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...
21,834
总 Skills
40.3M
总安装量
2,459
贡献者
# Skill 仓库 描述 安装量
14501 skill-integrator jwynia/agent-skills
Skill Integrator: Surface Skills Where They're Needed You bridge the gap between installed skills and agent awareness. Your role is to analyze project context, score installed skills for relevance, and generate actionable trigger-based guidance that gets inserted into CLAUDE.md or AGENTS.md. Core Principle Skills only help when agents know to reach for them. A hundred installed skills are useless if the agent doesn't know when each one applies. This skill transforms a silent inventory into activ...
 60
14502 erk-exec dagster-io/erk
erk exec Guide Quick Start Before running any erk exec command, check syntax with -h : erk exec < command > -h Commands by Workflow PR Review Operations When addressing PR review comments or resolving threads: Command Purpose get-pr-review-comments Fetch review comments (use --pr N ) resolve-review-thread Resolve a thread (use --thread-id ) reply-to-discussion-comment Reply to discussion comment get-pr-discussion-comments Fetch discussion comments Typical workflow: erk exec get-pr-review-comment...
 60
14503 figma-reader delexw/claude-code-misc
Figma Reader Read Figma design context via the Figma MCP server. Arguments $ARGUMENTS[0] — Figma link, design prompt copied from Figma, or attached UI design image (optional) $ARGUMENTS[1] — (optional) Output directory for persisting the design context. Defaults to .implement-assets/figma When invoked by the orchestrator (e.g. implement ), $ARGUMENTS[1] is provided. When used standalone, it defaults to .implement-assets/figma . Execution Codebase check : Verify this is a frontend project — follo...
 60
14504 capacitor-splash-screen cap-go/capacitor-skills
Splash Screen in Capacitor Configure and customize splash screens for iOS and Android. When to Use This Skill User wants to customize splash screen User needs splash screen assets User wants animated splash User has splash screen issues Quick Start Install Plugin bun add @capacitor/splash-screen bunx cap sync Basic Configuration // capacitor.config.ts import type { CapacitorConfig } from '@capacitor/cli' ; const config : CapacitorConfig = { plugins : { SplashScreen : { launchShowDuration : 2000 ...
 60
14505 pr-operations dagster-io/erk
PR Operations Skill Core Rule CRITICAL: Use ONLY erk exec Commands for PR Thread Operations ❌ DO NOT use raw gh api calls for thread operations ❌ DO NOT use gh pr commands directly for thread resolution ✅ ONLY use erk exec commands listed below The erk exec commands handle thread resolution correctly. Raw API calls only reply without resolving. Quick Reference Command Purpose Key Point get-pr-review-comments Fetch unresolved review threads Returns threads with line info get-pr-discussion-comment...
 60
14506 social-media-content-repurposer nicepkg/ai-workflow
Social Media Content Repurposer Transform content across platforms with platform-specific optimization. When to Use This Skill Activate when the user: Asks to "turn this into a Twitter thread" Wants to adapt content for different platforms Needs to create multiple social posts from one source Says "repurpose this blog post" Wants platform-specific content variations Mentions LinkedIn, Twitter/X, Instagram, Facebook, TikTok Needs hashtag suggestions Instructions Analyze Source Content Ident...
 60
14507 openai-image-vision zhayujie/chatgpt-on-wechat
OpenAI Image Vision Analyze images using OpenAI's GPT-4 Vision API. The model can understand visual elements including objects, shapes, colors, textures, and text within images. Setup This skill requires at least one of the following API keys (OpenAI is preferred when both are set): OpenAI (preferred): env_config(action="set", key="OPENAI_API_KEY", value="your-key") LinkAI (fallback): env_config(action="set", key="LINKAI_API_KEY", value="your-key") Optional: Set custom API base URL: env_config (...
 60
14508 review-implementing mhattingpete/claude-skills-marketplace
Review Feedback Implementation Systematically process and implement changes based on code review feedback. When to Use Provides reviewer comments or feedback Pastes PR review notes Mentions implementing review suggestions Says "address these comments" or "implement feedback" Shares list of changes requested by reviewers Systematic Workflow 1. Parse Reviewer Notes Identify individual feedback items: Split numbered lists (1., 2., etc.) Handle bullet points or unnumbered feedback Extract distin...
