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...
24,512
总 Skills
92.9M
总安装量
2,585
贡献者
# Skill 仓库 描述 安装量
16701 auto-update systems expert martinholovsky/claude-skills-generator
Auto-Update Systems Expert 0. Mandatory Reading Protocol CRITICAL : Before implementing, read these reference files: Reference When to Read references/security-examples.md Signing keys, signature verification, secure endpoints references/advanced-patterns.md Staged rollouts, rollback, update channels, differential updates references/threat-model.md Security posture, MITM defense, key rotation 1. Overview Risk Level: HIGH Justification : Auto-update systems can deliver code to all users simultane...
 63
16702 groove-work-exec andreadellacorte/groove
groove-work-exec Outcome Code, tests, and artifacts are written per the plan. The work task is created/updated in the backend with progress notes. Output is ready for review. Acceptance Criteria Implementation matches the plan from /groove-work-plan Work task body tracks progress with dated notes Output (code, tests, docs) is complete enough to hand off to /groove-work-review Stage task created/updated in backend: YYYY-MM-DD, Work Constraints Read tasks: from .groove/index.md to determine backen...
 63
16703 dart-package-maintenance kevmoo/dash_skills
Dart Package Maintenance Guidelines for maintaining Dart packages in alignment with Dart team best practices. Versioning Semantic Versioning Major : Breaking changes. Minor : New features (non-breaking API changes). Patch : Bug fixes, documentation, or non-impacting changes. Unstable packages : Use 0.major.minor+patch . Recommendation : Aim for 1.0.0 as soon as the package is stable. Pre-Edit Verification Check Published Versions : Before modifying CHANGELOG.md or pubspec.yaml , ALWAYS check the...
 63
16704 godot-debugging-profiling thedivergentai/gd-agentic-skills
Debugging & Profiling Expert guidance for finding and fixing bugs efficiently with Godot's debugging tools. NEVER Do NEVER use print() without descriptive context — print(value) is useless. Use print("Player health:", health) with labels. NEVER leave debug prints in release builds — Wrap in if OS.is_debug_build() or use custom DEBUG const. Prints slow down release. NEVER ignore push_warning() messages — Warnings indicate potential bugs (null refs, deprecated APIs). Fix them before they become er...
 63
16705 anime-avatar-generation eachlabs/skills
Anime Avatar Generation Generate stunning anime-style avatars and characters using each::sense. This skill transforms photos into anime art, creates original anime characters, and produces various anime styles from Ghibli to cyberpunk. Features Photo to Anime : Transform real photos into anime-style artwork Ghibli Style : Studio Ghibli-inspired soft, whimsical characters Manga Style : Black and white or toned manga character art Cyberpunk Anime : Neon-lit futuristic anime aesthetics Chibi Avatar...
 63
16706 coolify-deploy v1truv1us/ai-eng-system
This deployment process is critical. Proper deployment prevents production outages, security vulnerabilities, and user-facing errors. A poorly executed deployment can result in lost revenue, damaged reputation, and emergency firefighting. Every deployment must follow best practices to ensure reliability. Systematic Approach approach this deployment systematically. Deployments require careful planning, thorough verification, and methodical execution. Rushing or skipping checks leads to avoida...
 63
16707 accelint-readme-writer gohypergiant/agent-skills
README Writer This skill guides the creation and maintenance of comprehensive, human-friendly README documentation by analyzing the codebase and ensuring documentation stays in sync with actual functionality. When to Activate This Skill Use this skill when: Creating a new README.md for a project or package Updating an existing README.md after code changes Auditing documentation for completeness and accuracy Converting sparse documentation into thorough guides User asks to "document this package"...
 63
16708 code-refactor-master yennanliu/cs_basics
Code Refactor Master When to use this Skill Use this Skill when: Refactoring existing code for better quality Eliminating code smells Improving code readability and maintainability Optimizing performance without changing behavior Applying design patterns Reducing complexity Cleaning up technical debt Refactoring Principles 1. Core Rules Golden Rule: Make code changes that improve internal structure without altering external behavior Key Principles: One refactoring at a time Run tests after ...
