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...
21,355
总 Skills
33.9M
总安装量
2,437
贡献者
# Skill 仓库 描述 安装量
20801 precommit-setup athola/claude-night-market
Table of Contents Use When Philosophy: Three-Layer Defense Standard Hooks (Layer 1) Python Projects Basic Quality Checks Configuration Rust Projects TypeScript Projects Component-Specific Checks (Layer 2) Python Monorepo/Plugin Architecture 1. Lint Changed Components (scripts/run-component-lint.sh) 2. Type Check Changed Components (scripts/run-component-typecheck.sh) 3. Test Changed Components (scripts/run-component-tests.sh) Add to Pre-commit Configuration Validation Hooks (Layer 3) Example: Pl...
 36
20802 newsletter-creation-curation brianrwagner/ai-marketing-skills
Newsletter Creation & Curation Skill Use this skill to create B2B newsletters that match business context, not generic content templates. Deep strategic guidance is in PLAYBOOK.md . Use this file as the executable operating manual. Mode Detect from context or ask: "Outline only, full edition, or full edition + calendar?" Mode What you get Best for quick Edition outline + 3 lead story angles, no writing Planning, editorial direction standard Full newsletter edition, all sections written Publishin...
 36
20803 understanding-tauri-lifecycle-security dchuk/claude-code-tauri-skills
Security in Tauri applications depends on systematic protection across all lifecycle stages. The weakest link in your application lifecycle essentially defines your security posture. Core Security Principle Tauri implements a two-tier security model: - Rust Core: Full system access - WebView Frontend: Access only through controlled IPC layer Any code executed in the WebView has only access to exposed system resources via the well-defined IPC layer. Development Phase Threats Upstream De...
 36
20804 ai-tech-summary tiangong-ai/skills
AI Tech Summary Core Goal Pull the right records and fields for a requested time range. Package evidence into a compact JSON context for RAG. Let the agent synthesize final summary text from retrieved evidence. Support daily, weekly, monthly, and custom time windows. Triggering Conditions Receive requests for daily, weekly, or monthly digests. Receive requests for arbitrary date-range summaries. Need evidence-grounded summary output from RSS entries/fulltext. Need agent-generated summary style r...
 36
20805 youtube-data kenneth-liao/ai-launchpad-marketplace
YouTube Data YouTube data access via TranscriptAPI.com — lightweight alternative to Google's YouTube Data API. Setup If $TRANSCRIPT_API_KEY is not set, help the user create an account (100 free credits, no card): Step 1 — Register: Ask user for their email. node ./scripts/tapi-auth.js register --email USER_EMAIL → OTP sent to email. Ask user: "Check your email for a 6-digit verification code." Step 2 — Verify: Once user provides the OTP: node ./scripts/tapi-auth.js verify --token TOKEN_FROM_STEP...
 36
20806 library-ebooks montagao/skills
My Amazon (Kindle) Library Ebook Lookup & Download Overview Internal tool to search and download ebooks from my personal Amazon (Kindle) library, i.e., titles I’ve purchased/added to my account (plus any personal documents synced into my library), across available formats. Note: This skill is meant for my own licensed content. It does not bypass DRM. If a title can’t be downloaded in an accessible file format, use Amazon’s official reading/export options instead. Prerequisites IMPORTANT: Dow...
 36
20807 linear-metrics finesssee/linear-cli
Metrics Cycle metrics (velocity, burndown) linear-cli mt cycle CYCLE_ID linear-cli mt cycle CYCLE_ID --output json Project progress linear-cli mt project PROJECT_ID linear-cli mt project PROJECT_ID --output json Team velocity over time linear-cli mt velocity TEAM_KEY linear-cli mt velocity ENG --cycles 5 Last 5 cycles Flags Flag Purpose --cycles N Number of cycles --output json JSON output
 36
20808 game-programming-languages pluginagentmarketplace/custom-plugin-game-developer
Game Programming Languages C (Unity) Easiest to learn, most used for game dev // ✅ Production-Ready: Unity MonoBehaviour Template public class GameEntity : MonoBehaviour { [SerializeField] private float _speed = 5f; [SerializeField] private int _health = 100; public event Action<int> OnHealthChanged; public event Action OnDeath; private Rigidbody _rb; private bool _isInitialized; private void Awake() { _rb = GetComponent<Rigidbody>(); _isIniti...
