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...
27,427
总 Skills
160.9M
总安装量
2,740
贡献者
# Skill 仓库 描述 安装量
23551 archive-conversation nweii/agent-stuff
AI Conversation Archival Summary Create an archival summary of an AI conversation that captures its intellectual journey, key insights, or technical work session logs. Document either how thinking evolved throughout the discussion or the specific actions and technical decisions made during a work session. Deep Analysis Requirements Conduct a thorough analysis of the entire conversation: Read through completely first, identifying all conceptual threads, task sequences, and transitions Note pa...
 46
23552 github-repo-hunter breverdbidder/life-os
GitHub Repository Hunter Autonomous agent for discovering, evaluating, and integrating relevant GitHub repositories into BidDeed.AI and Life OS ecosystems. Mission Hunt GitHub for open-source projects that could enhance: BidDeed.AI - Foreclosure auction intelligence (scrapers, ML models, document processing, workflow automation) Life OS - Productivity, ADHD management, swimming analytics, dual-timezone coordination Core Workflow 1. Discovery Phase Search GitHub API using domain-specific keywords...
 46
23553 alicloud-ai-multimodal-qvq-test cinience/alicloud-skills
Category: test Minimal Viable Test Goals Validate that the QVQ skill includes the visual reasoning models and sample payload. Prerequisites Target skill: skills/ai/multimodal/alicloud-ai-multimodal-qvq Recommended check python skills/ai/multimodal/alicloud-ai-multimodal-qvq/scripts/prepare_qvq_request.py \ --output output/alicloud-ai-multimodal-qvq/request.json
 46
23554 canonical-format-checker panaversity/agentfactory
Canonical Format Checker Overview Prevent format drift by verifying content follows authoritative canonical sources. When teaching a pattern that exists elsewhere in the platform (skills, subagents, ADRs, etc.), this skill ensures the taught format matches the canonical source. Why this matters : The Chapter 14 format drift failure occurred because the lesson taught skill format differently from Chapter 5 (canonical source). Students learned incorrect patterns that contradicted earlier chapters....
 46
23555 research synthesizer eddiebe147/claude-settings
Research Synthesizer Synthesize insights from multiple research sources into cohesive analysis When to Use This Skill Use this skill when you need to: Analyze data and extract insights Conduct thorough investigation Synthesize complex information Not recommended for: Tasks requiring creative content generation business operations Quick Reference Action Command/Trigger Create research synthesizer research synthesis Review and optimize review research synthesizer Get best practices research synthe...
 46
23556 hitpay hit-pay/agent-skills
Payment gateway integration for APAC businesses using Next.js and JavaScript/TypeScript. Supports card payments via redirect and QR-based payments (PayNow, GrabPay, etc.) via embedded QR codes. When to Apply Reference this skill when: - Integrating HitPay payment gateway - Creating payment checkout flows - Implementing QR code payments (PayNow, GrabPay, ShopeePay) - Handling payment webhooks - Processing refunds Step 1: Determine Payment Methods Ask which payment methods the customer ...
 46
23557 git-expert cin12211/orca-q
Git Expert You are an expert in Git version control with deep knowledge of advanced workflows, branching strategies, collaboration patterns, and best practices. You help teams manage code efficiently and resolve complex version control issues. Core Expertise Essential Git Commands Basic Operations: Initialize repository git init git clone https://github.com/user/repo.git Check status and differences git status git diff Unstaged changes git diff --staged Staged changes git diff main .. .featu...
 46
23558 cto lotosbin/claude-skills
No SKILL.md available for this skill. View on GitHub
 46
23559 elasticsearch-index-manager jeremylongshore/claude-code-plugins-plus-skills
Elasticsearch Index Manager Purpose This skill provides automated assistance for elasticsearch index manager tasks within the DevOps Advanced domain. When to Use This skill activates automatically when you: Mention "elasticsearch index manager" in your request Ask about elasticsearch index manager patterns or best practices Need help with advanced devops skills covering kubernetes, terraform, advanced ci/cd, monitoring, and infrastructure as code. Capabilities Provides step-by-step guidance ...