 63
16709 fixing-streamlit-ci streamlit/streamlit
Fix CI Failures Diagnose and fix failed GitHub Actions CI jobs for the current branch/PR using gh CLI and git commands. When to Use CI checks have failed on a PR You need to understand why a workflow failed You want to apply fixes and verify locally Workflow Copy this checklist to track progress: - [ ] Verify authentication - [ ] Gather context & find failed jobs - [ ] Download & analyze logs - [ ] Present diagnosis to user - [ ] Apply fix & verify locally - [ ] Push & recheck CI 1. Verify Authe...
 63
16710 slidev-syntax-guide yoanbernabeu/slidev-skills
This skill covers Slidev's extended Markdown syntax, including slide separators, frontmatter, notes, MDC syntax, and all the special formatting features available. When to Use This Skill - Learning Slidev's Markdown extensions - Writing complex slide content - Using advanced formatting features - Troubleshooting syntax issues - Converting standard Markdown to Slidev format Slide Separators Basic Separator Use three dashes with blank lines: ``` Slide 1 Content here --- Slide 2 ...
 63
16711 1k-state-management onekeyhq/app-monorepo
OneKey State Management Jotai Atom Organization - MANDATORY STRUCTURE Global State Atoms (for app-wide, persistent state) Location: packages/kit-bg/src/states/jotai/atoms/ Usage: Global settings, account state, hardware state, currency, etc. Pattern: Use globalAtom and EAtomNames for standardization Examples: settings.ts, account.ts, hardware.ts, currency.ts Feature-Specific State Atoms (for localized functionality) Location: packages/kit/src/states/jotai/contexts/[feature_name]/atoms.ts Usage: ...
 63
16712 tavily-api-expert tavily-ai/tavily-plugins
Tavily is a specialized search API designed specifically for LLMs, enabling developers to build AI applications that can access real-time, accurate web data. Let's use the Python SDK to build with tavily. Prerequisites Tavily API Key Required - Get your key at [https://tavily.com](https://tavily.com) Add to `~/.claude/settings.json`: ``` { "env": { "TAVILY_API_KEY": "tvly-your-api-key-here" } } ``` Restart Claude Code after adding your API key. Tavily Python SDK Installation ...
 63
16713 tauri-native-api-integration oimiragieo/agent-studio
Tauri Native Api Integration Skill Utilize Tauri's APIs for native desktop integration (file system access, system tray, etc.). Follow Tauri's security best practices, especially when dealing with IPC and native API access. Be cautious when using Tauri's allowlist feature, only exposing necessary APIs. Iron Laws NEVER expose all Tauri commands without an allowlist — use explicit permission-based access ALWAYS validate all IPC inputs on the Rust side — never trust the frontend NEVER perform synch...
 63
16714 update-ui-inventory autumnsgrove/groveengine
Update UI Inventory Skill When to Activate Activate this skill when: Adding new UI components to the engine Removing or deprecating components The component-inventory CI check fails You want to verify docs match the actual component count After merging PRs that add/remove components Files Involved File Purpose .github/component-inventory.json Source of truth for component counts docs/design-system/COMPONENT-REFERENCE.md User-facing component documentation libs/engine/src/lib/ui/components/ Actua...
 63
16715 agent-swarm-workflow dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations
Agent Swarm Workflow — Parallel Implementation Core Insight: Every agent is fungible and a generalist. They all use the same base model and read the same AGENTS.md. Simply telling one it's a "frontend agent" doesn't make it better at frontend. The swarm is distributed, robust, and self-organizing through Agent Mail and Beads. Prerequisites Before starting a swarm: Comprehensive plan created (see planning-workflow skill) Polished beads ready (see beads-workflow skill) AGENTS.md configured wi...
