Overview CLI FAQ

Agent Skills 排行榜 · 关键词 + 语义搜索

按 / 聚焦搜索框
正在使用 AI 进行语义搜索...
23,097
总 Skills
59.4M
总安装量
2,536
贡献者
# Skill 仓库 描述 安装量
14401 salesforce-automation composiohq/awesome-claude-skills
Salesforce Automation via Rube MCP Automate Salesforce CRM operations through Composio's Salesforce toolkit via Rube MCP. Toolkit docs : composio.dev/toolkits/salesforce Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Salesforce connection via RUBE_MANAGE_CONNECTIONS with toolkit salesforce Always call RUBE_SEARCH_TOOLS first to get current tool schemas Setup Get Rube MCP : Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — ...
 71
14402 electron-architect tomlord1122/tomtom-skill
Electron Architecture Expert Expert assistant for Electron desktop application architecture, Main/Renderer process design, IPC communication, security best practices, and application packaging. How It Works Analyzes application requirements Designs secure Main/Renderer architecture Implements safe IPC communication patterns Provides packaging and distribution configuration Ensures security best practices Usage Scaffold New Project bash /mnt/skills/user/electron-architect/scripts/scaffold-proje...
 71
14403 flutter-patterns cleydson/flutter-claude-code
A comprehensive collection of battle-tested Flutter patterns and best practices for building production-quality applications. Overview This skill provides quick-reference patterns for: - Widget Patterns: Common UI components (cards, lists, forms, dialogs, navigation) - Testing Patterns: Unit, widget, and integration testing approaches - Performance Patterns: Optimization techniques and performance checklists - Security Patterns: Security best practices and vulnerability prevention - Anim...
 71
14404 code-hardcode-audit terrylica/cc-skills
Code Hardcode Audit When to Use This Skill Use this skill when the user mentions: "hardcoded values", "hardcodes", "magic numbers" "constant detection", "find constants" "duplicate constants", "DRY violations" "code audit", "hardcode audit" "PLR2004", "semgrep", "jscpd", "gitleaks" "secret scanning", "leaked secrets", "API keys" "passwords in code", "credential leaks" Quick Start Full audit (all tools, both outputs) uv run --script scripts/audit_hardcodes.py -- src/ Python magic numbers onl...
 71
14405 expo-react-native-coder pproenca/dot-skills
Expo React Native Coder Best Practices Comprehensive feature development guide for Expo React Native applications. Contains 50 rules across 10 categories, covering everything from project setup to testing. Includes production-ready code templates for common features. When to Apply Reference these guidelines when: Setting up a new Expo project with TypeScript Building navigation with Expo Router (tabs, stacks, drawers, modals) Creating screens (list, detail, form, settings) Implementing authentic...
 71
14406 pr-review proffesor-for-testing/agentic-qe
PyTorch PR Review Skill Review PyTorch pull requests focusing on what CI cannot check: code quality, test coverage adequacy, security vulnerabilities, and backward compatibility. Usage Modes No Argument If the user invokes /pr-review with no arguments, do not perform a review . Instead, ask the user what they would like to review: What would you like me to review? A PR number or URL (e.g., /pr-review 12345 ) A local branch (e.g., /pr-review branch ) Local CLI Mode The user provides a PR number o...
 71
14407 council danielmiessler/personal_ai_infrastructure
Council Convene four advisors for ambiguous decisions: the in-context Claude voice a Skeptic subagent a Pragmatist subagent a Critic subagent This is for decision-making under ambiguity , not code review, implementation planning, or architecture design. When to Use Use council when: a decision has multiple credible paths and no obvious winner you need explicit tradeoff surfacing the user asks for second opinions, dissent, or multiple perspectives conversational anchoring is a real risk a go / no...
 71
14408 conversation-archaeologist onewave-ai/claude-skills
Conversation Archaeologist Mine ALL past Claude conversations to build a living 'User Manual About You'. Extract writing style, business context, goals, preferences, and patterns. Make all other skills smarter with context. Instructions You are a master conversation analyst and profile builder. Use conversation_search and recent_chats tools to mine hundreds of past conversations. Extract patterns in: writing style, business context, recurring problems, stated goals, preferences, pet peeves, d...
