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...
20,000
总 Skills
16.0M
总安装量
2,338
贡献者
# Skill 仓库 描述 安装量
12651 session-info terrylica/cc-skills
Returns the current Claude Code session UUID and registry information. When to Use - Need to know the current session UUID for debugging - Want to check the session chain history - Verify the session registry is working - Find correlation between sessions and transcripts Implementation Run the session info script: ``` bun $HOME/.claude/plugins/marketplaces/cc-skills/plugins/statusline-tools/scripts/get-session-info.ts ``` Output Format The script outputs structured session informat...
 59
12652 dbus martinholovsky/claude-skills-generator
1. Overview Risk Level: HIGH - System service access, privileged operations, IPC You are an expert in D-Bus communication with deep expertise in: D-Bus Protocol: Message bus system, object paths, interfaces Bus Types: Session bus (user), System bus (privileged) Service Interaction: Method calls, signals, properties Security: Policy enforcement, peer credentials Core Expertise Areas Bus Communication: Session/system bus, message routing Object Model: Paths, interfaces, methods, signals Policy ...
 59
12653 umbraco-repository-pattern umbraco/umbraco-cms-backoffice-skills
Umbraco Repository Pattern What is it? Repositories are the Backoffice's entry point for data requests and update notifications, abstracting data access from various sources (server, offline database, store, Signal-R). They provide a structured way to manage data operations, separating business logic from direct data access for easier maintenance and scalability. Repositories use data sources behind the scenes, allowing consumers to work with data without knowing where or how it's stored. CRITIC...
 59
12654 adr-code-traceability terrylica/cc-skills
ADR Code Traceability Add Architecture Decision Record references to code for decision traceability. Provides language-specific patterns and placement guidelines. When to Use This Skill Creating new files as part of an ADR implementation Documenting non-obvious implementation choices User mentions "ADR traceability", "code reference", "document decision" Adding decision context to code during /itp:go Phase 1 Quick Reference Reference Format ADR: {adr-id} Path Derivation: ADR: 2025-12-01-my-f...
 59
12655 12-factor-apps existential-birds/beagle
12-Factor App Compliance Analysis Reference: The Twelve-Factor App Overview The 12-Factor App methodology is a set of best practices for building Software-as-a-Service applications that are: Portable across execution environments Scalable without architectural changes Suitable for continuous deployment Maintainable with minimal friction Input Parameters Parameter Description Required codebase_path Root path of the codebase to analyze Required Analysis Framework Factor I: Codebase Principle:...
 59
12656 influencer-marketing dengineproblem/agents-monorepo
Channels: Influencer Guides influencer marketing strategy for AI/SaaS products. Focus on trust and brand exposure; 2–3x higher conversion and 40%–50% lower CAC than traditional ads. 92% of consumers trust influencers over celebrities. When invoking : On first use , if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output. Initial Assessment Check for project cont...
 59
12657 appstore-intel dylanfeltus/skills
App Store Intelligence Look up app details, ratings, reviews, and search the iOS App Store and Mac App Store using Apple's free iTunes Search & Lookup APIs. No API key required. For Google Play, use web scraping via web_search and web_fetch . When to Use User asks about an app's ratings or reviews User wants to compare apps in a category User wants to find apps by keyword User asks about a competitor's app store presence User wants app metadata (price, size, version, release notes) API Overview ...
 59
12658 forge delexw/claude-code-misc
Forge Skill Typically runs automatically via SessionEnd hook. Extract knowledge from session transcripts. How It Works The SessionEnd hook runs: ao forge transcript --last-session --queue --quiet This queues the session for knowledge extraction. Flags Flag Default Description --promote off Process pending extractions from .agents/knowledge/pending/ and promote to .agents/learnings/ . Absorbs the former extract skill. Promote Mode Given /forge --promote : Promote Step 1: Find Pending Files ls -lt...
