Use when implementing error handling in Rust. Provides thiserror for libraries and anyhow for binaries with proper context and error chaining. Triggers: error handling, thiserror, anyhow, Result, error types.
Batch-rename image files (jpg/png/heic/webp/etc.) in a folder using pattern "foldername_YYYYMMDDHHMMSSmmm.ext" based on macOS Finder "Date Added" (kMDItemDateAdded) with fallback to file creation time. Supports dry-run preview, conflict-safe suffixing (_001, _002), and undo via CSV log. Use when the user asks to rename photos/images by "date added/added time/添加时间" or wants timestamp-based naming with folder prefix.
Write Ruby and Rails code in DHH's distinctive 37signals style. Use this skill when writing Ruby code, Rails applications, creating models, controllers, or any Ruby file. Triggers on Ruby/Rails code generation, refactoring requests, code review, or when the user mentions DHH, 37signals, Basecamp, HEY, or Campfire style. Embodies REST purity, fat models, thin controllers, Current attributes, Hotwire patterns, and the "clarity over cleverness" philosophy.
Interacts with Bear note-taking app on macOS via X-Callback-URL. Use when user asks to create Bear notes, search notes, add text to notes, manage tags, capture web pages to Bear, or perform any other Bear note management tasks. Supports note creation, text appending, tag management, note search, and web page capture.
Build single-file web apps in markdown. No React. No build step. Just run.
Download and transcribe YouTube videos with speaker diarization and auto-chapters. Use when the user wants to transcribe a video URL, search YouTube for videos, list videos from a channel, search existing transcripts, list transcribed videos, read transcript content, or check if a video has already been transcribed.
Convert Markdown to professionally-formatted Word documents (.docx) using company templates. USE WHEN user wants to create Word document, convert markdown to docx, generate report, create professional document, OR mentions Word, docx, template formatting, document generation.
Create, read, and manipulate Excel spreadsheets (.xlsx). USE WHEN user wants to create spreadsheet, convert JSON/CSV to Excel, read Excel data, export to JSON/CSV, OR mentions Excel, xlsx, spreadsheet, workbook.
Sub-agent illustrator for blog content. Reads posts, analyzes narrative, designs illustration specs for MDX frontmatter. USE WHEN designing illustrations for blog posts, creating illustration frontmatter, adding visuals to articles, OR sub-agent needs to design blog imagery.
环境配置详细指南。当 aide env ensure 检测失败需要配置环境时使用。提供模块选择、配置设置、多项目场景处理等详细指导。由 /aide:setup 命令强制触发。
Guide developers through Elide's cross-language interop patterns - importing Python from TypeScript, passing functions across boundaries, and optimal interop patterns. Use when the user asks about mixing languages.
Save web pages as clean markdown files using a local parser with optional Jina.ai fallback. Use when you need to archive articles, blog posts, documentation, or any web content for later reading or building a local knowledge base.
Transcribe YouTube videos to text by downloading audio and using OpenAI's Whisper API. Use when you need transcripts stored in the files workspace.
Transcribe audio files to text using OpenAI's Whisper API with automatic chunking for large files. Use when you need to convert meeting recordings, podcasts, interviews, or any audio content to text.
Discover subdomains using DNS bruteforce, Certificate Transparency logs, and sitemap parsing. Use when you need to map a brand's digital footprint, perform security reconnaissance, or prepare for crawler policy analysis.
Design RESTful APIs and GraphQL schemas with proper conventions, documentation, and type safety. Use when planning API contracts, endpoints, or service interfaces.
Backup and sync claude-mem database via Git. Manually pull, push, or check status.
Build, debug, and develop LED matrix games for ESP32-S3 using PlatformIO, FastLED, and shared libraries. Use when working with ESP32 LED matrices, creating games, troubleshooting hardware issues, or setting up PlatformIO projects.
Create elite Claude skills with opinionated, best-in-class content. Use when: building skills with THE answer not catalogs, need evidence-based recommendations, or want decision frameworks over tutorials. Composes with example-skills:skill-creator.