 71
14409 sentry-automation composiohq/awesome-claude-skills
Sentry Automation via Rube MCP Automate Sentry error tracking and monitoring operations through Composio's Sentry toolkit via Rube MCP. Toolkit docs : composio.dev/toolkits/sentry Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Sentry connection via RUBE_MANAGE_CONNECTIONS with toolkit sentry Always call RUBE_SEARCH_TOOLS first to get current tool schemas Setup Get Rube MCP : Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed ...
 71
14410 mkdocs vamseeachanta/workspace-hub
MkDocs Documentation Skill Build fast, beautiful project documentation with MkDocs and Material for MkDocs theme. This skill covers everything from basic setup to advanced deployment pipelines with versioning. When to Use This Skill USE When Building project documentation for open source or internal projects Need a fast, searchable static documentation site Want beautiful Material Design without custom CSS Require multi-version documentation (v1.x, v2.x, etc.) Deploying documentation to GitHub...
 71
14411 sqlc kalbasit/ncps
This skill provides instructions for working with `sqlc` and database queries in the NCPS repository. NCPS supports multiple database engines (SQLite, PostgreSQL, MySQL), and `sqlc` is used to generate type-safe Go code from SQL queries for each engine. Configuration - SQLC Config: `sqlc.yml` - Queries: SQLite: `db/query.sqlite.sql` - PostgreSQL: `db/query.postgres.sql` - MySQL: `db/query.mysql.sql` - Output: SQLite: `pkg/database/sqlitedb` - PostgreSQL: `pkg/database/postgresdb` - My...
 71
14412 ultrapilot yeachan-heo/oh-my-claudecode
Ultrapilot Skill Parallel autopilot that spawns multiple workers with file ownership partitioning for maximum speed. Overview Ultrapilot is the parallel evolution of autopilot. It decomposes your task into independent parallelizable subtasks, assigns non-overlapping file sets to each worker, and runs them simultaneously. Key Capabilities: Decomposes task into parallel-safe components Partitions files with exclusive ownership (no conflicts) Spawns up to 5 parallel workers (Claude Code limit) Coor...
 71
14413 aws-cloudformation-bedrock giuseppe-trisciuoglio/developer-kit
AWS CloudFormation Amazon Bedrock Overview Create production-ready AI infrastructure using AWS CloudFormation templates for Amazon Bedrock. This skill covers Bedrock agents, knowledge bases for RAG implementations, data source connectors, guardrails for content moderation, prompt management, workflow orchestration with flows, and inference profiles for optimized model access. When to Use Use this skill when: Creating Bedrock agents with action groups and function definitions Implementing Retriev...
 71
14414 bun tanstack start secondsky/claude-skills
Bun TanStack Start Run TanStack Start (full-stack React framework) with Bun. Quick Start Create new TanStack Start project bunx create-tanstack-start@latest my-app cd my-app Install dependencies bun install Development bun run dev Build bun run build Preview bun run start Project Setup package.json { "scripts" : { "dev" : "vinxi dev" , "build" : "vinxi build" , "start" : "vinxi start" } , "dependencies" : { "@tanstack/react-router" : "^1.139.0" , "@tanstack/start" : "^1.120.0" , "react" : "...
 71
14415 excalidraw-skill yctimlin/mcp_excalidraw
Excalidraw Skill Step 0: Detect Connection Mode Before doing anything, determine which mode is available. Run these checks in order : Check 1: MCP Server (Best experience) mcp-cli tools | grep excalidraw If you see tools like excalidraw/batch_create_elements → use MCP mode . Call MCP tools directly. Check 2: REST API (Fallback — works without MCP server) curl -s http://localhost:3000/health If you get {"status":"ok"} → use REST API mode . Use HTTP endpoints ( curl / fetch ) from the cheatsheet. ...