 46
23560 ld-permissions lightdash/lightdash
Permissions & Authorization Guide This skill helps you work with Lightdash's CASL-based permissions system, including scopes, custom roles, and authorization enforcement. What do you need help with? Add a new scope/permission - Step-by-step guide to add a new permission Debug a permission issue - Troubleshoot why a user can't access something Understand the permission flow - Learn how permissions work end-to-end Work with custom roles - Create or modify custom roles with specific scopes Quick Re...
 46
23561 workflow-test-fix catlog22/claude-code-workflow
Workflow Test Fix Unified test-fix orchestrator that combines test planning generation (Phase 1-4) with iterative test-cycle execution (Phase 5) into a single end-to-end pipeline. Creates test sessions with progressive L0-L3 test layers, generates test tasks, then executes them with adaptive fix cycles until pass rate >= 95% or max iterations reached. Architecture Overview ┌───────────────────────────────────────────────────────────────────────────┐ │ Workflow Test Fix Orchestrator (SKILL.md) ...
 46
23562 question-refiner liangdabiao/claude-code-stock-deep-research-agent
Question Refiner Role You are a Deep Research Question Refiner specializing in crafting, refining, and optimizing prompts for deep research. Your primary objectives are: Ask clarifying questions first to ensure full understanding of the user's needs, scope, and context Generate structured research prompts that follow best practices for deep research Eliminate the need for external tools (like ChatGPT) - everything is done within Claude Code Core Directives Do Not Answer the Research Query Dire...
 46
23563 sports-trivia-builder onewave-ai/claude-skills
Sports Trivia Builder Generate sports trivia questions by sport/era/difficulty. Multiple formats with obscure stats, fun facts, pub quiz ready content. Instructions You are an expert sports historian and trivia creator. Generate engaging trivia questions across sports, eras, and difficulty levels. Include: multiple choice, true/false, fill-in-blank formats, obscure stats, fun facts, answer explanations with context, and difficulty ratings. Output Format Sports Trivia Builder Output Generat...
 46
23564 nushell-usage ypares/agent-skills
Nushell Usage Patterns Critical Distinctions Pipeline Input vs Parameters CRITICAL: Pipeline input ($in) is NOT interchangeable with function parameters! ❌ WRONG - treats $in as first parameter def my-func [list: list, value: any] { $list | append $value } ✅ CORRECT - declares pipeline signature def my-func [value: any]: list -> list { $in | append $value } Usage [1 2 3] | my-func 4 Works correctly my-func [1 2 3] 4 ERROR! my-func doesn't take positional params This applie...
 46
23565 commit-message junoh-moon/skills
Commit Message Convention Based on the following git diff of staged changes, generate a conventional commit message with a clear subject line (max 72 chars) and body (wrapped at 72 chars). The message should clearly explain what changed and why. To create a commit message, focus on staged files ONLY. Run git diff --cached to see the changes. Sometimes, you have to git add files by yourself -- pre-commit fail, unstaged files, or manual edit by a user. In this case, NEVER USE git add -u or git ad...
 45
23566 outlier-detective dkyazzentwatwa/chatgpt-skills
Detect anomalies and outliers in numeric data using multiple methods. Features - Statistical Methods: Z-score, IQR, Modified Z-score - ML Methods: Isolation Forest, LOF, DBSCAN - Visualization: Box plots, scatter plots - Multi-Column: Analyze multiple variables - Reports: Detailed outlier reports - Flexible Thresholds: Configurable sensitivity Quick Start ``` from outlier_detective import OutlierDetective detective = OutlierDetective() detective.load_csv("sales_data.csv") Detect ou...
 45
23567 cursor-agent-supervisor ypares/agent-skills
Agent Supervisor You can start subagents (e.g. to work on a specific JJ revision) with: Create a conversation with a sub-agent: cursor-agent --print --model <model-name> create-chat Prints a conversation uuid Give a task to the sub-agent: (command will finish when sub-agent is done) cursor-agent --print --resume <conversation-uuid> "...description of the subagent's task..." Model Selection cursor-agent --print --model unknown-model will print an error that will list available models. Un...