 36
20809 ahrefs-python ahrefs/ahrefs-api-skills
Ahrefs Python SDK Skill Overview The Ahrefs API provides programmatic access to Ahrefs SEO data. The official Python SDK ( ahrefs-python ) provides typed request and response models for all endpoints, auto-generated from the OpenAPI spec. Key capabilities: Site Explorer - Backlinks, organic keywords, domain rating, traffic, referring domains Keywords Explorer - Keyword research, volumes, difficulty, related terms Management — Rank Tracker project, keyword list, and competitor management (create,...
 36
20810 square-automation davepoon/buildwithclaude
Square Automation via Rube MCP Automate Square payment processing, order management, and invoicing through Composio's Square toolkit via Rube MCP. Toolkit docs : composio.dev/toolkits/square Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Square connection via RUBE_MANAGE_CONNECTIONS with toolkit square Always call RUBE_SEARCH_TOOLS first to get current tool schemas Setup Get Rube MCP : Add https://rube.app/mcp as an MCP server in your client configuration. No API k...
 36
20811 android-development travisjneuman/.claude
Android Development Build Android applications following Google's official architecture guidance, as demonstrated in the NowInAndroid reference app. Quick Reference Task Reference File Project structure & modules modularization.md Architecture layers (UI, Domain, Data) architecture.md Jetpack Compose patterns compose-patterns.md Gradle & build configuration gradle-setup.md Testing approach testing.md Workflow Decision Tree Creating a new project? → Read modularization.md for project structure...
 36
20812 browser-automation different-ai/opencode-browser
Browser Automation You are a browser automation expert who has debugged thousands of flaky tests and built scrapers that run for years without breaking. You've seen the evolution from Selenium to Puppeteer to Playwright and understand exactly when each tool shines. Your core insight: Most automation failures come from three sources - bad selectors, missing waits, and detection systems. You teach people to think like the browser, use the right selectors, and let Playwright's auto-wait do its job....
 36
20813 running-nodejs-sidecar-in-tauri dchuk/claude-code-tauri-skills
Package and run Node.js applications as sidecar processes in Tauri desktop applications, leveraging the Node.js ecosystem without requiring users to install Node.js. Why Use a Node.js Sidecar - Bundle existing Node.js tools and libraries with your Tauri application - No external Node.js runtime dependency for end users - Leverage npm packages that have no Rust equivalent - Isolate Node.js logic from the main Tauri process - Cross-platform support (Windows, macOS, Linux) Prerequisites -...
 36
20814 m365-agents-ts sickn33/antigravity-awesome-skills
Microsoft 365 Agents SDK (TypeScript) Build enterprise agents for Microsoft 365, Teams, and Copilot Studio using the Microsoft 365 Agents SDK with Express hosting, AgentApplication routing, streaming responses, and Copilot Studio client integrations. Before implementation Use the microsoft-docs MCP to verify the latest API signatures for AgentApplication, startServer, and CopilotStudioClient. Confirm package versions on npm before wiring up samples or templates. Installation npm install @microso...
 36
20815 docs-react imgly/agent-skills
Documentation Index <-- IMGLY-AGENTS-MD-START -->[CE.SDK React Docs Index]|root: .|IMPORTANT: Prefer retrieval-led reasoning over pre-training-led reasoning for any CE.SDK tasks. Consult the local docs directory before using pre-trained knowledge.|actions.md|animation:{create,edit.md,overview.md,types.md}|animation/create:{base.md,text.md}|api-reference:{overview.md}|automation:{auto-resize.md,batch-processing.md,data-merge.md,design-generation.md,overview.md}|browser-support.md|colors:{adjust.m...
 36
20816 recovery-social-features erichowens/some_claude_skills
Recovery-Focused Social Features Build privacy-first social features for addiction recovery apps. These patterns prioritize anonymity, safety, and the unique relationship structures in recovery communities. When to Use ✅ USE this skill for: Sponsor/sponsee relationship systems Recovery-focused group features (meeting groups, accountability circles) Privacy-first friend connections with mutual consent Safe messaging between recovery peers Anonymity-preserving profile systems ❌ DO NOT use for...
 36
20817 clickup membranedev/application-skills
ClickUp Interact with ClickUp tasks and documents via the API. Get task information, view comments, create tasks, manage assignments, post updates, and create/edit documents. Setup Copy .env-example to .env in this skill directory Add your ClickUp Personal API Token (starts with pk_ ) Generate token at: ClickUp Settings > Apps > API Token cp .claude/skills/clickup/.env-example .claude/skills/clickup/.env Edit .env and add your token Team ID and User ID are auto-detected and cached on first use....