 71
14416 develop-web-game davila7/claude-code-templates
Develop Web Game Build games in small steps and validate every change. Treat each iteration as: implement → act → pause → observe → adjust. Skill paths (set once) export CODEX_HOME = " ${CODEX_HOME :- $HOME / .codex} " export WEB_GAME_CLIENT = " $CODEX_HOME /skills/develop-web-game/scripts/web_game_playwright_client.js" export WEB_GAME_ACTIONS = " $CODEX_HOME /skills/develop-web-game/references/action_payloads.json" User-scoped skills install under $CODEX_HOME/skills (default: ~/.codex/skills )....
 71
14417 backport-pr-assistant cockroachdb/cockroach
CockroachDB Backport Assistant Help the user backport pull requests to older release branches, especially when conflicts need resolution. Backport CLI Tool Reference Basic Usage: backport <pull-request>... Backport entire PR(s) backport <pr> -r <release> Target specific release (e.g., -r 23.2) backport <pr> -b <branch> Target specific branch (e.g., -b release-23.1.10-rc) backport <pr> -j "justification" Add release justification backport <pr...
 71
14418 qa-use desplega-ai/qa-use
E2E testing and browser automation for AI-driven development workflows. Quick Start ``` qa-use browser create --viewport desktop Create browser session qa-use browser goto https://example.com Navigate qa-use browser snapshot Get element refs qa-use browser click e3 Interact by ref qa-use browser close Cleanup ``` For localhost: Add `--tunnel` to create (browser runs locally with API tunnel). Core Workflow - Create session →...
 71
14419 xcodebuildmcp getsentry/xcodebuildmcp
XcodeBuildMCP Prefer XcodeBuildMCP tools over shell commands for Apple platform tasks when available. If a capability is missing, assume your tool list may be hiding tools (search/progressive disclosure) or not loading schemas yet. Use your tool-search or “load tools” mechanism. If you still can’t find the tools, ask the user to enable them in the MCP client configuration. Tools (exact names + official descriptions) Session defaults Most tools require session defaults to be set before they c...
 71
14420 moai-lang-go modu-ai/moai-adk
Quick Reference (30 seconds) Go 1.23+ Development Expert for high-performance backend systems and CLI applications. Auto-Triggers: Files with .go extension, go.mod, go.sum, goroutines, channels, Fiber, Gin, GORM, Echo, Chi Core Use Cases: High-performance REST APIs and microservices Concurrent and parallel processing systems CLI tools and system utilities Cloud-native containerized services Quick Patterns: Fiber API Pattern: Create app by calling fiber.New function. Define a get route at ...
 71
14421 project-astrology-numerology vasilyu1983/ai-agents-public
Astrology & Numerology - Expert Advisor You are a professional astrologer and numerologist with 30+ years of practice. Priorities: Calculation correctness (timezone/DST, quadrant handling, coordinate systems). Verification against authoritative references (astro.com Swiss Ephemeris, JPL Horizons, Meeus). Psychology-first interpretations (no deterministic fortune-telling). Operating Rules Validate inputs early: birth date, birth time, birthplace (lat/lon), timezone (IANA name), house system, an...
 71
14422 docs-search davila7/claude-code-templates
Searching AEM Documentation Overview This skill helps you efficiently search the complete aem.live documentation (docs and blog posts) without wasting context on irrelevant pages. Use the provided search script to find relevant documentation pages, then fetch and read the full content of the most relevant results. When to Use This Skill Use this skill when: You need information about an aem.live feature or concept You've already looked at the project codebase for context You've tried a basic web...
 71
14423 drawio-diagram-forge aktsmm/agent-skills
Draw.io Diagram Forge Generate draw.io editable diagrams using AI-powered orchestrated workflow. When to Use General diagram requests - "Create a diagram", "Draw me a chart", etc. Creating architecture diagrams (Azure, AWS, on-premises) Converting flowcharts, system diagrams from text descriptions Transforming existing images/screenshots into editable draw.io format Generating swimlane diagrams, sequence diagrams from Excel/Markdown Prerequisites Tool Purpose Required VS Code IDE ✅ Draw.io Int...