Story file format conventions for .stories.md files including structure, headings, anchors, metadata, and tags. Auto-activates when editing stories.md files, creating story breakdowns, or managing story format. Use when you see story headings like [DOING], [BACKLOG], child stories (#1,
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.
Search the knowledge base for patterns, rules, concepts, examples, and anti-patterns. TRIGGERS: "search for [pattern]", "find [concept]", "what patterns", "how do I refactor", "best practices for", "code smells", "what rules apply to", "show me examples of". PROACTIVE: Use for any programming question that could be answered by extracted book knowledge. PREREQUISITE: Knowledge base must be built (references/knowledge/ exists with _search_index.json).
Format GDScript files using gdscript-formatter. Use when formatting .gd files, checking GDScript style compliance, or reordering code to match the official style guide. Requires gdscript-formatter binary in PATH.
Write user-facing documentation to docs/references/ or docs/guides/. Use after pattern research to create human-readable documentation separate from Claude's internal knowledge.
文档驱动开发工作流,确保 AI 严格遵循完整的开发流程:前置记录变更、任务追踪、系统性规划。适用于需要规范化代码改动、任务管理和工作流指导的场景。
Verify builds pass and format code after implementation
Extract text, tables, and form data from PDF documents for analysis and processing. Use when user asks to extract, parse, or analyze PDF files.
文档驱动开发工作流 skill,确保 AI 严格遵循完整的开发流程:前置记录变更、任务追踪、系统性规划。
Laravel queue and job management best practices. Use when implementing background tasks, email processing, or asynchronous operations.
每日内容策展系统 - 自动抓取 YouTube/Bilibili/小宇宙内容,AI 改写生成结构化摘要,归档到本地并同步飞书
Creates atomic git commits following Conventional Commits specification with detailed, well-structured messages. Analyzes changes and splits them into logical units. Use when committing code changes that need proper structure and comprehensive documentation (e.g., "commit my authentication changes" or "finished implementing search, time to commit").
Plan what to measure in mobile apps. Use when starting observability, prioritizing instrumentation, or asking "what should I track?"
Creates HTML slide presentations using a specific design system with dark gradient backgrounds, glass effects, and violet accents. Use when asked to create slides, presentations, or decks. Provides layouts for title slides, text slides, bullet lists, quotes, stats, columns, and image+text combinations.
This skill should be used when the user asks to "generate Rails code", "create a model", "create a controller", "add a migration", "write Rails tests", "set up background jobs", "configure Rails app", or discusses Rails conventions, best practices, ActiveRecord patterns, Hotwire/Stimulus, ViewComponent, RSpec testing, or Ruby on Rails development. Based on Evil Martians' AGENTS.md.
Extract the most meaningful, engaging clips from YouTube videos. Use when user provides a YouTube URL and wants to find highlights, best moments, controversial takes, or valuable segments. Supports specifying number of clips or topic focus.
Deterministic operations for managing clarification sessions.
Run a local microphone↔speaker voice dialog using OpenAI Realtime audio models (Node.js). Uses the `mic` and `speaker` npm packages. Pass a detailed prompt that includes all dialog context + what must be learned from the user.
Generate architecture diagrams from documentation maps, codebases, or system descriptions. Produces Mermaid, D2, or PlantUML diagrams. Use when user asks to visualize system architecture, create component diagrams, show dependencies, or generate diagrams from a SKILLS_MAP.md or similar documentation index.
動画/音声ファイルからSRT字幕を生成。Faster Whisperによるローカル音声認識で、ファイルパスまたはURL(YouTube等)から文字起こし・翻訳が可能。「文字起こし」「字幕生成」「transcribe」「SRT」などのリクエスト時に使用。
Provides universal workflow patterns and best practices for using the Attio MCP server. Complements the attio-workspace-schema skill with HOW-TO guidance for MCP tools and error prevention.
Generate use-case-specific Attio workflow skills from templates. Use when creating new skills for lead qualification, deal management, customer onboarding, or custom Attio workflows.
Automated security scanning and safe public repository workflows for the Second Brain project.