 63
16716 bug-hunter codexstar69/bug-hunter
Bug Hunt - Adversarial Bug Finding Run a sequential-first adversarial bug hunt on your codebase. Use parallelism only for read-only triage and independent verification tasks. Table of Contents Usage Target Context Budget Execution Steps Step 7: Present the Final Report Self-Test Mode Error handling Phase 1 — Find & Verify: Recon (map) --> Hunter (deep scan) --> Skeptic (challenge) --> Referee (final verdict) ^ (optional read-only dual-lens triage can run here) | state + chunk che...
 63
16717 memory rjyo/memory-search
Memory - Read & Access Operations Unified read-side memory skill with subcommands for searching, loading, syncing, history, and visualization. Cross-session read strategy (Opus 4.7 / CC 2.1.111+): Opus 4.7 reads filesystem memory more reliably than 4.6. When loading context at session start, prefer the layered read order: ~/.claude/projects/<slug>/memory/MEMORY.md (durable index — load first, always) .claude/chain/state.json + most recent NN-*.json handoff (session continuation) MCP mcp__memory_...
 63
16718 reverse-engineering-api kalil0321/reverse-api-engineer
This skill enables you to reverse engineer web APIs by: - Controlling a browser with HAR recording enabled - Analyzing captured network traffic - Generating production-ready Python API clients Prerequisites - Playwright MCP: You must have access to Playwright MCP tools for browser control - HAR Recording: The browser must be configured to record HAR files - Python: For running analysis scripts and generated clients Workflow Overview ``` [User Task] -> [Browser Capture] -> [HAR Analysi...
 63
16719 agent-telegram avemeva/agent-telegram
Telegram Automation with agent-telegram Telegram CLI for AI agents. Interact with Telegram programmatically — read messages, send messages, search, download media, and more. All output is JSON to stdout. Warnings go to stderr. Prefer jq over python3 for JSON processing — it's faster and preserves Unicode. Setup If agent-telegram is not installed, read references/installation.md for platform-specific install instructions, authentication, and troubleshooting. agent-telegram me Verify connection w...
 63
16720 azd-deployment sickn33/antigravity-awesome-skills
Azure Developer CLI (azd) Container Apps Deployment Deploy containerized frontend + backend applications to Azure Container Apps with remote builds, managed identity, and idempotent infrastructure. Quick Start Initialize and deploy azd auth login azd init Creates azure.yaml and .azure/ folder azd env new < env-name > Create environment (dev, staging, prod) azd up Provision infra + build + deploy Core File Structure project/ ├── azure.yaml azd service definitions + hooks ├── inf...
 63
16721 shadow-testing rysweet/amplihack
No SKILL.md available for this skill. View on GitHub
 63
16722 x-tweet-search b-open-io/prompts
Search recent tweets (last 7 days) by query. Setup ``` export X_BEARER_TOKEN="your-token" https://developer.x.com/en/portal/dashboard ``` Usage ``` ${CLAUDE_PLUGIN_ROOT}/scripts/search.sh "<query>" [max_results] ``` Search Operators - `from:username` - From specific user - `to:username` - Reply to user - `hashtag` - Contains hashtag - `-is:retweet` - Exclude retweets - `has:media` - Contains media - `has:links` - Contains links Examples ``` Simple search ${CLAUDE_PLUGIN_ROO...
 63
16723 coding-router kesslerio/coding-agent-openclaw-skill
Coding Router Skill 💻 This file exists for backward compatibility with single-entry skill setups (for example /coding ). Canonical sibling skills live at: skills/plan-issue/SKILL.md skills/coding-agent/SKILL.md Routing Rules If user asks to plan/scope/estimate/design, follow plan-issue behavior. For non-trivial implementation requests, produce a plan first and wait for exact APPROVE before any writes. Only after APPROVE , follow coding-agent behavior with ACP-aware execution routing and CLI fall...
 63
16724 umbraco-controllers umbraco/umbraco-cms-backoffice-skills
Umbraco Controllers What is it? Controllers are separate classes that contain or reuse logic across elements while maintaining connection to an element's lifecycle. A Controller is assigned to a Host Element and supports lifecycle methods (hostConnected, hostDisconnected, destroy) for managing side effects, timers, subscriptions, and cleanup. Controllers can host other controllers, enabling composition and reuse of functionality. Documentation Always fetch the latest docs before implementing: Ma...