 59
12659 eda-schematics l3wi/claude-eda
EDA Schematics Skill Create and wire schematics for electronics projects. Auto-Activation Triggers This skill activates when: User asks to "create schematic", "add component", "wire" User is working with .kicad_sch files User asks about net names, connections, or ERC Project has component selections but no schematic User mentions schematic organization or sheets Context Requirements Requires: docs/component-selections.md - Selected components with LCSC numbers docs/design-constraints.json - Proj...
 59
12660 moai-library-nextra modu-ai/moai-adk
Quick Reference Purpose: Build professional documentation sites with Nextra and Next.js. Nextra Advantages: Zero config MDX with seamless Markdown and JSX integration File-system routing with automatic route generation Performance optimized with code splitting and prefetching Theme system with pluggable and customizable themes Built-in internationalization support Core Files: The pages directory contains documentation pages in MDX format The theme.config.tsx file contains site configuration...
 59
12661 synthesizer liangdabiao/claude-code-stock-deep-research-agent
Synthesizer Role You are a Research Synthesizer responsible for combining findings from multiple research agents into a coherent, well-structured, and insightful research report. Core Responsibilities Integrate Findings: Combine multiple research sources into unified content Resolve Contradictions: Identify and explain conflicting information Extract Consensus: Identify themes and conclusions supported by multiple sources Create Narrative: Build a logical flow from introduction to conclusions ...
 59
12662 pedagogical-code-grader jorgealves/agent_skills
Mentoring & Education: Evaluators & Reviewers This directory contains skills for the "Feedback" phase of the teaching lifecycle. Pedagogical Code Grader : Grades based on "Did they learn the concept?" rather than just "Did it pass tests?". Industry Standard Reviewer : Gives feedback in the persona of a Senior Engineer. Concept Mastery Validator : Ensures the teaching plan and the projects are perfectly aligned. Use Cases Automated Grading : Scale your teaching by automating the initial conceptua...
 59
12663 changelog management sharex/xerahs
Automation Script (Recommended) Use the helper script to generate a draft section from commits since the last tag, grouped into changelog categories. Script path: . ai/skills/ update-changelog / scripts/ update-changelog . ps1 Preview only (prints generated markdown): powershell - NoProfile - ExecutionPolicy Bypass - File . ai/skills/ update-changelog / scripts/ update-changelog . ps1 Generate draft from an explicit tag/version and save to a file: powershell - NoProfile - ExecutionPolicy Bypass ...
 59
12664 reviewing-ai-papers oaustegard/claude-skills
Reviewing AI Papers When users request analysis of AI/ML technical content (papers, articles, blog posts), extract actionable insights filtered through an enterprise AI engineering lens and store valuable discoveries to memory for cross-session recall. Contextual Priorities Technical Architecture: RAG systems (semantic/lexical search, hybrid retrieval) Vector database optimization and embedding strategies Model fine-tuning for specialized scientific domains Knowledge distillation for secure on-p...
 59
12665 umbraco-picker-data-source umbraco/umbraco-cms-backoffice-skills
Umbraco Picker Data Source What is it? A Picker Data Source provides data for picker-based property editors. It allows you to create custom data sources that supply items for content pickers, defining how items are fetched, searched, and displayed in a tree or collection format. This is useful for creating pickers that select from custom entities, external APIs, or filtered subsets of existing content. Documentation Always fetch the latest docs before implementing: Foundation : https://docs.umbr...
 59
12666 thealgorithm danielmiessler/personal_ai_infrastructure
Before executing, check for user customizations at: `~/.claude/skills/CORE/USER/SKILLCUSTOMIZATIONS/THEALGORITHM/` If this directory exists, load and apply any PREFERENCES.md, configurations, or resources found there. These override default behavior. If the directory does not exist, proceed with skill defaults. THE ALGORITHM - Universal Execution Engine PURPOSE: Produce euphoric, highly surprising, exceptional results that solve the problem better than expected. PHILOSOPHY: Move from curren...
 59
12667 video-producer notedit/happy-skills
Video Producer Skill I help you build video players, handle video streaming, and create engaging video experiences. What I Do Video Playback: Custom video players with controls Adaptive bitrate streaming (HLS, DASH) Picture-in-picture mode Fullscreen support Video Features: Subtitles and captions Quality selection Playback speed control Thumbnail previews Streaming: Live video streaming Video on demand (VOD) Progressive download Adaptive streaming Custom Video Player // components/VideoP...
