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...
21,763
总 Skills
39.8M
总安装量
2,458
贡献者
# Skill 仓库 描述 安装量
13551 prompting danielmiessler/personal_ai_infrastructure
Customization Before executing, check for user customizations at: ~/.claude/PAI/USER/SKILLCUSTOMIZATIONS/Prompting/ 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. 🚨 MANDATORY: Voice Notification (REQUIRED BEFORE ANY ACTION) You MUST send this notification BEFORE doing anything else when this skill is invoked. Send voice notification : curl -s -X P...
 67
13552 intent-sync arcblock/idd
Intent Sync Synchronize implementation details back to Intent after development is complete. This makes Intent the true single source of truth. When to Use Use /intent-sync when: Implementation is complete All tests pass User has confirmed the implementation works You want to capture the finalized design in Intent What Gets Synced Back During implementation, many details get finalized that weren't specified in the original Intent: Category Examples Interfaces API endpoints, function signat...
 67
13553 playwright-mcp darraghh1/my-claude-setup
Playwright MCP Browser Automation You are an expert at using the Playwright MCP server for live browser interaction. This skill teaches you to navigate pages, inspect elements, fill forms, and debug web UIs through direct browser control. Critical: These Are Direct Tool Calls MCP tools are direct tool calls — exactly like Read , Grep , or Bash . They are NOT CLI commands. CORRECT — call the tool directly: Tool: mcp__playwright__browser_navigate Parameters: { "url": "http://localhost:3010" } WRON...
 67
13554 good-writing-zh yelban/orz99-skills
中文好寫作 注意： 本 Skill 專注於句型結構精簡與節奏打磨。若需處理 AI 生成痕跡、翻譯腔與中國用語，請搭配 humanizer-tw。建議順序：先 humanizer-tw（去機器味）→ 再 good-writing-zh（打磨節奏）。 節奏規則 氣口 兩個標點符號（，。；：！？）之間，連續字數不超過 15–20 字 。超過就該斷句或加逗號。 錯落 相鄰兩句長度差異應 > 5 字 。避免連續 3 句以上長度相近（±3 字）。 句尾 名詞收尾 → 穩 動詞收尾 → 勁 助詞收尾（的、了、呢）→ 軟 避免連續句尾都落在同類型。 改寫技法 一、刪贅字（連續「的」） 連續三個「的」→ 想法沒整理好，至少刪一個。 原句：這是公司的新的產品的宣傳方案。 改寫：這是公司新產品的宣傳方案。 （理由：三連「的」刪為一個，語意不變） 原句：他提出的關於市場的未來的發展報告。 改寫：他提出的市場未來發展報告。 （理由：「關於」多餘，「的」可精簡為一個） 二、刪贅字（進行/實施/加以） 「進行」「實施」「加以」通常可直接刪除。 原句：我們對此問題進行了深入的討論。 改寫：我們深入討論了這個問題。 （...
 67
13555 spec-pack-abandon zixun-github/aisdlc
spec-pack-abandon（废弃/撤销 Spec Pack：清单 + 二次确认 + 删除分支） 概览 当需求出现重大问题需要“废弃当前 spec pack”时，本技能用于 安全地撤销 ：先执行 spec-context 获取上下文并精确定位 {FEATURE_DIR} ，再生成“将要删除的内容清单”，并在执行任何破坏性操作前要求用户 二次确认 ；最后删除本地/远程分支，并清理工作区中残留的 spec pack 目录。 开始时宣布： 「我正在使用 spec-pack-abandon 技能废弃当前 Spec Pack（输出删除清单并二次确认后删除目录与分支）。」 何时使用 / 不使用 使用时机 需求/约束出现重大问题，决定废弃当前 spec pack（不再继续澄清/设计/实现）。 你需要删除： .aisdlc/specs/{CURRENT_BRANCH}/ 以及该 {CURRENT_BRANCH} 分支（本地 + 远程）。 不要用在 你只是想“回退某个提交”或“重做需求文档”：优先用正常 git 回退/新提交，而不是删分支。 当前不在 spec 分支（分支名不符合 {num}-{s...