 45
23568 android_ui_verification sickn33/antigravity-awesome-skills
Android UI Verification Skill This skill provides a systematic approach to testing React Native applications on an Android emulator using ADB commands. It allows for autonomous interaction, state verification, and visual regression checking. When to Use Verifying UI changes in React Native or Native Android apps. Autonomous debugging of layout issues or interaction bugs. Ensuring feature functionality when manual testing is too slow. Capturing automated screenshots for PR documentation. 🛠 Prereq...
 45
23569 risk assessor eddiebe147/claude-settings
Risk Assessor The Risk Assessor skill helps teams proactively identify, analyze, prioritize, and mitigate project risks before they become problems. It uses systematic risk management frameworks to surface threats, evaluate their likelihood and impact, and create actionable mitigation strategies. This skill excels at conducting pre-mortem exercises, creating risk registers, assessing probability and impact, developing contingency plans, and establishing early warning indicators to catch risks be...
 45
23570 figma-prototyping dylantarre/animation-principles
Implement all 12 Disney animation principles using Figma's prototyping and Smart Animate features. 1. Squash and Stretch - Create two frames: normal and squashed states - Scale element: `width: 120%`, `height: 80%` - Connect with Smart Animate - Use "Ease In and Out" timing ``` Frame 1: Circle 100x100 Frame 2: Circle 120x80 (squashed) Interaction: Smart Animate, 150ms ``` 2. Anticipation Create 3 frames: - Idle - Starting position - Anticipate - Wind-up (move opposite to action) - ...
 45
23571 background-job-orchestrator erichowens/some_claude_skills
Background Job Orchestrator Expert in designing and implementing production-grade background job systems that handle long-running tasks without blocking API responses. When to Use ✅ Use for: Long-running tasks (email sends, report generation, image processing) Batch operations (bulk imports, exports, data migrations) Scheduled tasks (daily digests, cleanup jobs, recurring reports) Tasks requiring retry logic (external API calls, flaky operations) Priority-based processing (premium users firs...
 45
23572 code-documentation-generator dengineproblem/agents-monorepo
Эксперт по созданию качественной документации кода. Основные принципы - Clarity > Sophistication — ясность важнее сложности - Progressive disclosure — от общего к деталям - Consistency — единообразие форматирования - Accuracy — синхронизация с кодом - Accessibility — для разных уровней разработчиков JSDoc (JavaScript/TypeScript) ``` / * Calculates the total price including tax and discounts. * * @param {number} basePrice - The original price before modifications * @param {number} t...
 45
23573 systematic-debugging zenobi-us/dotfiles
Systematic Debugging Overview Random fixes waste time and create new bugs. Quick patches mask underlying issues. Core principle: ALWAYS find root cause before attempting fixes. Symptom fixes are failure. Violating the letter of this process is violating the spirit of debugging. The Iron Law NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST If you haven't completed Phase 1, you cannot propose fixes. When to Use Use for ANY technical issue: Test failures Bugs in production Unexpected behavior Perfor...
 45
23574 release-please-configuration laurigates/claude-plugins
Expert knowledge for configuring Google's release-please for automated releases. Core Files | `release-please-config.json` | Package configuration, changelog sections, extra-files | `.release-please-manifest.json` | Current versions for each package | `.github/workflows/release-please.yml` | GitHub Actions workflow Monorepo Configuration Critical Settings for Monorepos ``` { "$schema": "https://raw.githubusercontent.com/googleapis/release-please/main/schemas/config.json", "in...
 45
23575 deep-research heyvhuang/ship-faster
Deep Research Core System Instructions Purpose: Deliver citation-backed, verified research reports through 8-phase pipeline (Scope → Plan → Retrieve → Triangulate → Synthesize → Critique → Refine → Package) with source credibility scoring and progressive context management. Context Strategy: This skill uses 2025 context engineering best practices: Static instructions cached (this section) Progressive disclosure (load references only when needed) Avoid "loss in the middle" (critical info at start...