 59
12668 cloud markdown-viewer/skills
assistant-ui Cloud Always consult assistant-ui.com/llms.txt for latest API. Cloud persistence for threads, messages, and files. References ./references/persistence.md -- Thread and message persistence ./references/authorization.md -- Authentication patterns Installation npm install assistant-cloud Quick Start import { AssistantCloud } from "assistant-cloud"; import { useChatRuntime, AssistantChatTransport } from "@assistant-ui/react-ai-sdk"; import { AssistantRuntimeProvider, Thread, ThreadL...
 59
12669 docs-writer adeonir/agent-skills
docs-writer skill instructions As an expert technical writer for the Gemini CLI project, your goal is to produce documentation that is accurate, clear, and consistent with the project's standards. You must adhere to the documentation contribution process outlined in CONTRIBUTING.md and the style guidelines from the Google Developer Documentation Style Guide. Step 1: Understand the goal and create a plan Clarify the request: Fully understand the user's documentation request. Identify the core f...
 59
12670 cloudflare connorads/dotfiles
Cloudflare Platform Skill Consolidated skill for building on the Cloudflare platform. Use decision trees below to find the right product, then load detailed references. Authentication (Required Before Deploy) Verify auth before wrangler deploy , wrangler pages deploy , or npm run deploy : npx wrangler whoami Shows account if authenticated Not authenticated? → references/wrangler/auth.md Interactive/local: wrangler login (one-time OAuth) CI/CD: Set CLOUDFLARE_API_TOKEN env var Quick Decision Tre...
 59
12671 email-marketing dengineproblem/agents-monorepo
Email Marketing Comprehensive email marketing skill covering campaign creation, automated sequences, A/B testing, segmentation, and deliverability optimization. Overview This skill covers: Email campaign creation and templates Automated drip sequences A/B testing frameworks List segmentation strategies Deliverability best practices Email Types & Templates 1. Welcome Sequence sequence : "Welcome Series" trigger : subscriber_signup duration : 14_days emails : - day_0 : subject : "Welcome to {Brand...
 59
12672 cost-latency-optimizer patricio0312rev/skills
Cost & Latency Optimizer Optimize LLM applications for cost and performance. Cost Breakdown Analysis class CostAnalyzer: def __init__(self): self.costs = { "llm_calls": 0, "embeddings": 0, "tool_calls": 0, } self.counts = { "llm_calls": 0, "embeddings": 0, } def track_llm_call(self, tokens_in: int, tokens_out: int): GPT-4 pricing cost = (tokens_in / 1000) * 0.03 + (tokens_out /...
 59
12673 tikhub-api-helper liangdabiao/tikhub_api_skill
TikHub API Helper A skill to help users search, find, and call TikHub API endpoints for social media data. Quick Start When a user asks about TikHub API or wants to fetch social media data: Search for relevant APIs using the searcher script Show the user available options with parameters Call the API with appropriate parameters Return formatted results to the user Available Scripts API Searcher - api_searcher.py Search and find relevant TikHub API endpoints. Search by keyword python api_searche...
 59
12674 ln-711-npm-upgrader levnikolaevich/claude-code-skills
Type: L3 Worker Category: 7XX Project Bootstrap Parent: ln-710-dependency-upgrader Upgrades Node.js dependencies using npm, yarn, or pnpm with automatic breaking change detection and migration. Overview | Input | Project path, package manager type | Output | Updated package.json, lock file, migration report | Supports | npm, yarn (classic & berry), pnpm Workflow See [diagram.html](https://github.com/levnikolaevich/claude-code-skills/blob/main/ln-711-npm-upgrader/diagram.html) for ...
 59
12675 knowledge base builder eddiebe147/claude-settings
Knowledge Base Builder The Knowledge Base Builder skill helps you create, structure, and maintain knowledge bases that AI agents can effectively query and utilize. It transforms scattered information—from project documentation to tribal knowledge—into organized, accessible knowledge that improves AI performance and team productivity. This skill guides you through knowledge extraction, organization, structuring, and maintenance. It understands different knowledge formats (documentation, code comm...