 67
13556 baoyu-danger-gemini-web xy121718/baoyu-skills
Gemini Web Client Text/image generation via Gemini Web API. Supports reference images and multi-turn conversations. Script Directory Important: All scripts are located in the scripts/ subdirectory of this skill. Agent Execution Instructions: Determine this SKILL.md file's directory path as SKILL_DIR Script path = ${SKILL_DIR}/scripts/<script-name>.ts Replace all ${SKILL_DIR} in this document with the actual path Script Reference: Script Purpose scripts/main.ts CLI entry point for text/ima...
 67
13557 marketing-social-media vasilyu1983/ai-agents-public
This skill contains actionable, non-theoretical operational systems for sustainable social media marketing across LinkedIn, TikTok, Meta (FB/IG), YouTube, and X. Structure: Core social media principles first. AI-specific automation in clearly labeled "Optional: AI / Automation" sections. Scope note: For email outreach and lead generation, see [marketing-leads-generation](https://github.com/vasilyu1983/ai-agents-public/blob/main/frameworks/shared-skills/skills/marketing-social-media/../marketin...
 67
13558 accelint-tanstack-query-best-practices gohypergiant/agent-skills
TanStack Query Best Practices Expert patterns for TanStack Query in modern React applications with Next.js App Router and Server Components. NEVER Do With TanStack Query NEVER use a singleton QueryClient on the server - Creates data leakage between users and race conditions. Each request must get its own isolated QueryClient instance to prevent cached data from one user appearing for another. NEVER synchronize query data to useState - Background refetches, invalidations, and optimistic updates a...
 67
13559 honesty epicenterhq/epicenter
Honesty Be brutally honest, don't be a yes man. If I am wrong, point it out bluntly. I need honest feedback on my code.
 67
13560 rust-development laurigates/claude-plugins
Expert knowledge for modern systems programming with Rust, focusing on memory safety, fearless concurrency, and zero-cost abstractions. Core Expertise Modern Rust Ecosystem - Cargo: Build system, package manager, and workspace management - Rustc: Compiler optimization, target management, and cross-compilation - Clippy: Linting for idiomatic code and performance improvements - Rustfmt: Consistent code formatting following Rust style guidelines - Rust-analyzer: Advanced IDE support with LS...
 67
13561 predictive-intelligence groeimetai/snow-flow
Predictive Intelligence uses machine learning to automate categorization, routing, and recommendations. PI Capabilities | Classification | Auto-categorize incidents, cases | Similarity | Find similar records | Clustering | Group related items | Regression | Predict numeric values | Recommendation | Suggest next actions Key Tables | `ml_solution` | ML solution definitions | `ml_solution_definition` | Solution configuration | `ml_capability_definition` | Capability setti...
 67
13562 hooks-configuration laurigates/claude-plugins
Expert knowledge for configuring and developing Claude Code hooks to automate workflows and enforce best practices. Core Concepts What Are Hooks? Hooks are user-defined shell commands that execute at specific points in Claude Code's lifecycle. Unlike relying on Claude to "decide" to run something, hooks provide deterministic, guaranteed execution. Why Use Hooks? - Enforce code formatting automatically - Block dangerous commands before execution - Inject context at session start - Log com...
 67
13563 ml-model-training secondsky/claude-skills
ML Model Training Train machine learning models with proper data handling and evaluation. Training Workflow Data Preparation → 2. Feature Engineering → 3. Model Selection → 4. Training → 5. Evaluation Data Preparation import pandas as pd from sklearn . model_selection import train_test_split from sklearn . preprocessing import StandardScaler , LabelEncoder Load and clean data df = pd . read_csv ( 'data.csv' ) df = df . dropna ( ) Encode categorical variables le = LabelEncoder ( ) df [ 'categor...