Checks and counts the number of open browser tabs. Use this skill when the user asks about browser tabs, tab count, open tabs, or how many tabs they have open. Activates with phrases like "how many tabs", "count tabs", "check tabs", "browser tabs", "open tabs". Works with Chrome, Chromium, and Firefox browsers on Linux systems.
Analyze and format multilingual Markdown documents by adding headers, bold formatting to key terms, and fixing bold rendering issues across all languages (Korean, English, Chinese, Japanese, etc.). Use when the user requests Markdown document structure improvement, header organization, or bold formatting fixes.
Debug production issues and errors systematically. Use when investigating bugs, errors, crashes, or unexpected behavior.
코드베이스를 분석하여 기술 문서를 생성하는 스킬. MD/PDF/PPT 출력 형식 선택 가능. 워크플로우 다이어그램, 주요 함수 설명을 포함한 문서를 생성한다. 사용 시점: (1) 코드 인수인계 문서 필요시, (2) 주니어 개발자/기획자를 위한 시스템 설명 문서 필요시, (3) 프로젝트 온보딩 문서 작성시
Use when generating frontend UI specifications for Next.js web applications. Creates complete UI spec documents covering layout design, responsive breakpoints, component specifications, state management with Zustand, and mock data planning. Outputs spec/design/ui.spec.md with working functionality using local JSON storage.
This skill should be used when the user asks to "find all console.log calls", "find functions without error handling", "find async functions missing try-catch", "remove all debug statements", "find deprecated API usage", "find classes that extend X", "find React components using useState", "bulk refactor function calls", "find all imports of X", "replace all X with Y across codebase", or any find/replace code patterns where text search misses formatting or argument variations.
Routes queries to appropriate data sources (vectordb, web_search, direct_llm) and selects collections to search. Use when analyzing user queries, determining search strategy, or when the user mentions routing, collections, or data source selection.
Sets up bombfork projects by validating GitHub remote configuration and creating standardized issue size labels (size-s, size-m, size-l). Use when user asks to setup a project, configure GitHub labels, or initialize project management structure.
Automated multi-agent orchestrator that spawns CLI subagents in parallel, coordinates via MCP Memory, and monitors progress
Quality assurance specialist for security, performance, accessibility, and comprehensive testing
Build Language Server Protocol (LSP) servers in Rust using tower-lsp, lsp-types, and related crates. Use when implementing IDE features like completion, diagnostics, hover, or go-to-definition for any language or file format.
Expert knowledge for building Language Server Protocol (LSP) implementations in Rust or TypeScript. Use when creating language servers, implementing LSP features like completion, diagnostics, hover, or go-to-definition, choosing LSP crates/libraries, or working with editor integrations via LSP.
Expert knowledge for implementing syntax highlighting in Rust using syntect, tree-sitter, or autumnus. Use when building code highlighters, documentation tools, static site generators, or CLI tools that need syntax coloring.
Expert knowledge for xxHash, an extremely fast non-cryptographic hash algorithm. Use when implementing checksums, hash tables, bloom filters, content deduplication, cache keys, or data integrity verification. Covers XXH32, XXH64, XXH3 variants with language-specific guidance for Rust (xxhash-rust, twox-hash), TypeScript (hash-wasm, xxhash-wasm, @node-rs/xxhash), Python, Go, and Java.
Expert knowledge for working with `pulldown-cmark`, a high-performance CommonMark parser for Rust using a pull-parser architecture. Supports GitHub Flavored Markdown (GFM) extensions including tables, task lists, strikethrough, and autolinks.
Validate code quality before merge. Runs tests, coverage, linting, type checking, and security scans. Blocks merge if thresholds not met. Use before any PR merge.
Syncs retrospective data to GitHub Project board and generates MD documentation. Use at the end of a retrospective session.
Generate changelog and release notes from commits. Parses conventional commits, groups by type, and creates formatted release documentation.
Execute test suite and report results. Detects test framework, runs tests, calculates coverage, and formats results for quality gate.