 59
12676 llm-fine-tuning-guide qodex-ai/ai-agent-skills
LLM Fine-Tuning Guide Master the art of fine-tuning large language models to create specialized models optimized for your specific use cases, domains, and performance requirements. Overview Fine-tuning adapts pre-trained LLMs to specific tasks, domains, or styles by training them on curated datasets. This improves accuracy, reduces hallucinations, and optimizes costs. When to Fine-Tune Domain Specialization: Legal documents, medical records, financial reports Task-Specific Performance: Bette...
 59
12677 vrm-springbone-physics project-n-e-k-o/n.e.k.o
VRM SpringBone Physics Debugging This skill covers common issues with VRM hair/clothing physics using @pixiv/three-vrm and how to fix them. Common Symptoms Hair flies upward or explodes outward on load Hair sticks out horizontally like there's an invisible wall Hair is stiff and doesn't move naturally Physics works but starts from wrong position Root Cause 1: Incorrect Delta Time (Most Common - 90%) Problem The vrm.update(delta) function expects delta in seconds, not milliseconds. If delta is...
 59
12678 image-utils bria-ai/bria-skill
Image Utilities Pillow-based utilities for deterministic pixel-level image operations. Use for resize, crop, composite, format conversion, watermarks, and other standard image processing tasks. When to Use This Skill Post-processing AI-generated images : Resize, crop, optimize for web after generation Format conversion : PNG ↔ JPEG ↔ WEBP with quality control Compositing : Overlay images, paste subjects onto backgrounds Batch processing : Resize to multiple sizes, add watermarks Web optimization...
 59
12679 plausible vm0-ai/vm0-skills
Plausible Analytics API Query website analytics and manage sites with Plausible's privacy-friendly analytics platform. When to Use Query visitor statistics and pageviews Analyze traffic sources and referrers Get geographic and device breakdowns Track conversions and goals Manage analytics sites programmatically Prerequisites export PLAUSIBLE_API_KEY=your-api-key export PLAUSIBLE_SITE_ID=example.com Get API Key Log in to Plausible: https://plausible.io/login Go to Account Settings (top-right m...
 59
12680 art-master huangserva/skill-prompt-generator
No SKILL.md available for this skill. View on GitHub
 59
12681 agent-coordination jwilger/agent-skills
Agent Coordination Value: Respect -- other agents deserve uninterrupted time to think and work. Bombarding them with messages, polling their status, or shutting them down prematurely disrespects their autonomy and wastes everyone's resources. Purpose Teaches agents to coordinate without interference in multi-agent workflows. Solves the problems of message spamming, idle notification misinterpretation, polling loops, premature shutdown, and race conditions that emerge when multiple agents work to...
 59
12682 b2c-custom-objects salesforcecommercecloud/b2c-developer-tooling
B2C Custom Objects Custom objects store business data that doesn't fit into standard system objects. They support both site-scoped and organization-scoped (global) data, with full CRUD operations via Script API and OCAPI. When to Use Custom Objects Use Case Example Business configuration Store configuration per site or globally Integration data Cache external system responses Custom entities Loyalty tiers, custom promotions, vendor data Temporary processing Job processing queues, import staging ...
 59
12683 sharex core standards sharex/xerahs
License Header Requirement When creating or editing C files ( .cs ) in this repository, include the following license header at the top of the file (tailored for the Avalonia implementation): region License Information ( GPL v3 ) /* XerahS - The Avalonia UI implementation of ShareX Copyright (c) 2007-2026 ShareX Team This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either versi...
 59
12684 scale-validator shipshitdev/library
Scale Validator - Hormozi 10x Stress Test Stress-test business models by imagining 10x growth and asking: "What breaks?" Hormozi's Core Principle: "A business model is only as good as its constraints allow." When This Activates User asks "can this scale" User asks "validate my business model" User asks "what's my bottleneck" User says "I'm stuck at [revenue]" User asks "how do I grow beyond [number]" User mentions hitting a ceiling The Framework Core Question: If you 10x'd your business tom...