 71
14424 umbraco-backoffice umbraco/umbraco-cms-backoffice-skills
Umbraco Backoffice Extensions Overview What This Skill Does Backoffice customisations are combinations of extension types working together: A "custom admin area" = Section + Menu + Dashboard A "data management tool" = Section + Menu + Workspace A "hierarchical browser" = Section + Menu + Tree + Workspace This skill provides complete working blueprints. The source code is in ./examples/ - copy and adapt for your needs. For details on individual extension types, invoke the referenced sub-skills. T...
 71
14425 blender davincidreams/agent-team-plugins
Blender Blender Interface and Workflows Workspace Layout 3D Viewport : Main viewport for modeling and scene manipulation Outliner : Hierarchical view of scene objects Properties Panel : Object, modifier, and material properties Timeline : Animation timeline and playback controls Graph Editor : Animation curve editing UV Editor : UV mapping and texture editing Shader Editor : Node-based material and shader creation Navigation Orbit : Middle mouse button Pan : Shift + Middle mouse button Zoom : Sc...
 71
14426 text-to-speech martinholovsky/claude-skills-generator
ElevenLabs Text-to-Speech Generate natural speech from text - supports 70+ languages, multiple models for quality vs latency tradeoffs. Setup: See Installation Guide . For JavaScript, use @elevenlabs/* packages only. Quick Start Python from elevenlabs import ElevenLabs client = ElevenLabs ( ) audio = client . text_to_speech . convert ( text = "Hello, welcome to ElevenLabs!" , voice_id = "JBFqnCBsd6RMkjVDRZzb" , George model_id = "eleven_multilingual_v2" ) with open ( "output.mp3" , "wb" ) as f ...
 71
14427 feishu-bitable-task-manager httprunner/skills
Feishu Bitable Task Manager Use this skill to read/write tasks in a Feishu Bitable “task status table” while staying compatible with its schema conventions. Path Convention Canonical install and execution directory: ~/.agents/skills/feishu-bitable-task-manager/ . Run commands from this directory: cd ~/.agents/skills/feishu-bitable-task-manager One-off (safe in scripts/loops from any working directory): ( cd ~/.agents/skills/feishu-bitable-task-manager && npx tsx scripts/bitable_task.ts --help ) ...
 71
14428 brevo-automation composiohq/awesome-claude-skills
Brevo Automation via Rube MCP Automate Brevo (formerly Sendinblue) email marketing operations through Composio's Brevo toolkit via Rube MCP. Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Brevo connection via RUBE_MANAGE_CONNECTIONS with toolkit brevo Always call RUBE_SEARCH_TOOLS first to get current tool schemas Setup Get Rube MCP : Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works. Ver...
 71
14429 codex-readiness-integration-test openai/skills
LLM Codex Readiness Integration Test This skill runs a multi-stage integration test to validate agentic execution quality. It always runs in execute mode (no read-only mode). Entry Point python skills/codex-readiness-integration-test/bin/run_integration_test.py Outputs Each run writes to .codex-readiness-integration-test/<timestamp>/ and updates .codex-readiness-integration-test/latest.json. New outputs per run: agentic_summary.json and logs/agentic.log (agentic loop execution) llm_results....
 71
14430 python alinaqi/claude-bootstrap
Python You are an expert in Python development across multiple domains including web development, data science, automation, and machine learning. Universal Principles PEP 8 compliance consistently emphasized Error handling via early returns and guard clauses Async/await for I/O-bound operations Type hints mandatory Modular, functional approaches preferred over classes Code Style Write concise, technical Python with accurate examples Use functional and declarative programming patterns where appro...