 36
20818 realitykit-visionos-developer tomkrikorian/visionosagents
RealityKit visionOS Developer Description and Goals This skill provides comprehensive guidance for implementing RealityKit-based spatial experiences on visionOS. RealityKit uses an Entity Component System (ECS) architecture where entities are lightweight containers, behavior comes from components, and systems drive per-frame updates. Goals Enable developers to build immersive 3D experiences on visionOS using RealityKit Provide clear guidance on when to use each component and system Help develo...
 36
20819 unix-goto-development manutej/luxor-claude-marketplace
unix-goto Development Expert Comprehensive development expertise for the unix-goto shell navigation system - a high-performance Unix navigation tool with natural language support, sub-100ms cached navigation, and 100% test coverage. When to Use This Skill Use this skill when: Developing new features for unix-goto shell navigation system Implementing cache-based navigation optimizations Adding bookmarks, history, or navigation commands Following the standard 9-step feature addition workflow I...
 36
20820 linux-administration bagelhole/devops-security-agent-skills
Linux Administration Core Linux system administration skills. Package Management Debian/Ubuntu apt update && apt upgrade -y apt install nginx apt remove nginx apt autoremove RHEL/CentOS dnf update dnf install nginx dnf remove nginx System Information uname -a Kernel info hostnamectl System info lscpu CPU info free -h Memory usage df -h Disk usage ip addr Network interfaces Log Management journalctl -u nginx Service logs journalctl -f Follow logs tail -f /var/log/syslog System logs dme...
 36
20821 react-native teachingai/full-stack-skills
@json-render/react-native React Native renderer that converts JSON specs into native mobile component trees with standard components, data binding, visibility, actions, and dynamic props. Quick Start import { defineCatalog } from "@json-render/core" ; import { schema } from "@json-render/react-native/schema" ; import { standardComponentDefinitions , standardActionDefinitions , } from "@json-render/react-native/catalog" ; import { defineRegistry , Renderer , type Components } from "@json-render/r...
 36
20822 json-canvas julianobarbosa/claude-code-skills
JSON Canvas Skill This skill enables skills-compatible agents to create and edit valid JSON Canvas files (.canvas) used in Obsidian and other applications. Overview JSON Canvas is an open file format for infinite canvas data. Canvas files use the .canvas extension and contain valid JSON following the JSON Canvas Spec 1.0. File Structure A canvas file contains two top-level arrays: { "nodes": [], "edges": [] } nodes (optional): Array of node objects edges (optional): Array of edge obje...
 36
20823 openclaw-customizer petekp/claude-code-setup
OpenClaw Customizer Help the user configure, customize, and creatively leverage their OpenClaw instance. Approach Be imaginative and inventive. OpenClaw is a flexible system — suggest non-obvious combinations of features that solve real problems. Think beyond basic chat: cron jobs, multi-agent routing, hooks, channel-specific personas, memory pipelines, and automation patterns. When the user asks about a specific area, load the relevant reference file before responding. Reference Files Load thes...
 36
20824 error-detective htlin222/dotfiles
Use this skill when Working on error detective tasks or workflows Needing guidance, best practices, or checklists for error detective Do not use this skill when The task is unrelated to error detective You need a different domain or tool outside this scope Instructions Clarify goals, constraints, and required inputs. Apply relevant best practices and validate outcomes. Provide actionable steps and verification. If detailed examples are required, open resources/implementation-playbook.md . You ar...
 36
20825 roo-conflict-resolution roocodeinc/roo-code
Roo Code Conflict Resolution Skill When to Use This Skill Use this skill when the task involves: Resolving merge conflicts for a specific pull request Rebasing a branch that has conflicts with the target branch Understanding and analyzing conflicting code changes Making intelligent decisions about which changes to keep, merge, or discard Using git history to inform conflict resolution decisions When NOT to Use This Skill Do NOT use this skill when: There are no merge conflicts to resolve The tas...
 36
20826 ru dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations
RU - Repo Updater A comprehensive Bash CLI for synchronizing dozens or hundreds of GitHub repositories. Beyond basic sync, RU includes a full AI-assisted code review system and agent-sweep capability for automatically processing uncommitted changes across your entire projects directory. Why This Exists When you work with 47+ repos (personal projects, forks, dependencies), keeping them synchronized manually is tedious. But synchronization is just the beginning—RU also orchestrates AI coding ag...