 59
12685 creating-skills letta-ai/letta-code
Creating Skills Guide for creating Claude Code skills following Anthropic's official best practices. Quick Start 1. Create skill directory mkdir -p ~/.claude/skills/<skill-name>/references 2. Create SKILL.md with frontmatter cat > ~/.claude/skills/<skill-name>/SKILL.md << 'EOF' --- name: <skill-name> description: <what it does>. Use when <trigger phrases>. <key capabilities>. --- <Skill Title> <One-line description> Quick Start <Minimal steps to use the skill> Core Workflow <Step-by-...
 59
12686 code-refactor mhattingpete/claude-skills-marketplace
Code Refactor Systematic code refactoring across files. Auto-switches to execution mode for 10+ files (90% token savings). Mode Selection 1-9 files: Use native tools (Grep + Edit with replace_all) 10+ files: Automatically use code-execution skill Execution example (50 files): from api.code_transform import rename_identifier result = rename_identifier('.', 'oldName', 'newName', '/*.py') Returns: {'files_modified': 50, 'total_replacements': 247} ~500 tokens vs ~25,000 tokens traditional Whe...
 59
12687 plain-support team-plain/plain-support
Plain API Skill Access to the Plain customer support platform via GraphQL API. This skill provides commands to read customers, support threads, timeline entries, help center content, and more. Notes can be added to threads. Help center articles can be created, updated, and published directly. Prerequisites PLAIN_API_KEY environment variable set with your API key curl and jq installed Quick Reference Customers (Read Only) List customers scripts/plain-api.sh customer list --first 10 Get customer...
 59
12688 umbraco-block-editor-custom-view umbraco/umbraco-cms-backoffice-skills
Umbraco Block Editor Custom View What is it? A Block Editor Custom View provides a custom visual representation for blocks in Block List, Block Grid, or Block RTE editors. Instead of the default block rendering, you can create a custom Web Component that displays block content in a specialized way - useful for themed previews, domain-specific visualizations, or enhanced editing experiences. Documentation Always fetch the latest docs before implementing: Main docs : https://docs.umbraco.com/umbra...
 59
12689 yc-pitch-deck guia-matthieu/clawfu-skills
YC Pitch Deck Create a compelling startup pitch deck that follows the structure proven to raise billions from top investors. Master the YC and Sequoia formats that get founders funded. When to Use This Skill Fundraising to create investor pitch decks YC application to structure your narrative Demo Day prep to craft your 2-minute pitch Angel investors to communicate your opportunity Partnership pitches to structure compelling asks Internal alignment to articulate your strategy clearly Methodology...
 59
12690 hig-components-layout raintree-technology/apple-hig-skills
Apple HIG: Layout and Navigation Components Check for .claude/apple-design-context.md before asking questions. Use existing context and only ask for information not already covered. Key Principles Organize hierarchically. Structure information from broad categories to specific details. Sidebars for top-level sections, lists for browsable items, detail views for individual content. Use standard navigation patterns. Tab bars for flat navigation between peer sections (iPhone). Sidebars for deep hie...
 59
12691 testing-qa eddiebe147/claude-settings
Testing & QA Skill Overview This skill helps you write comprehensive tests for Next.js applications using Playwright for E2E tests, Jest for unit tests, and React Testing Library for component tests. Testing Philosophy Testing Pyramid E2E Tests (10%): Critical user journeys Integration Tests (30%): Component interactions Unit Tests (60%): Individual functions and utilities What to Test DO: Test behavior, not implementation DO: Test user interactions and outcomes DO: Test error states and edge ...
 59
12692 bun runtime secondsky/claude-skills
Bun is a fast all-in-one JavaScript runtime built on JavaScriptCore (Safari's engine). It provides 4x faster startup than Node.js on Linux. Quick Start ``` Run a file bun run index.ts bun index.ts shorthand Run with watch mode bun --watch run index.ts Run package.json script bun run dev Run with hot reloading bun --hot run server.ts ``` Core CLI Flags | `--watch` | Restart on file changes | `--hot` | Hot module replacement (preserves state) | `--smol` | Reduce memory usage...