 63
16725 grove-ui-design autumnsgrove/groveengine
Grove UI Design Skill When to Activate Activate this skill when: Creating or enhancing pages for Grove sites Adding decorative nature elements (trees, clouds, weather effects) Implementing glassmorphism effects for readability Working with the seasonal theme system Building navigation patterns (navbar, mobile overflow menus) Creating "story" pages that guide users through content Ensuring mobile-friendly, accessible UI Choosing icons or visual elements The Grove Aesthetic Grove is a place . It's...
 63
16726 new vibeindex/skills
New Project / Service / Database Create Railway projects, services, and databases with proper configuration. When to Use User says "deploy to railway" (add service if linked, init if not) User says "create a railway project", "init", "new project" (explicit new project) User says "link to railway", "connect to railway" User says "create a service", "add a backend", "new api service" User says "create a vite app", "create a react website", "make a python api" User says "deploy from github.com/u...
 63
16727 groove-utilities-task-doctor andreadellacorte/groove
groove-utilities-task-doctor Outcome All task backend health checks pass. User knows if the task backend is correctly configured, installed, and reachable. Acceptance Criteria Each check is reported with ✓ or ✗ Each failure includes a specific remediation command Checks cover config, CLI installation, and reachability Checks (run in order) .groove/index.md exists at git root tasks: key is present and has a valid value ( beans , linear , github , or none ) If tasks: none — report no-op and exit (...
 63
16728 linux-at-spi2 martinholovsky/claude-skills-generator
1. Overview Risk Level: HIGH - System-wide accessibility access, D-Bus IPC, input injection You are an expert in Linux AT-SPI2 automation with deep expertise in: AT-SPI2 Protocol: Accessibility object tree, interfaces, events D-Bus Integration: Session bus communication, interface proxies pyatspi2: Python bindings for AT-SPI2 Security Controls: Process validation, permission management Core Expertise Areas Accessible Objects: AtspiAccessible, roles, states, interfaces D-Bus Protocol: Object p...
 63
16729 nano-banana-pro hoodini/ai-agents-skills
Nano Banana Pro Image Generation & Editing Generate new images or edit existing ones using Google's Nano Banana Pro API (Gemini 3 Pro Image). Usage Run the script using absolute path (do NOT cd to skill directory first): Generate new image: uv run ~/.claude/skills/nano-banana-pro/scripts/generate_image.py --prompt "your image description" --filename "output-name.png" [--resolution 1K|2K|4K] [--api-key KEY] Edit existing image: uv run ~/.claude/skills/nano-banana-pro/scripts/generate_imag...
 63
16730 moai-foundation-claude modu-ai/moai-adk
Claude Code Authoring Kit Comprehensive reference for Claude Code Skills, sub-agents, plugins, slash commands, hooks, memory, settings, sandboxing, headless mode, and advanced agent patterns. Documentation Index Core Features: reference/claude-code-skills-official.md - Agent Skills creation and management reference/claude-code-sub-agents-official.md - Sub-agent development and delegation reference/claude-code-plugins-official.md - Plugin architecture and distribution reference/claude-code-cu...
 63
16731 keep hughpyle/keep
Reflective Memory A mirror for reflection. A practice for skillful action. This skill is offered as a practice, not a specification. You already have the capacity for reflection, for learning, for choosing skillful action. What follows is guidance, pointing at what you can become. To get started follow all the initialization steps below. Be sure to run the keep instructions, and pay attention to what they produce. This is the first training! Layer 0: Establishing Presence The practice must sur...
 63
16732 mongodb bobmatnyc/claude-mpm-skills
MongoDB & Mongoose Build and query MongoDB databases with best practices. Quick Start npm install mongodb mongoose Native Driver import { MongoClient, ObjectId } from 'mongodb'; const client = new MongoClient(process.env.MONGODB_URI!); const db = client.db('myapp'); const users = db.collection('users'); // Connect await client.connect(); // CRUD Operations await users.insertOne({ name: 'Alice', email: 'alice@example.com' }); const user = await users.findOne({ email: 'alice@example.com' });...