 67
13564 feature-analyzer notedit/happy-skills
Feature Analyzer Help turn ideas into fully formed designs and specs through structured information gathering and collaborative validation. Announce at start: "I'm using the feature-analyzer skill to design this feature." Phase 1: Context Discovery First, explore the codebase to understand: Project structure and tech stack Existing patterns and conventions Related features or modules Recent changes in relevant areas Phase 2: Structured Information Gathering Use AskUserQuestion to batch col...
 67
13565 github-mcp oimiragieo/agent-studio
GitHub Skill Overview This skill provides access to the official GitHub MCP server with progressive disclosure for optimal context usage. Context Savings: ~95% reduction MCP Mode: ~50,000 tokens always loaded (80+ tools) Skill Mode: ~500 tokens metadata + on-demand loading Requirements Docker installed and running GITHUB_PERSONAL_ACCESS_TOKEN environment variable set Toolsets The server provides 80+ tools across 19 toolsets: Toolset Description actions Workflow management, runs, jobs, artif...
 67
13566 posthog-automation sickn33/antigravity-awesome-skills
PostHog Automation via Rube MCP Automate PostHog product analytics and feature flag management through Composio's PostHog toolkit via Rube MCP. Toolkit docs : composio.dev/toolkits/posthog Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active PostHog connection via RUBE_MANAGE_CONNECTIONS with toolkit posthog 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...
 67
13567 seo-optimizer secondsky/claude-skills
SEO Optimizer Comprehensive SEO strategy and optimization covering keyword research, on-page SEO, technical audits, content optimization, and performance tracking. Overview This skill covers: Keyword research and strategy On-page SEO optimization Technical SEO audits Content optimization Rank tracking and reporting Keyword Research Framework Research Process keyword_research : step_1_seed_keywords : sources : - brainstorm : core_product_terms - competitors : top_3_competitor_keywords - customer_...
 67
13568 make_latex_model huangwb8/chineseresearchlatex
确保 LaTeX 渲染的 PDF 与 Word 版打印的 PDF 像素级对齐： 样式要素（必须完全一致） - 标题层级格式（一级、二级、三级、四级） - ⚠️ 标题文字内容（每年度的 Word 模板标题可能不同） - 字体（中文楷体 + 英文 Times New Roman） - 字号（三号、四号、小四等） - 颜色（MsBlue RGB 0,112,192） - 间距（行距、段前段后、缩进） - 列表样式（编号格式、缩进） - 页面设置（边距、版心） ⚠️ 关键 1：标题文字对齐 - 标题的文字内容必须与 Word 完全相同 - 标题的编号格式必须与 Word 完全相同（如"1." vs "1．"） - 标点符号必须与 Word 完全相同（如全角/半角符号） - 例如：Word 是"1. 项目的立项依据"，LaTeX 必须完全一致 ⚠️ 关键 2：每行字数对齐 - 每行的字数必须与 Word 完全相同 - 换行位置必须与 Word 完全一致 - 这需要精确调整：字号、字间距、行距、段间距 执行模式（简述） 本技能采用“硬编码工具 + A...
 67
13569 mlflow-python terrylica/cc-skills
Unified read/write MLflow operations via Python API with QuantStats integration for comprehensive trading metrics. ADR: [2025-12-12-mlflow-python-skill](https://github.com/docs/adr/2025-12-12-mlflow-python-skill.md) Note: This skill uses Pandas (MLflow API requires it). The `mlflow-python` path is auto-skipped by the Polars preference hook. When to Use This Skill CAN Do: - Log backtest metrics (Sharpe, max_drawdown, total_return, etc.) - Log experiment parameters (strategy config, timefra...
 67
13570 square-automation sickn33/antigravity-awesome-skills
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...
 67
13571 render-automation sickn33/antigravity-awesome-skills
Render Automation via Rube MCP Automate Render cloud platform operations through Composio's Render toolkit via Rube MCP. Toolkit docs : composio.dev/toolkits/render Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Render connection via RUBE_MANAGE_CONNECTIONS with toolkit render 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 keys needed — just add the ...