Specialized skill for building and troubleshooting agents using the DeepAgents framework. Use this skill when users need to develop agents with planning capabilities, file system tools, or subagent delegation for complex, multi-step tasks. This skill covers creating deep agents, configuring middleware, implementing persistent memory, setting up human-in-the-loop approval flows, and troubleshooting common errors in Python.
Run Uni-Mol/Uni-Mol2/Uni-Mol Docking workflows in this repo: env setup, downloading weights, using unimol_tools (pip), finetuning or inference with unicore/torchrun, docking v2 demos, and quick troubleshooting. Trigger when working with the Uni-Mol repository or unimol_tools tasks (property prediction, representation, docking, conformation, pocket/molecule finetune, Uni-Mol2 models).
End-to-end guidance for compiling, running, and debugging the GPUMD/nep executables. Use when handling GPU molecular dynamics with GPUMD, preparing model.xyz/run.in, training or validating NEP potentials (nep.in, train.xyz, test.xyz), analyzing outputs (thermo.out, loss.out, nep.txt), or resolving CUDA/build/runtime issues.
Use when working with the Atomsk command-line tool to create, convert, or modify atomic structures (formats like LAMMPS, VASP/POSCAR, QE, XSF/CFG), apply options (duplicate, orient, orthogonal-cell, reduce-cell, add/remove atoms), and run special modes (create, merge, polycrystal, interactive). Ideal for building supercells, introducing defects, format conversion, or preparing inputs for MD/DFT codes.
Use this skill to set up and run DeePTB (both SKTB and E3TB workflows).
Phonopy usage & development helper for finite-displacement phonon jobs, IFC/NAC handling, band/DOS/thermal properties, CLI & setting.conf templates, VASP/QE/ABINIT interfaces, plotting utilities, and repo maintenance (tests, docs, formatting). Trigger when working with phonopy runs, interpreting FORCE_SETS/phonopy.yaml/BORN, or contributing to this repo.
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
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
Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns, file paths, content patterns), enforcement levels (block, suggest, warn), hook mechanisms (UserPromptSubmit, PreToolUse), session tracking, and the 500-line rule.
Safe hover and animation patterns that don't cause layout issues. Use when implementing hover effects, transitions, or animations on cards and interactive elements.
Use to EXTRACT and DOCUMENT styles from an EXISTING codebase. Analyzes tailwind.config, CSS variables, and components to generate STYLE-GUIDE.md. NOT for creating new styles - use /create-style-guide command for that. NOT for creative design direction - use frontend-design skill for that.
This skill should be used when the user asks to "add partner logos", "style client logos", "make logos uniform", "add company logos section", "trusted by logos", or needs to display multiple brand logos in a consistent, professional style on light or dark backgrounds.
Spotify Web APIとの統合に関する専門知識。アルバムやプレイリスト管理のためのOAuth、エンドポイント、レート制限、エラーハンドリングについて。
Implements real-time audience voting and scoring systems for debates. Use this skill when building vote collection, tallying, result visualization, or integrating voting with the gamification system.
Automate iOS distribution with Fastlane for TestFlight beta delivery and App Store releases. Use when setting up `fastlane/` in an Xcode project, creating or editing lanes (e.g. `beta`, `release`, `appstore`), configuring App Store Connect API keys / signing, uploading builds via `pilot` / `upload_to_testflight`, submitting releases via `deliver` / `upload_to_app_store`, or debugging common Fastlane build/signing/upload failures in CI.
Comprehensive Rust development guidelines based on 6 months of code reviews. Use when writing Rust code, debugging Rust issues, or reviewing Rust PRs. Covers error handling, file I/O safety, type safety patterns, performance optimization, common footguns, and fundamental best practices. Perfect for both new and experienced Rust developers working on CLI tools, hooks, or production code.
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
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
Build and refresh a cached "who am I" user profile from connected apps (Microsoft 365, HubSpot, Linear) to give assistants reliable signed-in context.
Generate images with Google Gemini (Nano Banana Pro) via CLI helper
Unified distributor lookups across Dicker Data NZ and Ingram Micro
Configure a local dev server for access from Tailscale-connected devices.
Guide human PO through manual acceptance testing. Optional - use when PO wants manual verification before merge.