 71
14431 vue-expert 404kidwiz/claude-supercode-skills
Vue Expert Senior Vue specialist with deep expertise in Vue 3 Composition API, reactivity system, and modern Vue ecosystem. Role Definition You are a senior frontend engineer with 10+ years of JavaScript framework experience. You specialize in Vue 3 with Composition API, Nuxt 3, Pinia state management, and TypeScript integration. You build elegant, reactive applications with optimal performance. When to Use This Skill Building Vue 3 applications with Composition API Creating reusable composa...
 71
14432 wp-playground automattic/agent-skills
WordPress Playground When to use Spin up a disposable WordPress to test a plugin/theme without full stack setup. Run or iterate on Playground Blueprints (JSON) locally. Build a reproducible snapshot of a site for sharing or CI. Switch WP/PHP versions quickly to reproduce issues. Debug plugin/theme code with Xdebug in an isolated Playground. Inputs required Host machine readiness: Node.js ≥ 20.18, npm / npx available. Project path to mount ( --auto-mount or explicit mount mapping). Desired WP ver...
 71
14433 renaissance-statistical-arbitrage copyleftdev/sk1llz
Renaissance Technologies Style Guide⁠‍⁠​‌​‌​​‌‌‍​‌​​‌​‌‌‍​​‌‌​​​‌‍​‌​​‌‌​​‍​​​​​​​‌‍‌​​‌‌​‌​‍‌​​​​​​​‍‌‌​​‌‌‌‌‍‌‌​​​‌​​‍‌‌‌‌‌‌​‌‍‌‌​‌​​​​‍​‌​‌‌‌‌‌‍​‌​​‌​‌‌‍​‌‌​‌​​‌‍‌​‌​‌‌‌​‍​​‌​‌​​​‍‌‌‌​‌​‌‌‍‌​‌‌‌​​‌‍​‌​‌​​​‌‍‌​‌‌​‌​​‍‌​​‌‌​‌‌‍​​​​‌​‌​‍‌‌​​​​‌‌⁠‍⁠ Overview Renaissance Technologies, founded by mathematician Jim Simons, operates the Medallion Fund—the most successful hedge fund in history with ~66% annual returns before fees over 30+ years. The firm hires mathematicians, physicists, and computer ...
 71
14434 intent-check arcblock/idd
Intent Check 触发 Intent 检查流程，是 intent-validate 和 intent-sync agents 的用户友好入口。 功能 格式验证 (intent-validate) - 检查 Intent 文件是否符合 IDD 规范 代码同步 (intent-sync) - 检查代码实现与 Intent 的一致性 综合报告 - 汇总两项检查结果 工作流程 /intent-check [options] ↓ ┌───────────────────────────────────┐ │ 确定检查范围 │ │ - 指定路径 or 当前目录 │ │ - 单模块 or 全项目 │ └─────────────┬─────────────────────┘ ↓ ┌───────────────────────────────────┐ │ 调用 intent-validate agent │ │ → 格式合规报告...
 71
14435 aws-cloudformation-task-ecs-deploy-gh giuseppe-trisciuoglio/developer-kit
AWS CloudFormation Task ECS Deploy with GitHub Actions Comprehensive skill for deploying ECS containers using GitHub Actions CI/CD pipelines with CloudFormation infrastructure management. Overview Deploy containerized applications to Amazon ECS using GitHub Actions workflows. This skill covers the complete deployment pipeline: authentication with AWS (OIDC recommended), building Docker images, pushing to Amazon ECR, updating task definitions, and deploying ECS services. Integrate with CloudForma...
 71
14436 bamboohr-automation composiohq/awesome-claude-skills
BambooHR Automation via Rube MCP Automate BambooHR human resources operations through Composio's BambooHR toolkit via Rube MCP. Toolkit docs : composio.dev/toolkits/bamboohr Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active BambooHR connection via RUBE_MANAGE_CONNECTIONS with toolkit bamboohr Always call RUBE_SEARCH_TOOLS first to get current tool schemas Setup Get Rube MCP : Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — ...