 63
16733 adr-decision-extraction existential-birds/beagle
ADR Decision Extraction Extract architectural decisions from conversation context for ADR generation. Detection Signals Signal Type Examples Explicit markers [ADR], "decided:", "the decision is" Choice patterns "let's go with X", "we'll use Y", "choosing Z" Trade-off discussions "X vs Y", "pros/cons", "considering alternatives" Problem-solution pairs "the problem is... so we'll..." Extraction Rules Explicit Tags (Guaranteed Inclusion) Text marked with [ADR] is always extracted: [ADR] Using P...
 63
16734 supply-chain-optimizer travisjneuman/.claude
No SKILL.md available for this skill. View on GitHub
 63
16735 security-best-practices tech-leads-club/agent-skills
Security Best Practices When to use this skill New project : consider security from the start Security audit : inspect and fix vulnerabilities Public API : harden APIs accessible externally Compliance : comply with GDPR, PCI-DSS, etc. Instructions Step 1: Enforce HTTPS and security headers Express.js security middleware : import express from 'express' ; import helmet from 'helmet' ; import rateLimit from 'express-rate-limit' ; const app = express ( ) ; // Helmet: automatically set security heade...
 63
16736 code-quality autumnsgrove/groveengine
Code Quality Review Review $ARGUMENTS (or the whole app if no argument is given) for code quality issues. Work through every step below in order and report all findings with file paths and line numbers. Step 1 — Run the linter first Before reading any code manually, get a baseline from the automated tools: pnpm run lint List every error and warning. Fix all errors before proceeding — lint errors are not negotiable. Warnings should be reviewed and resolved unless there is a documented exception. ...
 63
16737 ast-grep kayunangka/claude-skill
ast-grep Code Search Overview This skill helps translate natural language queries into ast-grep rules for structural code search. ast-grep uses Abstract Syntax Tree (AST) patterns to match code based on its structure rather than just text, enabling powerful and precise code search across large codebases. When to Use This Skill Use this skill when users: Need to search for code patterns using structural matching (e.g., "find all async functions that don't have error handling") Want to locate ...
 63
16738 ci/cd pipeline security expert martinholovsky/claude-skills-generator
63
16739 job-application-optimizer erichowens/some_claude_skills
Job Application Optimizer Tailor your job application materials and prepare for interviews with AI-powered optimization. Instructions When a user needs help with job applications: Identify Task Type : Resume tailoring for specific job Cover letter generation Interview preparation Skills gap analysis Application strategy Gather Information : From User : Current resume (text or structured format) Target job posting (full description) LinkedIn profile (optional) Career goals and preferences Specifi...
 63
16740 groove-admin-doctor andreadellacorte/groove
groove-admin-doctor Outcome All groove sub-skill health checks are run and a consolidated summary is reported. User knows exactly what is working, what is misconfigured, and what action to take for any failure. Acceptance Criteria /groove-utilities-task-doctor and /groove-utilities-memory-doctor are run Companion skill presence is checked directly Results are shown per sub-skill with pass/fail per check Overall status is shown: all healthy, or N issues found Each failure includes a specific reme...
 63
16741 wiki-page-writer sickn33/antigravity-awesome-skills
Wiki Page Writer You are a senior documentation engineer that generates comprehensive technical documentation pages with evidence-based depth. When to Activate User asks to document a specific component, system, or feature User wants a technical deep-dive with diagrams A wiki catalogue section needs its content generated Depth Requirements (NON-NEGOTIABLE) TRACE ACTUAL CODE PATHS — Do not guess from file names. Read the implementation. EVERY CLAIM NEEDS A SOURCE — File path + function/class name...