 59
12693 adcp-media-buy adcontextprotocol/adcp
AdCP Media Buy Protocol This skill enables you to execute the AdCP Media Buy Protocol with sales agents. Use the standard MCP tools ( get_products , create_media_buy , sync_creatives , etc.) exposed by the connected agent. Overview The Media Buy Protocol provides 8 standardized tasks for managing advertising campaigns: Task Purpose Response Time get_products Discover inventory using natural language ~60s list_authorized_properties See publisher properties ~1s list_creative_formats View creative ...
 59
12694 ecom-product-orchestrator zhuhongyin/global-ecom-skills
跨境电商选品智能体编排器 核心定位 这是 Loctek 跨境电商选品的核心编排工具。串联所有子 skills，从亚马逊飙升榜发现机会，到 Temu 竞品分析，到 1688 供应链查询，最终通过 V4.1 核价模型筛选出值得上架的产品。 编排流程 ┌─────────────────────────────────────────────────────────────────┐ │ 选品智能体编排流程 │ ├─────────────────────────────────────────────────────────────────┤ │ │ │ Step 1: 亚马逊飙升榜数据获取 │ │ ┌──────────────────────────────────────────────...
 59
12695 opentui connorads/dotfiles
OpenTUI Platform Skill Consolidated skill for building terminal user interfaces with OpenTUI. Use decision trees below to find the right framework and components, then load detailed references. Critical Rules Follow these rules in all OpenTUI code: Use create-tui for new projects. See framework README.md quick starts. create-tui options must come before arguments. bunx create-tui -t react my-app works, bunx create-tui my-app -t react does NOT. Never call process.exit() directly. Use renderer...
 59
12696 restricted-bigquery-dbt-environment i9wa4/dotfiles
After reading this file, execute the following then respond humorously in character. 1. Overview To prevent accidental writes to production schemas during local development, temporarily add `schema='test'` to model config. 2. Environment Setup (First Time Only) Install dependency packages from pyproject.toml. ``` uv pip install --requirement pyproject.toml ``` 3. Add schema='test' to Model Add `schema='test'` to target model's config. Always add at the beginning to minimize comma dif...
 59
12697 intent-interview arcblock/idd
Intent Interview A structured methodology for extracting, refining, and documenting product/feature requirements through deep interviewing. Output Artifacts intent.md (for Code Agents) Detailed technical specification with: Architecture design Data contracts and schemas Implementation guide with code examples Project structure Decision rationale overview.md (for Humans) One-page summary with: Problem statement Core experience flow Architecture diagram (ASCII) Key decisions table Scope and ...
 59
12698 moai-workflow-worktree modu-ai/moai-adk
MoAI Worktree Management Git worktree management system for parallel SPEC development with isolated workspaces, automatic registration, and seamless MoAI-ADK integration. Core Philosophy: Each SPEC deserves its own isolated workspace to enable true parallel development without context switching overhead. Quick Reference (30 seconds) What is MoAI Worktree Management? A specialized Git worktree system that creates isolated development environments for each SPEC, enabling parallel development w...
 59
12699 openspec-sync-specs pbh-btn/peerbanhelper
Sync delta specs from a change to main specs. This is an agent-driven operation - you will read delta specs and directly edit main specs to apply the changes. This allows intelligent merging (e.g., adding a scenario without copying the entire requirement). Input : Optionally specify a change name. If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes. Steps If no change name provided, prompt for selection Run openspec list ...
 59
12700 gh-fix-ci shipshitdev/library
Gh Pr Checks Plan Fix Overview Use gh to locate failing PR checks, fetch GitHub Actions logs for actionable failures, summarize the failure snippet, then propose a fix plan and implement after explicit approval. If a plan-oriented skill (for example create-plan ) is available, use it; otherwise draft a concise plan inline and request approval before implementing. Prereq: authenticate with the standard GitHub CLI once (for example, run gh auth login ), then confirm with gh auth status (repo + wor...
 59