 60
14509 rivetkit-typescript rivet-dev/skills
Build high-performance, long-lived, in-memory processes on Rivet's actor runtime. Use this skill whenever HTTP endpoints, databases, or queues no longer meet the requirements for AI agents, realtime collaboration, workflow orchestration, or geo-distributed data. What To Do If You Get Stuck If something is not working as intended or you are stuck, prompt the user to join the [Rivet Discord](https://rivet.dev/discord) or file an issue on the [Rivet GitHub](https://github.com/rivet-dev/rivet) to...
 60
14510 system diagnostician daffy0208/ai-dev-standards
System Diagnostician Analyze project health and recommend capabilities using Codex-powered system understanding Purpose Performs comprehensive project health analysis to diagnose issues, identify missing capabilities, and recommend improvements. Uses Codex to understand project structure, detect anti-patterns, analyze dependencies, and suggest optimal capability additions based on project goals. When to Use New project onboarding: "What does this project need?" Health checks: "Is this project fo...
 60
14511 google-ads-report openclaudia/openclaudia-skills
Google Ads Report Pull campaign, keyword, and conversion data from the Google Ads API. Prerequisites Requires: GOOGLE_CLIENT_ID and GOOGLE_CLIENT_SECRET (OAuth) GOOGLE_ADS_DEVELOPER_TOKEN (apply at https://ads.google.com/home/tools/manager-accounts/ ) GOOGLE_ADS_CUSTOMER_ID (the account ID, format: XXX-XXX-XXXX , passed without dashes) GOOGLE_ADS_LOGIN_CUSTOMER_ID (if using a manager account, the manager account ID) Set in .env , .env.local , or ~/.claude/.env.global . Getting an Access Token S...
 60
14512 umbraco-entity-create-option-action umbraco/umbraco-cms-backoffice-skills
Umbraco Entity Create Option Action What is it? Entity Create Option Actions add customizable options when creating entities. These options appear in a create options dialog when the "Create" entity action is selected, allowing users to choose between different creation methods or paths. This enables extensibility where other developers can add their own creation options to existing workflows. Documentation Always fetch the latest docs before implementing: Main docs : https://docs.umbraco.com/um...
 60
14513 disk-usage ukgovernmentbeis/inspect_ai
Disk Usage Skill Use this skill to analyze disk space and filesystem usage on Linux systems. Quick Start Run the included script for a disk usage overview: ./scripts/diskinfo.sh Manual Commands Filesystem Overview df -h - Disk space usage for all mounted filesystems (human-readable) df -i - Inode usage (number of files) lsblk - Block device tree (disks, partitions) mount - Currently mounted filesystems Directory Size Analysis du -sh /path - Total size of a directory du -h --max-depth=1 /path - S...
 60
14514 muapi-platform samuraigpt/generative-media-skills
⚙️ MuAPI Platform Utilities Setup and polling utilities for the muapi.ai platform. Configure your API key, verify connectivity, and poll for async generation results. Available Scripts Script Description setup.sh Configure API key, show config, test key validity check-result.sh Poll for async generation results by request ID Quick Start Save your API key bash setup.sh --add-key "YOUR_MUAPI_KEY" Show current configuration bash setup.sh --show-config Test API key validity bash setup.sh --test ...
 60
14515 tech-lead lotosbin/claude-skills
Tech Lead Skill Overview You are an expert Technical Lead bridging architecture and implementation. You ensure code quality, provide technical guidance, and create implementation plans. Progressive Disclosure Load phases as needed: Phase When to Load File Code Review Reviewing code changes phases/01-code-review.md Implementation Creating implementation plans phases/02-implementation.md Refactoring Planning refactoring work phases/03-refactoring.md Core Principles ONE FILE per response - Neve...
 60
14516 legal-compliance travisjneuman/.claude
No SKILL.md available for this skill. View on GitHub
 60
14517 orval orval-labs/orval
Orval OpenAPI Best Practices Comprehensive guide for generating type-safe TypeScript clients from OpenAPI specifications using Orval. Contains 42 rules across 8 categories, prioritized by impact to guide automated configuration, client generation, and testing setup. When to Apply Reference these guidelines when: Configuring Orval for a new project Setting up OpenAPI-based TypeScript client generation Integrating React Query, SWR, or Vue Query with generated hooks Creating custom mutators for...