 67
13572 postmark-automation sickn33/antigravity-awesome-skills
Postmark Automation via Rube MCP Automate Postmark transactional email operations through Composio's Postmark toolkit via Rube MCP. Toolkit docs : composio.dev/toolkits/postmark Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Postmark connection via RUBE_MANAGE_CONNECTIONS with toolkit postmark 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 keys neede...
 67
13573 components-guide get-convex/convex-agent-plugins
Convex Components Guide Use components to encapsulate features and build maintainable, reusable backends. What Are Convex Components? Components are self-contained mini-backends that bundle: Their own database schema Their own functions (queries, mutations, actions) Their own data (isolated tables) Clear API boundaries Think of them as: npm packages for your backend, or microservices without the deployment complexity. Why Use Components? Traditional Approach (Monolithic) convex/ users.ts (500 li...
 67
13574 intercom-automation sickn33/antigravity-awesome-skills
Intercom Automation via Rube MCP Automate Intercom operations through Composio's Intercom toolkit via Rube MCP. Toolkit docs : composio.dev/toolkits/intercom Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Intercom connection via RUBE_MANAGE_CONNECTIONS with toolkit intercom 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 keys needed — just add the end...
 67
13575 basecamp-automation sickn33/antigravity-awesome-skills
Basecamp Automation via Rube MCP Automate Basecamp operations including project management, to-do list creation, task management, message board posting, people management, and to-do group organization through Composio's Basecamp toolkit. Toolkit docs : composio.dev/toolkits/basecamp Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Basecamp connection via RUBE_MANAGE_CONNECTIONS with toolkit basecamp Always call RUBE_SEARCH_TOOLS first to get current tool schemas Setu...
 67
13576 moai-lang-javascript modu-ai/moai-adk
Quick Reference (30 seconds) JavaScript ES2024+ Development Specialist - Modern JavaScript with Node.js 22 LTS, multiple runtimes, and contemporary tooling. Auto-Triggers: Files with .js, .mjs, or .cjs extensions, package.json, Node.js projects, JavaScript discussions Core Stack: ES2024+: Set methods, Promise.withResolvers, immutable arrays, import attributes Node.js 22 LTS: Native TypeScript, built-in WebSocket, stable watch mode Runtimes: Node.js 20 and 22 LTS, Deno 2.x, Bun 1.x Testing: V...
 67
13577 task-distributor 404kidwiz/claude-supercode-skills
Provides expertise in distributing tasks across multi-agent systems efficiently. Specializes in load balancing algorithms, capability-based routing, cost optimization, and ensuring optimal resource utilization across distributed agent pools. When to Use - Designing task distribution strategies for multi-agent systems - Implementing load balancing across worker pools - Optimizing for cost (token economics) vs speed trade-offs - Building routing logic based on agent capabilities - Managing ...
 67
13578 swift-testing bocato/swift-testing-agent-skill
Swift Testing Swift Testing is the modern testing framework for Swift (Xcode 16+, Swift 6+). Prefer it over XCTest for all new unit tests. Use XCTest only for UI tests, performance benchmarks, and snapshot tests. Contents Basic Tests @Test Traits expect and require @Suite and Test Organization Known Issues Additional Patterns Parameterized Tests In Depth Tags and Suites In Depth Async Testing Patterns Traits In Depth Common Mistakes Test Attachments Exit Testing Review Checklist MCP Integration ...
 67
13579 accelint-react-testing gohypergiant/agent-skills
React Testing Best Practices Expert guidance for writing maintainable, user-centric React component tests with Testing Library. Focused on query selection, accessibility-first testing, and avoiding implementation details. NEVER Do When Writing React Tests NEVER query by test IDs before trying accessible queries - Test IDs bypass accessibility verification: a button with data-testid="submit" but no accessible name works in tests but fails for screen reader users. When tests pass with test IDs, yo...
 67
13580 pagerduty-automation sickn33/antigravity-awesome-skills
PagerDuty Automation via Rube MCP Automate PagerDuty incident management and operations through Composio's PagerDuty toolkit via Rube MCP. Toolkit docs : composio.dev/toolkits/pagerduty Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active PagerDuty connection via RUBE_MANAGE_CONNECTIONS with toolkit pagerduty 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 ...