 45
23576 styling-system mgd34msu/goodvibes-plugin
Resources scripts/ validate-styling.sh references/ styling-comparison.md Styling System This skill guides you through CSS architecture decisions and implementation using GoodVibes precision tools. Use this workflow when setting up styling infrastructure, creating design systems, or implementing theming and responsive patterns. When to Use This Skill Load this skill when: Setting up a new project's styling infrastructure Choosing between Tailwind, CSS Modules, CSS-in-JS, or vanilla CSS Implementi...
 45
23577 executing-plans guanyang/antigravity-skills
Executing Plans Overview Load plan, review critically, execute all tasks, report when complete. Announce at start: "I'm using the executing-plans skill to implement this plan." Note: Tell your human partner that Superpowers works much better with access to subagents. The quality of its work will be significantly higher if run on a platform with subagent support (such as Claude Code or Codex). If subagents are available, use superpowers:subagent-driven-development instead of this skill. The Proce...
 45
23578 changelog railwayapp/railway-skills
You are a witty and enthusiastic product marketer tasked with creating a fun, engaging change log for an internal development team. Your goal is to summarize the latest merges to the main branch, highlighting new features, bug fixes, and giving credit to the hard-working developers. Time Period For daily changelogs: Look at PRs merged in the last 24 hours For weekly summaries: Look at PRs merged in the last 7 days Always specify the time period in the title (e.g., "Daily" vs "Weekly") Default: G...
 45
23579 athlete-social-media-manager onewave-ai/claude-skills
Athlete Social Media Manager Create brand-safe content for athletes. Personal branding strategy, engagement optimization, crisis communication, sponsor integration. Instructions You are an expert athlete brand manager and social media strategist. Create: brand-safe content strategies, personal branding plans, engagement optimization tactics, crisis communication templates, sponsor integration ideas, and platform-specific content calendars. Output Format Athlete Social Media Manager Output ...
 45
23580 staging-mastery dylantarre/animation-principles
Staging Mastery The Clarity Principle Staging is the presentation of an idea so that it is unmistakably clear. Borrowed from theater, this principle addresses animation's core challenge: the audience has limited time to comprehend each moment. Poor staging creates confusion; masterful staging creates effortless understanding. Core Theory One Idea Per Moment: The eye cannot process competing focal points simultaneously. Every frame should have exactly one primary point of interest. Secondary e...
 45
23581 us-stock-analysis nicepkg/ai-workflow
US Stock Analysis Overview Perform comprehensive analysis of US stocks covering fundamental analysis (financials, business quality, valuation), technical analysis (indicators, trends, patterns), peer comparisons, and generate detailed investment reports. Fetch real-time market data via web search tools and apply structured analytical frameworks. Data Sources Always use web search tools to gather current market data: Primary Data to Fetch: Current stock price and trading data (price, volume, 52-w...
 45
23582 telegram himself65/finance-skills
📬 Telegram CLI Fast Telegram CLI for reading, searching, and sending messages. 🎯 When to Use Use this skill when the user: Asks to check Telegram messages or inbox Wants to search Telegram for a topic/keyword Wants to send a Telegram message or reply to one Asks about a Telegram group, contact, or chat Wants to see unread messages Needs to look up group members or admins Wants to mute/unmute a noisy chat or group Needs to kick/remove a user from a group Wants to export or sync chat history to fi...
 45
23583 vendor manager eddiebe147/claude-settings
Vendor Manager Expert vendor and supplier management system that helps you evaluate vendors, manage contracts, track performance, negotiate terms, and optimize procurement. This skill provides structured workflows for vendor selection, performance monitoring, and relationship management based on supply chain and procurement best practices. Effective vendor management reduces costs, mitigates risk, and ensures reliable supply. This skill helps you build strategic vendor relationships, hold suppli...
 45
23584 diagnostic-issue-resolver terrylica/cc-skills
Diagnostic Issue Resolver Diagnose and fix common TTS + Telegram bot issues through systematic symptom collection, automated diagnostics, and targeted fixes. Platform : macOS (Apple Silicon) When to Use This Skill TTS audio is not playing or sounds wrong Telegram bot is not responding to messages Kokoro engine errors or timeouts Lock file appears stuck Audio plays twice (race condition) MLX Metal acceleration is not working Queue appears full or backed up Requirements Access to ~/.claude/automat...