 60
14518 dual-channel-watchexec-notifications terrylica/cc-skills
Dual-Channel Watchexec Notifications Send reliable notifications to both Telegram and Pushover when watchexec detects file changes or process crashes. Core Pattern watchexec wrapper script → detect event → notify-script → Telegram + Pushover wrapper.sh - Monitors process and detects restart reasons watchexec --restart -- python bot.py On event, call: notify-script.sh <reason> <exit_code> <watchexec_info_file> <crash_context> Critical Rule: Format Differences Telegram: HTML mode ONLY ME...
 60
14519 google-apps-script henkisdabro/wookstar-claude-code-plugins
Google Apps Script Build automation scripts for Google Sheets and Workspace apps. Scripts run server-side on Google's infrastructure with a generous free tier. What You Produce Apps Script code pasted into Extensions > Apps Script Custom menus, dialogs, sidebars Automated triggers (on edit, time-driven, form submit) Email notifications, PDF exports, API integrations Workflow Step 1: Understand the Automation Ask what the user wants automated. Common scenarios: Custom menu with actions (report ge...
 60
14520 smart-docs sopaco/deepwiki-rs
You are an expert software architect and technical writer. Your task is to generate comprehensive, professional codebase documentation similar to Litho/deepwiki-rs, but using Claude Code's native capabilities without external LLM API calls. Core Principles - Progressive Analysis: Analyze codebases incrementally, not all at once - Pattern Recognition: Identify common architectural patterns - C4 Model: Structure documentation following C4 model levels - Mermaid Diagrams: Use Mermaid for all ...
 60
14521 creative-writer tatat/agents-playground
Creative Writer Create engaging creative content across various formats and styles. Capabilities Write short stories and flash fiction Compose poetry in various forms Generate creative concepts and ideas Adapt writing style to different genres Provide writing prompts and exercises Input Format Content type (story, poem, script, concept) Genre/style (fantasy, mystery, humor, literary) Tone (dark, uplifting, whimsical, serious) Length (flash, short, medium) Theme or prompt (optional) Any constra...
 60
14522 traffic-validator shipshitdev/library
Traffic Validator - Traffic Secrets Scorecard Assess traffic strategy against Traffic Secrets principles. Expose scattered traffic efforts and unclear audience strategy. Brunson's Principle: "Your customers are already congregating. Find the watering holes." When This Activates User asks "validate my traffic plan" User asks "is my audience strategy right" User says "I can't get enough traffic" User asks "should I do paid or organic" User mentions Dream 100 The Framework Dream 100 → Work In or...
 60
14523 typescript-expert oimiragieo/agent-studio
TypeScript Expert You are an advanced TypeScript expert with deep, practical knowledge of type-level programming, performance optimization, and real-world problem solving based on current best practices. When invoked: If the issue requires ultra-specific expertise, recommend switching and stop: Deep webpack/vite/rollup bundler internals → typescript-build-expert Complex ESM/CJS migration or circular dependency analysis → typescript-module-expert Type performance profiling or compiler interna...
 60
14524 druid autumnsgrove/groveengine
The Druid 🌿 The druid is not an animal. The druid is the keeper who walks among them, who knows every creature by name, who understands what niche each fills in the forest. When a new animal is needed — when the ecosystem has a gap, a role unfulfilled — the druid performs the ritual of creation. They commune with the existing creatures, walk through the grove to find where the new one belongs, envision its form, and summon it into existence. The druid creates what the forest needs. When to Activ...
 60
14525 ralph civitai/civitai
ralph (Ouroboros) — Specification-First AI Development Stop prompting. Start specifying. "The beginning is the end, and the end is the beginning." The serpent doesn't repeat — it evolves. When to use this skill Before writing any code — expose hidden assumptions with Socratic interviewing Long-running tasks that need autonomous iteration until verified Vague requirements — crystallize them into an immutable spec (Ambiguity ≤ 0.2) Tasks requiring guaranteed completion — loop until verification pa...
 60
14526 frontend-design shipshitdev/library
This skill guides creation of distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics. Implement real working code with exceptional attention to aesthetic details and creative choices. The user provides frontend requirements: a component, page, application, or interface to build. They may include context about the purpose, audience, or technical constraints. Design Thinking Before coding, understand the context and commit to a BOLD aesthetic direction: Purpose :...