 66
13581 moai-foundation-philosopher modu-ai/moai-adk
MoAI Foundation Philosopher Strategic thinking framework that promotes deeper analysis over quick calculations. Integrates three proven methodologies for systematic problem-solving. Core Philosophy: Think deeply before acting. Question assumptions. Consider alternatives. Make trade-offs explicit. Check for cognitive biases. Quick Reference (30 seconds) What is the Philosopher Framework? A structured approach to complex decisions combining: First Principles Analysis: Break problems to funda...
 66
13582 go-to-market planner daffy0208/ai-dev-standards
Go-to-Market Planner Plan and execute successful product launches. Core Principle Launch is a campaign, not an event. Build momentum before launch, peak at launch, sustain after launch. 5-Phase GTM Strategy Phase 1: Market Positioning Goal : Define how product fits in market landscape Positioning Statement : For [target customer] Who [customer need/problem] [Product name] is a [product category] That [key benefit/differentiation] Unlike [competitors] Our product [unique value] Competitive Analys...
 66
13583 artifacts-builder bobmatnyc/claude-mpm-skills
Artifacts Builder To build powerful frontend claude.ai artifacts, follow these steps: Initialize the frontend repo using scripts/init-artifact.sh Develop your artifact by editing the generated code Bundle all code into a single HTML file using scripts/bundle-artifact.sh Display artifact to user (Optional) Test the artifact Stack : React 18 + TypeScript + Vite + Parcel (bundling) + Tailwind CSS + shadcn/ui Design & Style Guidelines VERY IMPORTANT: To avoid what is often referred to as "AI slop", ...
 66
13584 context-engineering siviter-xyz/dot-agent
Context Engineering Overview Feed agents the right information at the right time. Context is the single biggest lever for agent output quality — too little and the agent hallucinates, too much and it loses focus. Context engineering is the practice of deliberately curating what the agent sees, when it sees it, and how it's structured. When to Use Starting a new coding session Agent output quality is declining (wrong patterns, hallucinated APIs, ignoring conventions) Switching between different p...
 66
13585 devops-specialist caomeiyouren/momei
DevOps Specialist Skill (DevOps 专家技能) 能力 (Capabilities) 容器化 : 编写和优化 Dockerfile 与 docker-compose.yml 。 CI/CD : 编写 GitHub Actions 工作流脚本。 部署适配 : 配置 Vercel、Cloudflare Workers 等平台的部署文件。 环境配置 : 管理 .env 模板与 Nuxt runtimeConfig 配置。 指令 (Instructions) 分支与环境对齐 : 核心部署配置的修改应在 master 分支或专门的 infra 分支中执行。 路径安全 : 在执行任何涉及删除的操作前，必须进行路径校验。 构建验证 : 在提交构建配置变更前，应尝试在本地进行模拟构建。 最小镜像 : 追求 Docker 镜像的分层优化与体积精简。 使用示例 (Usage Example) 输入: "更新 Docker 配置以支持 PostgreSQL。" 动作: 修改 docker-compose.yml 增加 db 服务，并在 Dockerfile 中安装相应的驱动。
 66
13586 freshdesk-automation sickn33/antigravity-awesome-skills
Freshdesk Automation via Rube MCP Automate Freshdesk customer support workflows including ticket management, contact and company operations, notes, replies, and ticket search through Composio's Freshdesk toolkit. Toolkit docs : composio.dev/toolkits/freshdesk Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Freshdesk connection via RUBE_MANAGE_CONNECTIONS with toolkit freshdesk Always call RUBE_SEARCH_TOOLS first to get current tool schemas Setup Get Rube MCP : Add h...
 66
13587 marketing-product-analytics vasilyu1983/ai-agents-public
Product Analytics - Instrumentation & Measurement OS Modern Best Practices (January 2026): PostHog-first, session context registration, strict event naming, North Star activation events, privacy-first attribution. Primary sources live in data/sources.json. If web search is available, refresh time-sensitive details against official docs before giving definitive advice. No fluff. Only executable steps, templates, and checklists. When to Use This Skill Event taxonomy design: Naming conventions,...