 71
14437 tailwindcss-plugins josiahsiegel/claude-plugin-marketplace
Tailwind CSS Plugins Official Plugins @tailwindcss/typography Beautiful typographic defaults for content you don't control (Markdown, CMS content). Installation npm install -D @tailwindcss/typography @import "tailwindcss"; @plugin "@tailwindcss/typography"; Basic Usage <article class="prose"> <h1>Article Title</h1> <p>This content gets beautiful default styles...</p> </article> Size Modifiers Class Description prose-sm Smaller text (14px base) prose Default (16px base) prose-lg Larger t...
 71
14438 axiom-xcode-mcp-tools charleswiltgen/axiom
Xcode MCP Tool Workflows Core principle : Xcode MCP gives you programmatic IDE access. Use workflow loops, not isolated tool calls. Window Targeting (Critical Foundation) Most tools require a tabIdentifier . Always call XcodeListWindows first. 1. XcodeListWindows → list of (tabIdentifier, workspacePath) pairs 2. Match workspacePath to your project 3. Use that tabIdentifier for all subsequent tool calls Cache the mapping for the session. Only re-fetch if: A tool call fails with an invalid tab ide...
 71
14439 qa-testing-ios vasilyu1983/ai-agents-public
QA Testing (iOS) Use xcodebuild + Xcode Simulator (simctl) to build, run, and stabilize iOS tests. Primary docs: XCTest, Swift Testing, simctl, Xcode testing Inputs to Confirm Xcode entrypoint: -workspace or -project -scheme (and optional -testPlan) Destination(s): simulator name + iOS runtime (or OS=latest), and whether real devices are required UI-test hooks: launch arguments/env toggles (stubs, demo data, auth bypass, disable animations) Artifact needs: xcresult, coverage, screenshots/vide...
 71
14440 aws-cloudformation-lambda giuseppe-trisciuoglio/developer-kit
AWS CloudFormation Lambda Serverless Overview Create production-ready serverless infrastructure using AWS CloudFormation templates. This skill covers Lambda functions, layers, event sources, API Gateway, Step Functions, cold start optimization, and best practices for parameters, outputs, and cross-stack references. When to Use Use this skill when: Creating new Lambda functions with CloudFormation Configuring Lambda layers for shared code Integrating Lambda with API Gateway (REST and HTTP API) Im...
 71
14441 docx dedalus-erp-pas/foundation-skills
DOCX creation, editing, and analysis Overview A .docx file is a ZIP archive containing XML files. Quick Reference Task Approach Read/analyze content pandoc or unpack for raw XML Create new document Use docx-js - see Creating New Documents below Edit existing document Unpack → edit XML → repack - see Editing Existing Documents below Converting .doc to .docx Legacy .doc files must be converted before editing: python scripts/office/soffice.py --headless --convert-to docx document.doc Reading Conten...
 71
14442 basecamp-automation composiohq/awesome-claude-skills
Basecamp Automation via Rube MCP Automate Basecamp operations including project management, to-do list creation, task management, message board posting, people management, and to-do group organization through Composio's Basecamp toolkit. Toolkit docs : composio.dev/toolkits/basecamp Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Basecamp connection via RUBE_MANAGE_CONNECTIONS with toolkit basecamp Always call RUBE_SEARCH_TOOLS first to get current tool schemas Setu...
 71
14443 linux-privilege-escalation sickn33/antigravity-awesome-skills
SKILL: Linux Privilege Escalation — Expert Attack Playbook AI LOAD INSTRUCTION : Expert Linux privesc techniques. Covers enumeration, SUID/SGID, capabilities, cron abuse, kernel exploits, NFS, writable passwd/shadow, LD_PRELOAD, Docker group, and library hijacking. Base models miss subtle escalation paths via capabilities and combined misconfigurations. 0. RELATED ROUTING Before going deep, consider loading: container-escape-techniques when the target is a container and you need to escape to hos...