 36
20827 pyspark-transformer jeremylongshore/claude-code-plugins-plus-skills
Pyspark Transformer Purpose This skill provides automated assistance for pyspark transformer tasks within the Data Pipelines domain. When to Use This skill activates automatically when you: Mention "pyspark transformer" in your request Ask about pyspark transformer patterns or best practices Need help with data pipeline skills covering etl, data transformation, workflow orchestration, and streaming data processing. Capabilities Provides step-by-step guidance for pyspark transformer Follows indus...
 36
20828 caam dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations
CAAM — Coding Agent Account Manager A Go CLI for instant account switching between fixed-cost AI coding subscriptions (Claude Max, GPT Pro, Gemini Ultra). When you hit rate limits, swap accounts in ~50ms instead of 30-60 seconds of browser OAuth friction. Why This Exists You're paying $200-275/month for fixed-cost AI coding subscriptions. These plans have rolling usage limits—not billing caps, but rate limits that reset over time. When you hit them mid-flow: The Problem: /login → browser op...
 36
20829 openclaw-inter-instance aaaaqwq/claude-code-skills
OpenClaw 实例间通信 当使用此技能 需要给另一个 OpenClaw 实例发消息 跨机器远程执行命令 多 agent 协作任务 同步仓库/文件到远程实例 通信方式优先级 按可靠性和实时性排序，依次尝试： 1. sessions_send（最优，需配置） 直接 agent-to-agent 消息，实时双向。 前提 : 双方配置中开启： // ~/.openclaw/openclaw.json "tools" : { "agentToAgent" : { "enabled" : true } } 用法 : sessions_send(sessionKey="agent:<target-agent>:main", message="...") 优点 : 实时、双向、最简洁 缺点 : 默认禁用，需要两端都开启 2. nodes.run（远程命令执行） 通过已配对的 node 在远程机器上执行命令。 前提 : 目标机器已配对为 node 且在线（ nodes status 检查） 用法 : nodes(action="run", node="<node-name>", command=["...
 36
20830 architecture-md-builder tdimino/claude-code-minoan
Architecture.md Builder Create production-quality ARCHITECTURE.md files that serve as definitive maps of any codebase, following matklad's canonical guidelines with modern AI-agent documentation patterns. When to Use This Skill Creating architecture documentation for a new or existing repository Auditing a codebase to understand its structure Onboarding documentation for developers and AI agents User asks to "document the architecture", "create architecture.md", or "map this codebase" Core Princ...
 36
20831 calendly-automation davepoon/buildwithclaude
Calendly Automation via Rube MCP Automate Calendly operations including event listing, invitee management, scheduling link creation, availability queries, and organization administration through Composio's Calendly toolkit. Toolkit docs : composio.dev/toolkits/calendly Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Calendly connection via RUBE_MANAGE_CONNECTIONS with toolkit calendly Always call RUBE_SEARCH_TOOLS first to get current tool schemas Many operations re...
 36
20832 pytorch-model-trainer jeremylongshore/claude-code-plugins-plus-skills
Pytorch Model Trainer Purpose This skill provides automated assistance for pytorch model trainer tasks within the ML Training domain. When to Use This skill activates automatically when you: Mention "pytorch model trainer" in your request Ask about pytorch model trainer patterns or best practices Need help with machine learning training skills covering data preparation, model training, hyperparameter tuning, and experiment tracking. Capabilities Provides step-by-step guidance for pytorch model t...
 36
20833 requirements-engineering eyadsibai/ltk
Requirements Engineering Master the art of capturing what needs to be built before diving into how to build it. This skill teaches the EARS (Easy Approach to Requirements Syntax) format for creating clear, testable requirements. When to Use This Skill Use requirements engineering when: Starting any new feature or project Clarifying ambiguous stakeholder requests Creating acceptance criteria for user stories Documenting system behavior for testing Ensuring all team members share understanding...
 36
20834 agent-module-architecture tencentblueking/bk-ci
Agent 构建机模块架构指南 模块定位: Agent 是 BK-CI 的构建机核心组件，由 Go 语言编写，负责与后端服务通信、接收构建任务、拉起 Worker 进程执行构建。 一、模块概述 1.1 核心职责 职责 说明 进程管理 Daemon 守护 Agent 进程，确保持续运行 任务调度 从 Dispatch 服务拉取构建任务并执行 Worker 管理 拉起 Worker（Kotlin JAR）执行实际构建逻辑 心跳上报 定期向后端上报 Agent 状态和环境信息 自动升级 检测并自动升级 Agent、Worker、JDK 数据采集 通过 Telegraf 采集构建机指标数据 Docker 构建 支持 Docker 容器化构建（Linux） 1.2 与 Worker 的关系 ┌─────────────────────────────────────────────────────────────┐ │ 构建机 (Build Machine) │ ├──────────────────────────...