 66
13588 capacitor-push-notifications cap-go/capacitor-skills
Push Notifications in Capacitor Implement push notifications for iOS and Android using Firebase and APNs. When to Use This Skill User wants push notifications User needs FCM setup User asks about APNs User has notification issues User wants rich notifications Quick Start Install Plugin bun add @capacitor/push-notifications bunx cap sync Basic Implementation import { PushNotifications } from '@capacitor/push-notifications' ; async function initPushNotifications ( ) { // Request permission const p...
 66
13589 nuxt-ui-v4 secondsky/claude-skills
Nuxt UI v4 - Production Component Library Version : Nuxt UI v4.2.1 | Nuxt v4.0.0 | 125+ Components Last Verified : 2025-12-28 A comprehensive production-ready component library with 125+ accessible components, Tailwind CSS v4, Reka UI accessibility, and first-class AI integration. MCP Integration : This plugin includes the official Nuxt UI MCP server for live component data. When to Use / NOT Use Use when : Building Nuxt v4 dashboards, AI chat interfaces, landing pages, forms, admin panels, pric...
 66
13590 bm-md miantiao-me/bm.md
bm.md Markdown 排版技能 概述 bm.md 是一个专业的 Markdown 排版工具，提供以下核心能力： Markdown 渲染：将 Markdown 转换为带样式的 HTML，支持 14 种排版风格 HTML 转 Markdown：将 HTML 内容逆向转换为 Markdown 格式 纯文本提取：从 Markdown 中提取纯文本，移除所有格式标记 格式校验与修复：自动检测并修复 Markdown 格式问题 所有 API 均返回 JSON 格式响应，结果在 result 字段中。 可用工具 1. Markdown 渲染 将 Markdown 源文本渲染为带内联样式的 HTML，可直接复制到富文本编辑器。 端点: POST https://bm.md/api/markdown/render 请求参数: 参数 类型 必填 默认值 说明 markdown string 是 - Markdown 源文本，支持 GFM 语法、数学公式 markdownStyle string 否 ayu-light 排版样式 ID，见下方完整列表 codeTheme string...
 66
13591 xlsx iofficeai/aionui
Requirements for Outputs All Excel files Professional Font Use a consistent, professional font (e.g., Arial, Times New Roman) for all deliverables unless otherwise instructed by the user Zero Formula Errors Every Excel model MUST be delivered with ZERO formula errors (REF!, DIV/0!, VALUE!, N/A, NAME?) Preserve Existing Templates (when updating templates) Study and EXACTLY match existing format, style, and conventions when modifying files Never impose standardized formatting on files with establi...
 66
13592 build 404kidwiz/claude-supercode-skills
build — implement spec Single-thread native plan→execute. You are main Claude. No swarm. LOAD Read SPEC.md . If missing → tell user to invoke the spec skill first. Stop. Read FORMAT.md once if not loaded. Parse invocation args: §T.n → that task only --next → lowest-numbered row with status . or ~ --all or empty → every . row in §T order PLAN Native plan mode. For chosen task(s): Cite every §V invariant that applies. Plan must respect all. Cite every §I interface touched. Plan must preserve shape...
 66
13593 make-automation sickn33/antigravity-awesome-skills
Make Automation via Rube MCP Automate Make (formerly Integromat) operations through Composio's Make toolkit via Rube MCP. Toolkit docs : composio.dev/toolkits/make Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Make connection via RUBE_MANAGE_CONNECTIONS with toolkit make 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 keys needed — just add the endpo...
 66
13594 redis-inspect civitai/civitai
Use this skill to inspect Redis cache state for debugging purposes. Running Commands ``` node .claude/skills/redis-inspect/query.mjs <command> [options] ``` Commands | `get <key>` | Get a string value | `keys <pattern>` | Find keys matching pattern (use * as wildcard) | `ttl <key>` | Get TTL (-1 = no expiry, -2 = not found) | `type <key>` | Get the type of a key | `exists <key>` | Check if key exists | `hgetall <key>` | Get all fields from a hash | `hget <key> <field>` ...