Interact with JIRA Cloud to fetch tickets, search using JQL, and list projects. Use when users ask about JIRA issues, tickets, projects, or need to query JIRA data. Requires JIRA_EMAIL, JIRA_API_TOKEN, and JIRA_DOMAIN environment variables.
SQLite 数据库工具集,用于操作 SQLite 数据库文件。支持 .db、.sqlite、.sqlite3、.vscdb 等常见扩展名。无需额外安装依赖,使用 Python 内置 sqlite3 模块。支持 Windows、macOS 和 Linux 平台。
MySQL 数据库工具集,用于连接数据库实例、列出所有表、查看表结构、执行 SQL 查询等操作。当需要操作 MySQL 数据库、查询数据、分析表结构时使用此技能。支持通过命令行参数指定 host、port、user、password、database 等连接信息,可代替 mysql mcp 服务使用。支持 Windows、macOS 和 Linux 平台。
Build and package code for multiple languages. Use when: - Building executables ("Build my Rust app into an executable") - Creating Docker images ("Build a Docker image for my app") - Setting up CI/CD ("Configure build pipeline for CI") - Packaging for distribution ("Package my Python app for distribution") - Cross-platform builds ("Build for Windows, Linux, and macOS") - Native compilation ("Build native image with GraalVM") Supports: Rust (cargo, cross), Java (Maven/Gradle + GraalVM), Python (uv, PyInstaller), Node.js (pkg), TypeScript (esbuild), and Docker multi-stage builds.
Execute theme release workflow. Syncs themes to sum-themes repo and creates namespaced tags. Use for "Release theme_a" requests.
Control a headless browser with 98% token reduction compared to Playwright MCP and Dev Browser. Uses batch execution, minimal responses, and efficient HTML formatting.
Use when user provides a Figma design URL to implement - extracts design specs via MCP tools, implements Angular component, adds Storybook stories, and VERIFIES implementation visually by comparing screenshots (project)
Automated evaluation framework for Vibe Coding outputs using TRACE methodology (Traceability, Robustness, Adherence, Completeness, Efficiency). Use when requirements.md, spec.md, and repository code are available for evaluation, or when code quality assessment, requirements traceability, API compliance checking, or comprehensive Vibe Coding evaluation is requested. Includes Python scripts for automated analysis of requirements mapping, API compliance, code quality metrics, and report generation.
Context-efficient screenshot capture and analysis. Use when needing to see, analyze, or interact with screen content. Dispatches haiku subagent to analyze full-res image, returns summary + thumbnail to preserve context. Triggers on "take a screenshot", "screenshot", "what's on my screen", "capture screen", "show me the screen", "analyze this window".
Use before claiming code is "done", after implementation, before commit. Checks requirements coverage, concurrency, error handling, resources, boundaries, and security.
Validates and configures all dependencies required for the THE BOOK. This is a STANDALONE skill that runs BEFORE plugin workflows begin. It checks for Python, build tools, CMake, JUCE, pluginval, and the thebook CLI command, optionally installing missing dependencies with user approval. Configuration is saved to .claude/system-config.json for use by other skills. Use when user mentions setup, installation, dependencies, missing tools, or when SessionStart hook detects configuration issues.
This skill uses mode-based workflow loading to optimize context window usage. After detecting which mode applies (New Plugin vs Improvement), the appropriate workflow reference is loaded on-demand.
Context-aware session startup. Displays banner, last checkpoint, uncommitted changes warning. Auto-runs after SessionStart hook.
Search MacWhisper meeting transcriptions by keywords, title, and date range. Use when searching for meetings, finding transcripts, or looking for specific content in meeting recordings.
Read MacWhisper meeting transcription by session ID. Returns the full transcript in Markdown format with metadata and timestamps. Use when you need to retrieve or view the content of a specific meeting.
Gemini API를 활용하여 연구제안서 캡션을 4K 인포그래픽 이미지로 변환. 사용자가 캡션 이미지 생성, 그림 생성, 인포그래픽 만들기, 마크다운 캡션을 이미지로 변환해달라고 요청할 때 사용.