 36
20835 animation principles - master dylantarre/animation-principles
The Philosophy Behind the Principles Masters don't just apply principles - they understand their origins in human perception and storytelling. This is animation as visual psychology. Why the Principles Work Squash and Stretch: Persistence of Vision The eye blurs motion. Stretch simulates motion blur our brains expect. Squash simulates impact compression we've observed since infancy. We're matching internal neural predictions. Anticipation: Predictive Processing Human brains constantly predict ne...
 36
20836 seo-technical andrehfp/tinyplate
Technical SEO Audit Categories 1. Crawlability robots.txt: exists, valid, not blocking important resources XML sitemap: exists, referenced in robots.txt, valid format Noindex tags: intentional vs accidental Crawl depth: important pages within 3 clicks of homepage JavaScript rendering: check if critical content requires JS execution Crawl budget: for large sites (>10k pages), efficiency matters AI Crawler Management As of 2025-2026, AI companies actively crawl the web to train models and power AI...
 36
20837 webperf-media nucliweb/webperf-snippets
WebPerf: Media Performance JavaScript snippets for measuring web performance in Chrome DevTools. Execute with mcp__chrome-devtools__evaluate_script , capture output with mcp__chrome-devtools__get_console_message . Scripts scripts/Image-Element-Audit.js — Image Element Audit scripts/SVG-Embedded-Bitmap-Analysis.js — SVG Embedded Bitmap Analysis scripts/Video-Element-Audit.js — Video Element Audit Descriptions and thresholds: references/snippets.md Common Workflows Complete Media Audit When the us...
 36
20838 social-analytics guia-matthieu/clawfu-skills
Social Analytics Analyze social media profiles and calculate engagement metrics - understand what content works for competitors and your own accounts. When to Use This Skill Competitor analysis - Audit competitor social presence Engagement benchmarking - Calculate and compare engagement rates Content analysis - Identify top-performing post types Profile audit - Assess social media health Reporting - Generate social performance reports What Claude Does vs What You Decide Claude Does You Decide St...
 36
20839 menu-design-generation eachlabs/skills
Menu Design Generation Generate professional menu designs for restaurants, cafes, bars, and food service businesses using each::sense. This skill creates visually appealing menu layouts with food imagery, typography, and design elements optimized for various formats and dining experiences. Features Full Page Menus : Complete restaurant menus with sections and pricing Digital Display Boards : High-contrast menus for screens and digital signage Cafe & Coffee Menus : Cozy, artisanal designs for cof...
 36
20840 liaison erichowens/some_claude_skills
THE LIAISON You are The Liaison—the bridge between complex agent activity and human understanding. Your job is to translate what's happening in the ecosystem into clear, actionable communication. Activation Triggers Responds to: status, update me, brief me, what's happening, summarize, report, liaison, inform, announce, tell me, progress Core Identity Mission: Ensure the human never feels lost in their own creation. Philosophy: Clarity Over Completeness - Say what matters, skip what doesn...
 36
20841 daily-news qiaoshouqing/skills
Daily News Skill Query daily news and hot topics from the 6551 platform REST API. No authentication required. Base URL : https://ai.6551.io News Operations 1. Get News Categories Get all available news categories and subcategories. curl -s -X GET "https://ai.6551.io/open/free_categories" 2. Get Hot News Get hot news articles and trending tweets by category. curl -s -X GET "https://ai.6551.io/open/free_hot?category=macro" Parameter Type Required Description category string Yes Category key from f...
 36
20842 review-claudemd ykdojo/claude-code-tips
Review CLAUDE.md from conversation history Analyze recent conversations to improve both global (~/.claude/CLAUDE.md) and local (project) CLAUDE.md files. Step 1: Find conversation history The project's conversation history is in ~/.claude/projects/ . The folder name is the project path with slashes replaced by dashes. Find the project folder (replace / with -) PROJECT_PATH = $( pwd | sed 's|/|-|g' | sed 's|^-||' ) CONVO_DIR =~ /.claude/projects/- ${PROJECT_PATH} ls -lt " $CONVO_DIR " /*.jsonl |...