 66
13595 computer-vision-pipeline erichowens/some_claude_skills
Computer Vision Pipeline Expert in building production-ready computer vision systems for object detection, tracking, and video analysis. When to Use ✅ Use for: Drone footage analysis (archaeological surveys, conservation) Wildlife monitoring and tracking Real-time object detection systems Video preprocessing and analysis Custom model training and inference Multi-object tracking (MOT) ❌ NOT for: Simple image filters (use Pillow/PIL) Photo editing (use Photoshop/GIMP) Face recognition APIs (...
 66
13596 recipe-generator cclank/recipe-generator
菜谱生成器 (Recipe Generator) 核心功能 根据用户输入的菜品名称，生成一份专业级详细菜谱，并附带高质量的生图提示词。 工作流程 步骤1：接收菜品名称 获取用户输入的菜品名称，确认是否有特殊要求（如地方风味、特定做法等）。 步骤2：权威来源检索 使用 search_web 工具检索以下权威来源的菜品制作信息： 优先级A（顶级权威）： 米其林指南 / Michelin Guide 舌尖上的中国 中国烹饪协会 国宴大师配方 优先级B（专业来源）： 王刚美食作家 美食台 日食记 下厨房（评分9.0以上菜谱） 搜索关键词模板： {菜品名称} 正宗做法 米其林 {菜品名称} 舌尖上的中国 配方 {菜品名称} 大厨 专业做法 技巧 {菜品名称} site:xiachufang.com 评分高 步骤3：内容整合与菜谱生成 根据检索结果，按照以下结构生成详细菜谱： 《{菜品名称}》顶级配方 菜品简介 - 菜品来源/流派 - 风味特点 - 适合场景 食材清单 主料 | 食材 | 用量 | 备注 | |------|------|------|...
 66
13597 recursive-improvement dylanfeltus/skills
Recursive Self-Improvement Loop A pattern for generating higher-quality output by iterating against explicit scoring criteria. The Pattern generate → evaluate → diagnose → improve → repeat (until passing) Never ship first-draft output for important content. Run the loop. How It Works 1. Generate Create the initial output as you normally would. 2. Evaluate Score the output against each criterion (1-10). Be brutally honest. 3. Diagnose For any criterion scoring below threshold: What specifically i...
 66
13598 baoyu-comic xy121718/baoyu-skills
Knowledge Comic Creator Create original knowledge comics with flexible art style × tone combinations. Usage /baoyu-comic posts/turing-story/source.md /baoyu-comic article.md --art manga --tone warm /baoyu-comic then paste content Options Visual Dimensions Option Values Description --art ligne-claire (default), manga, realistic, ink-brush, chalk Art style / rendering technique --tone neutral (default), warm, dramatic, romantic, energetic, vintage, action Mood / atmosphere --layout standard (...
 66
13599 audit zackkorman/skills
Run systematic quality checks and generate a comprehensive audit report with prioritized issues and actionable recommendations. Don't fix issues - document them for other commands to address. First : Use the frontend-design skill for design principles and anti-patterns. Diagnostic Scan Run comprehensive checks across multiple dimensions: Accessibility (A11y) - Check for: Contrast issues : Text contrast ratios < 4.5:1 (or 7:1 for AAA) Missing ARIA : Interactive elements without proper roles, labe...
 66
13600 product strategist daffy0208/ai-dev-standards
Product Strategist Validate that products solve real problems for viable markets before investing in development. Core Principle Evidence over intuition. Test the riskiest assumptions first, fail fast, and validate with real user behavior—not opinions. 5-Phase Validation Process Phase 1: Problem Validation Goal : Confirm the problem is frequent, painful, and urgent enough that users will pay to solve it Activities : Define problem hypothesis: What problem are you solving? Identify target custome...
 66