 45
23585 due diligence coordinator eddiebe147/claude-settings
Due Diligence Coordinator Coordinate and prepare for investor due diligence with organized data rooms When to Use This Skill Use this skill when you need to: Improve business operations and strategy Make data-driven business decisions Optimize processes and outcomes Not recommended for: Tasks requiring creative design work technical coding Quick Reference Action Command/Trigger Create due diligence coordinator due diligence Review and optimize review due diligence coordinator Get best practices ...
 45
23586 ppt-deck cklxx/elephant.ai
ppt-deck Generate presentation decks from topic to deliverable PPTX/PDF, following storyline templates (SCQA, Pyramid, Before/After/Bridge), accessibility best practices, and 10/20/30 guidelines. All slide generation, layout, and export logic are handled by run.py. 调用 python3 skills/ppt-deck/run.py create --topic 'Q1 Review' --audience leadership --format pptx
 45
23587 release-checklist yonatangross/orchestkit
Release Checklist Sequential release gate for OrchestKit. Each step reports [PASS] or [FAIL] . Stop on first failure, suggest a fix, then continue after user confirmation. Load details: Read("${CLAUDE_PLUGIN_ROOT}/skills/release-checklist/references/release-flow.md") for why the order matters and hotfix guidance. Quick Reference Category Rules Impact When to Use Pre-Release Gates 2 CRITICAL Before every release commit Release Commit 2 HIGH Staging, committing, tagging, pushing Total: 4 rules acr...
 45
23588 naming-rules dengineproblem/agents-monorepo
Naming Rules Интерактивный помощник для настройки правил именования Campaign/AdSet/Ad и структуры аккаунта. Твои задачи Определить аккаунт для настройки Задать вопросы о структуре и нейминге Собрать существующие кампании из аккаунта Сгенерировать файл правил config/naming/{account}_naming.md Обновить бриф аккаунта (добавить ссылку на naming rules) Что создаётся в результате .claude/ads-agent/config/ └── naming/ └── {account}_naming.md ← правила нейминга для аккаунта Workflow (7 шагов) Шаг 0: О...
 45
23589 id8labs agent suite eddiebe147/claude-settings
ID8Labs Agent Suite A complete idea-to-exit pipeline for solo builders. 8 interconnected agents manage the entire product lifecycle from initial concept through exit. Agents Agent Role Architect Product design and technical architecture Scout Market research and opportunity discovery Launch Go-to-market strategy and execution Growth User acquisition and retention strategies Ops Operations, automation, and efficiency Tracker Metrics, analytics, and progress tracking Today Daily planning and prior...
 45
23590 uniappx-project-creator teachingai/full-stack-skills
Use this skill whenever the user wants to: - Create a new uni-app-x project from scratch - Initialize uni-app-x project structure with TypeScript and Vue 3 - Set up development environment for uni-app-x - Generate project templates with TypeScript configuration - Configure manifest.json and pages.json for uni-app-x - Create uni-app-x pages and components with TypeScript - Set up uni-app-x project with HBuilderX or CLI How to use this skill To create a uni-app-x project with a single co...
 45
23591 linear-documents finesssee/linear-cli
Documents List documents linear-cli d list linear-cli d list --output json Get document linear-cli d get DOC_ID linear-cli d get DOC_ID --output json Create document linear-cli d create "Design Doc" -p PROJECT_ID linear-cli d create "RFC" -p PROJECT_ID --id-only Update document linear-cli d update DOC_ID --title "New Title" linear-cli d update DOC_ID --content "New content" Flags Flag Purpose -p PROJECT Project ID --id-only Return ID only --output json JSON output
 45
23592 v3 performance optimization proffesor-for-testing/agentic-qe
V3 Performance Optimization What This Skill Does Validates and optimizes claude-flow v3 to achieve industry-leading performance through Flash Attention, AgentDB HNSW indexing, and comprehensive system optimization with continuous benchmarking. Quick Start Initialize performance optimization Task ( "Performance baseline" , "Establish v2 performance benchmarks" , "v3-performance-engineer" ) Target validation (parallel) Task ( "Flash Attention" , "Validate 2.49x-7.47x speedup target" , "v3-perfor...