 60
14527 tiltup 0xbigboss/claude-code
Tilt Up Principles (Always Active) These apply whenever working with Tiltfiles, Tilt errors, or dev environment bootstrap: Fix the Tiltfile, Not the Symptoms Fix the source config directly - Tiltfile, Dockerfile, k8s manifest, or helm values Never add shell workarounds - no wrapper scripts, no || true , no try/except pass Never hard-code ports, paths, hostnames, image tags, or container names that should be dynamic Never add fallbacks that mask the real error - if a resource fails, the failure m...
 60
14528 os-use zrong/skills
OS Use - Cross-Platform OS Automation A comprehensive cross-platform toolkit for OS automation, screenshot capture, visual recognition, mouse/keyboard control, and window management. Supports macOS 12+ and Windows 10+ . Platform Support Matrix Feature macOS Implementation Windows Implementation Screenshot pyautogui + PIL pyautogui + PIL Visual Recognition opencv-python + pyautogui opencv-python + pyautogui Mouse/Keyboard pyautogui pyautogui Window Management AppleScript (native) pywinauto / pyge...
 60
14529 memory-schema basicmachines-co/basic-memory-skills
Memory Schema Manage structured note types using Basic Memory's Picoschema system. Schemas define what fields a note type should have, making notes uniform, queryable, and validatable. When to Use New note type emerging — you notice several notes share the same structure (meetings, people, decisions) Validation check — confirm existing notes conform to their schema Schema drift — detect fields that notes use but the schema doesn't define (or vice versa) Schema evolution — add/remove/change field...
 60
14530 define-architecture mblode/agent-skills
Define Architecture Define durable, easy-to-change architecture defaults for TypeScript apps. How to use this skill Determine context: New codebase: follow Architecture setup workflow . Existing codebase: follow Adoption workflow . Produce an architecture brief using Output template . Run Validation loop before finalizing. Load references only when needed: Stack defaults: references/stack-defaults.md Shipping and rollout: references/shipping-practices.md Engineering quality checklists: reference...
 60
14531 brand-guidelines davepoon/buildwithclaude
Anthropic Brand Styling Overview To access Anthropic's official brand identity and style resources, use this skill. Keywords : branding, corporate identity, visual identity, post-processing, styling, brand colors, typography, Anthropic brand, visual formatting, visual design Brand Guidelines Colors Main Colors: Dark: 141413 - Primary text and dark backgrounds Light: faf9f5 - Light backgrounds and text on dark Mid Gray: b0aea5 - Secondary elements Light Gray: e8e6dc - Subtle backgrounds Accent Co...
 60
14532 stable-diffusion-image-generation orchestra-research/ai-research-skills
Stable Diffusion Image Generation Comprehensive guide to generating images with Stable Diffusion using the HuggingFace Diffusers library. When to use Stable Diffusion Use Stable Diffusion when: Generating images from text descriptions Performing image-to-image translation (style transfer, enhancement) Inpainting (filling in masked regions) Outpainting (extending images beyond boundaries) Creating variations of existing images Building custom image generation workflows Key features: Text-to...
 60
14533 wechat-draft-publisher solar-luna/fully-automatic-article-generation-skill
自动将 HTML 格式的文章发布到微信公众号草稿箱，支持封面图上传、标题、作者和摘要等元数据管理。 ⚡ 快速开始 最简单的用法： ``` python publisher.py --title "文章标题" --content article.html ``` 完整参数： ``` python publisher.py \ --title "标题" \ --content article.html \ --author "作者名" \ --cover cover.png \ --digest "文章摘要" ``` 默认值： - 作者：`YanG` - 封面图：`cover.png` 📋 执行步骤 发布文章到微信草稿箱的完整流程： - 查找 HTML 文件 优先查找 `*_formatted.html`（formatter 输出） - 回退到最新的 `.html` 文件 - 提取文章标题 从 HTML 注释提取：`<!-- Title: xxx -->` - 从文件名提取 - 询问用户 - 检查封面图 查找 `cov...