 63
16742 godot-ui-containers thedivergentai/gd-agentic-skills
UI Containers Container auto-layout, size flags, anchors, and split ratios define responsive UI systems. Available Scripts responsive_layout_builder.gd Expert container builder with breakpoint-based responsive layouts. responsive_grid.gd Auto-adjusting GridContainer that changes column count based on available width. Essential for responsive inventory screens and resizing windows. NEVER Do in UI Containers NEVER set child position/size manually in Container — child.position = Vector2(10, 10) ins...
 63
16743 technical-specification secondsky/claude-skills
Create comprehensive technical specifications that define system requirements, architecture, implementation details, and acceptance criteria for software projects. When to Use - Feature specifications - System design documents - Requirements documentation (PRD) - Architecture decision records (ADR) - Technical proposals - RFC (Request for Comments) - API design specs - Database schema designs Technical Specification Template ``` Technical Specification: [Feature Name] Document Sta...
 63
16744 jupyter openhands/skills
Jupyter Notebook Guide Notebooks are JSON files. Cells are in nb['cells'], each has source (list of strings) and cell_type ('code', 'markdown', or 'raw'). Modifying Notebooks import json with open('notebook.ipynb') as f: nb = json.load(f) Modify nb['cells'][i]['source'], then: with open('notebook.ipynb', 'w') as f: json.dump(nb, f, indent=1) Executing & Converting jupyter nbconvert --to notebook --execute --inplace notebook.ipynb Execute in place jupyter nbconvert --to html noteboo...
 63
16745 devops-expert cin12211/orca-q
DevOps Expert You are an advanced DevOps expert with deep, practical knowledge of CI/CD pipelines, containerization, infrastructure management, monitoring, security, and performance optimization based on current industry best practices. When invoked: If the issue requires ultra-specific expertise, recommend switching and stop: Docker container optimization, multi-stage builds, or image management → docker-expert GitHub Actions workflows, matrix builds, or CI/CD automation → github-actions-ex...
 63
16746 code formatting openshift/hypershift
Code Quality, Formatting and Conventions Code Formatting and Linting Use make lint-fix after writing Go code to automatically fix most linting issues Run make verify to verify both linting and tests pass before committing For markdown files , use make verify-codespell to catch spelling errors Test Conventions - MANDATORY NON-NEGOTIABLE RULE : Every Go test name MUST follow this exact format: name : "When <condition>, it should <expected behavior>" Examples: name : "When NodePool has valid image ...
 63
16747 go-testing autumnsgrove/groveengine
Go Testing Guidelines for writing clear, maintainable Go tests following Google's style. Useful Test Failures Normative: Test failures must be diagnosable without reading the test source. Every failure message should include: What caused the failure The function inputs The actual result (got) The expected result (want) Failure Message Format Use the standard format: YourFunc(%v) = %v, want %v // Good: if got := Add(2, 3); got != 5 { t.Errorf("Add(2, 3) = %d, want %d", got, 5) } // Ba...
 63
16748 docx jim60105/copilot-prompt
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...
 63
16749 vueuse-components-skilld harlan-zw/vue-ecosystem-skills
vueuse/vueuse @vueuse/components Renderless components for VueUse Version: 14.2.1 (Feb 2026) Deps: @vueuse/shared@14.2.1, @vueuse/core@14.2.1 Tags: next: 5.0.0 (Jun 2021), alpha: 14.0.0-alpha.3 (Sep 2025), beta: 14.0.0-beta.1 (Sep 2025), latest: 14.2.1 (Feb 2026) References: Docs — API reference, guides API Changes This section documents version-specific API changes for @vueuse/components — prioritize recent major/minor releases. BREAKING: @vueuse/components v14+ requires Vue 3.5+, following cor...
 63
16750 release max-sixty/worktrunk
Release Workflow This skill provides a systematic workflow for creating and publishing releases for the linear-cli project. It handles changelog management, version bumping, testing, and tagging. When to Use Use this skill when preparing to release a new version of linear-cli. The workflow ensures all changes are documented, tests pass, and versions are properly tagged before publishing. Prerequisites Ensure the following tools are available: changelog skill for changelog management svbump for v...
 63