 45
23593 toxic-manager-translator dedalus-erp-pas/foundation-skills
This skill transforms raw emotional reactions, venting messages, or frustrated communications from collaborators into professional, strategic responses appropriate for dealing with difficult or toxic managers. It helps maintain professionalism while protecting the collaborator's interests and well-being. When to Use This Skill Activate when the user: - Shares a frustrated message they want to send to their manager - Asks to "make this professional" or "tone this down" for a difficult boss ...
 45
23594 review-quality heyvhuang/ship-faster
Quality Review (Unified) Goal: turn “is this change good?” into a repeatable review with a clear merge/production readiness verdict. This skill intentionally merges three review lenses: Merge readiness (requirements alignment + risk + verification) Code maintainability (Clean Code-style review) Documentation consistency (README/docs vs implementation) This is the single entry point for Ship Faster reviews. It includes an internal auto-triage: Always run the unified review (this skill). If React/...
 45
23595 flutter conventions & best practices kaakati/rails-enterprise-dev
Layer-first (recommended for Clean Architecture): ``` lib/ ├── domain/ ├── data/ └── presentation/ ``` Feature-first (alternative): ``` lib/ └── features/ ├── auth/ │ ├── domain/ │ ├── data/ │ └── presentation/ └── profile/ ``` Null Safety ``` // Use late for non-nullable fields initialized later class MyController extends GetxController { late final UserRepository repository; @override void onInit() { super.onInit(); repository = Get.find(); ...
 45
23596 resend-webhooks hookdeck/webhook-skills
Resend Webhooks When to Use This Skill Setting up Resend webhook handlers Debugging signature verification failures Understanding Resend event types and payloads Handling email delivery events (sent, delivered, bounced, etc.) Processing inbound emails via email.received events Essential Code (USE THIS) Express Webhook Handler (Using Resend SDK) const express = require ( 'express' ) ; const { Resend } = require ( 'resend' ) ; const resend = new Resend ( process . env . RESEND_API_KEY ) ; const ap...
 45
23597 test-report laurigates/claude-plugins
Context Quick status check without re-running tests. Reads cached results from last test execution. Use when: Checking current test health Quick status update for standup Reviewing before deciding next action Parameters --history : Show trend from recent runs --coverage : Include coverage summary --flaky : Identify potentially flaky tests Cached Result Locations Framework Cache Location pytest .pytest_cache/ , htmlcov/ Vitest node_modules/.vitest/ Jest coverage/ , .jest-cache/ Playwright test-re...
 45
23598 php vapvarun/claude-backup
PHP Development Modern PHP 8.x development patterns and best practices. PHP 8.x Features Constructor Property Promotion // Before PHP 8 class User { private string $name; private int $age; public function __construct(string $name, int $age) { $this->name = $name; $this->age = $age; } } // PHP 8+ class User { public function __construct( private string $name, private int $age, private bool $active = true ) {} } Named Arguments f...
 45
23599 vps-checkup jmerta/codex-skills
Provide: - A read-only report using `references/report-template.md`. - A prioritized list of recommended fixes and which ones require explicit confirmation. - The exact commands run (or requested if the user ran them manually).
 45
23600 alicloud-ai-multimodal-qwen-omni cinience/alicloud-skills
Category: provider Model Studio Qwen Omni Validation mkdir -p output/alicloud-ai-multimodal-qwen-omni python -m py_compile skills/ai/multimodal/alicloud-ai-multimodal-qwen-omni/scripts/prepare_omni_request.py && echo "py_compile_ok" > output/alicloud-ai-multimodal-qwen-omni/validate.txt Pass criteria: command exits 0 and output/alicloud-ai-multimodal-qwen-omni/validate.txt is generated. Critical model names Use one of these exact model strings: qwen3-omni-flash qwen3-omni-flash-realtime qwen-omn...
 45