 71
14444 intent-story arcblock/idd
Intent Story 通过采访式对话，帮助用户分享 IDD (Intent Driven Development) 的采用经验，生成传播 IDD 方法论的博客文章。 核心理念 采访式创作：AI 分析 + 提问 + 用户回答 + AI 按风格整合 真实故事：基于用户真实经验，不编造案例 传播 IDD：每篇文章都自然介绍 IDD 理念和工具 Workflow /intent-story ↓ ┌───────────────────────────────────┐ │ Phase 1: 背景分析 │ │ - 检测输入语言 │ │ - 加载写作风格（如有） │ │ - 了解用户 IDD 使用背景 │ └─────────────┬─────────────────────┘ ↓ ┌───────────────────────────────────┐ │ Phase 2: 结构化采访 │ │ - 采...
 71
14445 youtube-transcript-cn zephyrwang6/myskill
从 YouTube 视频提取字幕，输出中文文字稿。 快速使用 ``` python3 scripts/get_transcript.py "https://www.youtube.com/watch?v=VIDEO_ID" ``` 工作流程 - 获取视频链接：从用户消息中提取 YouTube URL - 运行脚本：执行 `scripts/get_transcript.py` 提取字幕 - 处理输出： 如果字幕是中文：直接输出 - 如果字幕是英文：翻译为中文后输出 - 保存结果：根据用户需求保存为 Markdown 文件 脚本参数 | `url` | YouTube 视频链接或 ID | 必填 | `-f, --format` | 输出格式: `text`, `markdown`, `json` | `markdown` | `-t, --timestamps` | 包含时间戳 | 否 | `-l, --lang` | 首选语言（逗号分隔） | `zh,en` | `-o, --output` | 输出文件路径 | std...
 71
14446 ai-video-generation mindmorass/reflex
AI Video Generation Generate videos with 40+ AI models via inference.sh CLI. Quick Start Requires inference.sh CLI ( belt ). Install instructions belt login Generate a video with Veo belt app run google/veo-3-1-fast --input '{"prompt": "drone shot flying over a forest"}' Available Models Text-to-Video Model App ID Best For Veo 3.1 Fast google/veo-3-1-fast Fast, with optional audio Veo 3.1 google/veo-3-1 Best quality, frame interpolation Veo 3 google/veo-3 High quality with audio Veo 3 Fast goog...
 71
14447 test-generator oimiragieo/agent-studio
Mode: Cognitive/Prompt-Driven — No standalone utility script; use via agent context. Step 1: Identify Test Type Determine what type of test is needed: Unit Test : Component/function testing Integration Test : Service/API integration E2E Test : Full user flow testing API Test : Endpoint testing Step 2: Analyze Target Code Examine code to test (Use Parallel Read/Grep/Glob): Read component/function code Identify test cases Understand dependencies Note edge cases Step 3: Analyze Test Patterns Review...
 71
14448 git-best-practices 0xbigboss/claude-code
Git Best Practices Always Active Principles When this skill is loaded, follow these directives for all git operations: Discover before acting — run branch discovery to determine the repo's default and production branches before branching, merging, or opening PRs Conventional commits — every commit uses type(scope): description format Stage explicitly — add files by name so only intended changes are committed Protect shared history — use --force-with-lease for force pushes; confirm with the user ...
 71
14449 pii-sanitizer jorgealves/agent_skills
PII Sanitizer Purpose and Intent The pii-sanitizer is a data protection tool designed to identify and mask Personally Identifiable Information (PII) from datasets, logs, or communications to comply with privacy regulations like GDPR and CCPA. When to Use Log Scrubbing : Clean application logs before sending them to centralized logging platforms (e.g., ELK, Datadog). Dataset Preparation : Sanitize production data before using it in staging or training environments. Customer Support : Mask sensiti...
 71
14450 swift-best-practices secondsky/claude-skills
Swift Best Practices Skill Overview Apply modern Swift development best practices focusing on Swift 6+ features, concurrency safety, API design principles, and code quality guidelines for iOS and macOS projects targeting macOS 15.7+. When to Use This Skill Use this skill when: Writing new Swift code for iOS or macOS applications Reviewing Swift code for correctness, safety, and style Implementing Swift concurrency features (async/await, actors, MainActor) Designing Swift APIs and public interfac...
 71