 60
14534 erk-diff-analysis dagster-io/erk
Diff Analysis This skill provides the commit message generation prompt used by PR submission commands. When to Use Only load this skill when: Explicitly requested by name ( erk-diff-analysis ) Invoked by commands like /erk:git-pr-push Usage Load references/commit-message-prompt.md when analyzing a diff, then apply its principles to generate output. Key Principles Be concise and strategic - focus on significant changes Use component-level descriptions - reference modules/components, not individua...
 60
14535 session-recovery terrylica/cc-skills
When to use this skill: - "No conversations found to resume" when running `claude -r` - New conversations not creating session files - Sessions appearing in wrong locations (`/tmp/` instead of `~/.claude/projects/`) - Session history missing after environment changes - IDE/terminal settings affecting session creation - Need to migrate or recover 600+ legacy sessions Official Session Storage Standard Location: `~/.claude/projects/` Structure: ``` ~/.claude/projects/ ├── -home-username-...
 60
14536 beads johnlindquist/claude
Beads - Persistent Task Memory for AI Agents Graph-based issue tracker that survives conversation compaction. Provides persistent memory for multi-session work with complex dependencies. bd vs TodoWrite Decision test : "Will I need this context in 2 weeks?" YES = bd, NO = TodoWrite. bd (persistent) TodoWrite (ephemeral) Multi-session, dependencies, compaction survival Single-session linear tasks Dolt-backed team sync Conversation-scoped See BOUNDARIES.md for detailed comparison. Prerequisites bd...
 60
14537 gh-address-comments shipshitdev/library
PR Comment Handler Guide to find the open PR for the current branch and address its comments with gh CLI. Run all gh commands with elevated network access. Prereq: ensure gh is authenticated (for example, run gh auth login once), then run gh auth status with escalated permissions (include workflow/repo scopes) so gh commands succeed. If sandboxing blocks gh auth status , rerun it with sandbox_permissions=require_escalated . 1) Inspect comments needing attention Run scripts/fetch_comments.py whic...
 60
14538 tool-openclaw heyvhuang/ship-faster
OpenClaw Expert Goal: answer OpenClaw install/config/ops questions using the bundled docs snapshot under references/docs/ . Default assumption: the snapshot is the source of truth. Do not guess command flags or config keys. Inputs / I-O Contract (Required) Reads (primary): references/docs/ (offline mirror of https://docs.openclaw.ai/*.md ) references/entrypoints.md (curated map) references/troubleshooting.md (routing/playbook) Writes: None by default. If refreshing the snapshot: references/docs/...
 60
14539 umbraco-header-apps umbraco/umbraco-cms-backoffice-skills
Umbraco Header Apps What is it? Header apps are single-purpose extensions that appear in Umbraco's top navigation bar, positioned next to the user profile avatar and global search. They provide globally accessible functionality to the Backoffice, such as quick links to documentation, tools, or custom interactive features. Header apps can be simple links or custom interactive components that open modals or perform actions. Documentation Always fetch the latest docs before implementing: Main docs ...
 60
14540 nuxt-data secondsky/claude-skills
Nuxt 4 Data Management Composables, data fetching, and state management patterns for Nuxt 4 applications. Quick Reference Data Fetching Methods Method Use Case SSR Caching Reactive useFetch Simple API calls Yes Yes Yes useAsyncData Custom async logic Yes Yes Yes $fetch Client-side only, events No No No Composable Naming Prefix Purpose Example use State/logic composable useAuth, useCart fetch Data fetching only fetchUsers (rare) When to Load References Load references/composables.md when: Wri...
 60
14541 umbraco-entry-point umbraco/umbraco-cms-backoffice-skills
Umbraco Entry Point What is it? Entry Points are extensions that execute JavaScript code when the Umbraco backoffice starts up. The Backoffice Entry Point runs after user authentication and is used for initialization logic, loading external libraries, registering UI extensions dynamically, or including global CSS. An optional onUnload function handles cleanup. Documentation Always fetch the latest docs before implementing: Main docs : https://docs.umbraco.com/umbraco-cms/customizing/extending-ov...
 60
14542 phase-3-mockup popup-studio-ai/bkit-claude-code
Create trendy UI without a designer + Consider Next.js componentization Purpose Quickly validate ideas before actual implementation. Even without a designer, research UI/UX trends to create high-quality prototypes, designed for easy conversion to Next.js components later. What to Do in This Phase - Screen Mockups: Implement UI with HTML/CSS - Interactions: Implement behavior with basic JavaScript - Data Simulation: Simulate API responses with JSON files - Feature Validation: Test user f...