 36
20843 math-reasoning lingzhi227/agent-research-skills
Mathematical Reasoning Perform rigorous mathematical reasoning and produce publication-quality LaTeX output. Input $0 — Task type: derive , prove , formalize , stats , notation , verify $1 — Context: equation, theorem statement, problem description, or data description Tasks derive — Step-by-step equation derivation Show every intermediate step. Justify each with the rule applied. Box final result with \boxed{} . Number important equations with \label{eq:name} . prove — Formal theorem proof Use ...
 36
20844 setup-ralph glittercowboy/taches-cc-resources
<essential_principles> What is Ralph? Ralph is Geoffrey Huntley's autonomous AI coding methodology that uses iterative loops with task selection, execution, and validation. In its purest form, it's a Bash loop: ``` while :; do cat PROMPT.md | claude ; done ``` The loop feeds a prompt file to Claude, the agent completes one task, updates the implementation plan, commits changes, then exits. The loop restarts immediately with fresh context. Core Philosophy The Ralph Wiggum Technique is de...
 36
20845 slidev-deployment yoanbernabeu/slidev-skills
This skill covers deploying Slidev presentations as static websites to various hosting platforms, making your presentations accessible online. When to Use This Skill - Sharing presentations via URL - Hosting for conferences/events - Creating permanent presentation archives - Setting up CI/CD for presentations - Embedding presentations in websites Building for Production Build Command ``` npx slidev build ``` Or via npm script: ``` npm run build ``` Output Creates `dist/` direc...
 36
20846 pdf nicepkg/ai-workflow
PDF Processing Guide Overview This guide covers essential PDF processing operations using Python libraries and command-line tools. For advanced features, JavaScript libraries, and detailed examples, see REFERENCE.md. If you need to fill out a PDF form, read FORMS.md and follow its instructions. Quick Start from pypdf import PdfReader , PdfWriter Read a PDF reader = PdfReader ( "document.pdf" ) print ( f"Pages: { len ( reader . pages ) } " ) Extract text text = "" for page in reader . pages : t...
 36
20847 customer-workspace aktsmm/agent-skills
Customer Workspace Skill 顧客固有のワークスペースを初期化し、情報蓄積・議事録管理の仕組みを提供。 When to use 顧客ごとのワークスペース初期化が必要なとき インボックス機能や議事録管理を追加したいとき 顧客情報の整理・自動分類ルールを導入したいとき 機能 機能 説明 インボックス チャット・メール等を貼るだけで自動分類・蓄積 議事録管理 Teams AI議事録→テンプレート変換 自動判定 入力パターンから処理を自動振り分け 顧客プロファイル 顧客情報を一元管理 クイックスタート スクリプトで初期化（推奨） 基本 .\scripts\Initialize-CustomerWorkspace.ps1 -CustomerName "ABC株式会社様" フルオプション .\scripts\Initialize-CustomerWorkspace.ps1 ` -CustomerName "ABC株式会社様" ` -ContractType "MACC" ` -ContractPeriod "2025/04 - 2028/03" ` -...
 36
20848 opencode-acp-control bjesuiter/opencode-acp-skill
OpenCode ACP Skill Control OpenCode directly via the Agent Client Protocol (ACP). Metadata For ACP Protocol Docs (for Agents/LLMs): https://agentclientprotocol.com/llms.txt GitHub Repo: https://github.com/bjesuiter/opencode-acp-skill If you have issues with this skill, please open an issue ticket here: https://github.com/bjesuiter/opencode-acp-skill/issues Quick Reference Action How Start OpenCode bash(command: "opencode acp --cwd /path/to/project", background: true) Send message process.write(s...
 36
20849 thought-patterns markpitt/claude-skills
Thought Patterns Orchestration Skill This skill provides access to a comprehensive library of human cognitive thinking patterns. It includes an intelligent orchestration system that selects and chains appropriate patterns based on task requirements. Quick Reference: When to Load Which Resource Task Type Load Resource Debugging, troubleshooting, system analysis resources/foundational-patterns.md Logic problems, hypothesis generation, learning new concepts resources/reasoning-patterns.md Brainst...
 36
20850 dependency-doctor patricio0312rev/skills
Dependency Doctor Comprehensive dependency health analysis and upgrade planning. Core Workflow Scan manifests: Analyze package.json, requirements.txt, Cargo.toml, go.mod, etc. Check versions: Identify outdated packages against latest stable versions Detect issues: Find duplicates, security vulnerabilities, deprecated packages, heavy bundles Assess risk: Evaluate breaking changes and version compatibility Prioritize: Rank issues by severity (security > performance > maintenance) Generate upgrad...
 36