLUX、Gemini）生成或編輯影像。用於一般用途的影像生成，包括照片、插圖、藝術品、視覺素材、概念藝術，以及任何非技術圖表或示意圖的影像。如需流程圖、電路圖、路徑圖和技術圖表，請改用 scientific-schematics 技能。

查詢 Open Targets 平台以獲取靶點-疾病關聯、藥物靶點發現、可藥性/安全性資料、遺傳學/組學證據、已知藥物，用於治療靶點識別。

Google 量子運算框架。適用於針對 Google Quantum AI 硬體、設計雜訊感知電路或執行量子特性實驗時使用。最適合 Google 硬體、雜訊建模和低階電路設計。若使用 IBM 硬體請用 qiskit；若進行含自動微分的量子機器學習請用 pennylane；若進行物理模擬請用 qutip。

Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems.

使用 OpenAlex 資料庫查詢和分析學術文獻。此技能應在搜尋學術論文、分析研究趨勢、尋找特定作者或機構的著作、追蹤引用、發現開放取用出版物，或對 2.4 億篇以上學術著作進行文獻計量分析時使用。用於文獻搜尋、研究產出分析、引用分析和學術資料庫查詢。

系統發育樹工具包（ETE）。樹操作（Newick/NHX）、演化事件偵測、直系同源/旁系同源、NCBI 分類、視覺化（PDF/SVG），用於系統發育基因組學。

生產就緒的強化學習演算法（PPO、SAC、DQN、TD3、DDPG、A2C），具有類似 scikit-learn 的 API。用於標準 RL 實驗、快速原型設計和文件完善的演算法實作。最適合搭配 Gymnasium 環境的單一代理 RL。對於高效能平行訓練、多代理系統或自訂向量化環境，請改用 pufferlib。

查詢 Reactome REST API 進行路徑分析、富集、基因-路徑對應、疾病路徑、分子互動、表現分析，用於系統生物學研究。

Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.

用於處理 DICOM（醫學數位影像傳輸協定）檔案的 Python 函式庫。當讀取、寫入或修改 DICOM 格式的醫學影像資料、從醫學影像（CT、MRI、X 光、超音波）提取像素資料、匿名化 DICOM 檔案、處理 DICOM 詮釋資料和標籤、將 DICOM 影像轉換為其他格式、處理壓縮的 DICOM 資料，或處理醫學影像資料集時使用此技能。適用於涉及醫學影像分析、PACS 系統、放射科工作流程和醫療影像應用的任務。

用於代謝體學的質譜相似性和化合物鑑定。用於比較質譜、計算相似性分數（餘弦、修正餘弦）以及從質譜庫識別未知化合物。最適合代謝物鑑定、質譜匹配、質譜庫搜尋。對於完整的 LC-MS/MS 蛋白質體學流程，請使用 pyopenms。

Complete mass spectrometry analysis platform. Use for proteomics workflows feature detection, peptide identification, protein quantification, and complex LC-MS/MS pipelines. Supports extensive file formats and algorithms. Best for proteomics, comprehensive MS data processing. For simple spectral comparison and metabolite ID use matchms.

開放量子系統的量子物理模擬庫。適用於研究主方程、Lindblad 動力學、退相干、量子光學或腔量子電動力學。最適合物理研究、開放系統動力學和教育模擬。不適用於基於電路的量子計算——請使用 qiskit、cirq 或 pennylane 進行量子演算法和硬體執行。

基於擴散的分子對接。從 PDB/SMILES 預測蛋白質-配體結合姿態、信心分數、虛擬篩選，用於基於結構的藥物設計。不適用於親和力預測。

與廠商無關的實驗室自動化框架。用於控制多種設備類型（Hamilton、Tecan、Opentrons、微孔盤讀取器、幫浦）或需要跨不同廠商統一程式設計時使用。最適合複雜工作流程、多廠商設置、模擬。對於僅使用 Opentrons 官方 API 的協定，opentrons-integration 可能更簡單。

Deep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training.

NGS analysis toolkit. BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks), for ChIP-seq, RNA-seq, ATAC-seq visualization.

High-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational genomics and machine learning applications.

查詢 openFDA API 以獲取藥物、醫療器材、不良事件、召回、法規提交（510k、PMA）、物質識別（UNII）等資訊，用於 FDA 法規資料分析和安全研究。

Python library for working with geospatial vector data including shapefiles, GeoJSON, and GeoPackage files. Use when working with geographic data for spatial analysis, geometric operations, coordinate transformations, spatial joins, overlay operations, choropleth mapping, or any task involving reading/writing/analyzing vector geographic data. Supports PostGIS databases, interactive maps, and integration with matplotlib/folium/cartopy. Use for tasks like buffer analysis, spatial joins between datasets, dissolving boundaries, clipping data, calculating areas/distances, reprojecting coordinate systems, creating maps, or converting between spatial file formats.

使用此技能處理和分析超過可用 RAM 的大型表格資料集（數十億列）。Vaex 擅長核外 DataFrame 操作、惰性求值、快速聚合、大資料的高效視覺化，以及大型資料集上的機器學習。當使用者需要處理大型 CSV/HDF5/Arrow/Parquet 檔案、對海量資料集執行快速統計、建立大資料視覺化，或建構無法放入記憶體的機器學習管線時，請應用此技能。

Therapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits, molecular oracles, for therapeutic ML and pharmacological prediction.

材料科學工具包。晶體結構（CIF、POSCAR）、相圖、能帶結構、態密度、Materials Project 整合、格式轉換，用於計算材料科學。

使用 Data Commons 進行工作，這是一個提供程式化存取全球來源公共統計資料的平台。當處理人口統計資料、經濟指標、健康統計、環境資料或透過 Data Commons 提供的任何公共資料集時使用此技能。適用於查詢人口統計、GDP 數據、失業率、疾病盛行率、地理實體解析以及探索統計實體之間的關係。