 60
14543 reflex-dev silvainfm/claude-skills
Reflex Development Overview Reflex is a full-stack Python framework for building web applications without writing JavaScript. Apps compile to a React frontend and FastAPI backend, with state management and event handlers running entirely in Python. Architecture: Frontend: Compiled to React (JavaScript) for UI rendering Backend: FastAPI server running Python event handlers Communication: WebSockets for real-time state updates State: Server-side Python state synchronized to frontend Core Concep...
 60
14544 hooks-development terrylica/cc-skills
Guide for developing Claude Code hooks with proper output visibility patterns. When to Use This Skill - Creating a new PostToolUse or PreToolUse hook - Hook output is not visible to Claude (most common issue) - User asks about `decision: block` pattern - Debugging why hook messages don't appear - User mentions "Claude Code hooks" or "hook visibility" Quick Reference: Visibility Patterns Critical insight: PostToolUse hook stdout is only visible to Claude when JSON contains `"decision": ...
 60
14545 advanced-video-downloader jst-well-dan/skill-box
Advanced Video Downloader Overview This skill provides comprehensive video downloading and transcription capabilities from 1000+ platforms including YouTube, Bilibili, TikTok, Twitter, Instagram, and more. It combines: yt-dlp: Powerful video downloading tool SiliconFlow API: Free AI-powered transcription to convert videos to Markdown When to Use This Skill Activate this skill when the user: Explicitly requests to download a video ("download this video", "下载视频") Provides video URLs from any p...
 60
14546 ci-cd cosmix/loom
CI/CD Pipelines Comprehensive guide for CI/CD pipeline design, optimization, security, and troubleshooting across GitHub Actions, GitLab CI, and other platforms. When to Use This Skill Use this skill when: Creating new CI/CD workflows or pipelines Debugging pipeline failures or flaky tests Optimizing slow builds or test suites Implementing caching strategies Setting up deployment workflows Securing pipelines (secrets, OIDC, supply chain) Implementing DevSecOps security scanning (SAST, DAST, ...
 60
14547 status-report-template dengineproblem/agents-monorepo
Status Report Template Generator Эксперт по созданию эффективных статус-отчётов для проектной коммуникации на всех уровнях организации. Core Principles Foundational Requirements effective_status_report : principles : - name : "Consistent Formatting" description : "Use consistent structure and hierarchy across all reports" - name : "Audience-Specific" description : "Tailor depth and focus to reader's needs" - name : "Traffic Light System" description : "Green/Yellow/Red for quick visual assessmen...
 60
14548 openfga openfga/agent-skills
OpenFGA Best Practices Comprehensive guide for authoring OpenFGA authorization models and using OpenFGA SDKs, maintained for AI agents and developers. Contains rules across 7 categories covering core concepts, relationship patterns, testing, custom roles, model optimization, and language-specific SDK usage. When to Apply Reference these guidelines when: Creating new OpenFGA authorization models Defining types and relations in .fga files Writing relationship tuples Testing models with .fga.ya...
 60
14549 godot-animation-player thedivergentai/gd-agentic-skills
AnimationPlayer Expert guidance for Godot's timeline-based keyframe animation system. NEVER Do NEVER forget RESET tracks — Without a RESET track, animated properties don't restore to initial values when changing scenes. Create RESET animation with all default states. NEVER use Animation.CALL_MODE_CONTINUOUS for function calls — Calls method EVERY frame during keyframe. Use CALL_MODE_DISCRETE (calls once). Continuous causes spam. NEVER animate resource properties directly — Animating material.alb...
 60
14550 raccoon-audit autumnsgrove/groveengine
Raccoon Audit 🦝 The raccoon is curious. It lifts every rock, peers into every crevice, washes every object to see what it truly is. Nothing escapes those clever paws. What looks clean on the surface reveals its secrets under inspection. The raccoon finds what others miss—secrets buried in commits, vulnerabilities hiding in dependencies, mess that accumulated while no one was watching. When to Activate User asks to "audit security" or "check for secrets" User says "clean this up" or "sanitize bef...
 60