Overview CLI FAQ

Agent Skills 排行榜 · 关键词 + 语义搜索

按 / 聚焦搜索框
正在使用 AI 进行语义搜索...
20,000
总 Skills
16.0M
总安装量
2,338
贡献者
# Skill 仓库 描述 安装量
11051 expert-architect shipshitdev/library
Expert Architect - Expert Secrets Builder Overview You are an expert architect thinking like Russell Brunson. You help people build their positioning using Expert Secrets principles—Attractive Character, Epiphany Bridge, Big Domino, and New Opportunity framing. You create expert positioning that makes them the obvious choice. Brunson's Core Principle: "You don't need to be the most qualified—you need to be the most positioned." Your Role: Build positioning. Craft origin stories. Create expert...
 69
11052 aws-cloudformation-ecs giuseppe-trisciuoglio/developer-kit
AWS CloudFormation ECS Create production-ready container infrastructure using AWS CloudFormation templates. This skill covers ECS clusters, services, task definitions, container configurations, scaling, service discovery, load balancing, and blue/green deployments with CodeDeploy. When to Use Use this skill when: Creating new ECS clusters with CloudFormation Defining task definitions for container workloads Configuring ECS services with deployment strategies Integrating ECS with Application Load...
 69
11053 profile-website-bot-detection kernel/skills
Profile Website for Bot Detection Vendors Analyzes a target website to identify bot detection vendors, their specific products, and challenge types. Supports comparative analysis between stealth and non-stealth browser modes. Prerequisites Kernel CLI installed and authenticated Node.js 22+ installed jq installed ( brew install jq or apt install jq ) KERNEL_API_KEY environment variable set. If it is not set, prompt the user to supply. Comparative Workflow (Recommended) Compare bot detection behav...
 69
11054 writing-skills izyanrajwani/agent-skills-library
Writing Skills Overview Writing skills IS Test-Driven Development applied to process documentation. Personal skills live in agent-specific directories ( ~/.claude/skills for Claude Code, ~/.agents/skills/ for Codex) You write test cases (pressure scenarios with subagents), watch them fail (baseline behavior), write the skill (documentation), watch tests pass (agents comply), and refactor (close loopholes). Core principle: If you didn't watch an agent fail without the skill, you don't know if the...
 69
11055 better-auth secondsky/claude-skills
better-auth - D1 Adapter & Error Prevention Guide Package: better-auth@1.4.16 (Jan 21, 2026) Breaking Changes: ESM-only (v1.4.0), Admin impersonation prevention default (v1.4.6), Multi-team table changes (v1.3), D1 requires Drizzle/Kysely (no direct adapter) ⚠️ CRITICAL: D1 Adapter Requirement better-auth DOES NOT have d1Adapter(). You MUST use: Drizzle ORM (recommended): drizzleAdapter(db, { provider: "sqlite" }) Kysely: new Kysely({ dialect: new D1Dialect({ database: env.DB }) }) See Issu...
 69
11056 pinia martinholovsky/claude-skills-generator
Pinia Pinia is the official state management library for Vue, designed to be intuitive and type-safe. It supports both Options API and Composition API styles, with first-class TypeScript support and devtools integration. The skill is based on Pinia v3.0.4, generated at 2026-01-28. Core References Topic Description Reference Stores Defining stores, state, getters, actions, storeToRefs, subscriptions core-stores Features Extensibility Topic Description Reference Plugins Extend stores with custom p...
 69
11057 odoo marcfargas/odoo-toolbox
/odoo Odoo ERP integration. Two ways to work: CLI (fastest for most tasks) and Library (for scripts and automation). Two Ways to Work with Odoo CLI — Fastest for Most Tasks The odoo CLI lets you search, create, update, and delete records without writing any code. 1. Verify connection (always do this first) odoo config check 2. Search records odoo records search res.partner --fields name,email --limit 5 3. Create a record odoo records create res.partner --data '{"name":"Acme Corp"}' --confirm ...
 69
11058 code-review cloudflare/cloudflare-docs
Code Review When to use this skill Reviewing pull requests Checking code quality Providing feedback on implementations Identifying potential bugs Suggesting improvements Security audits Performance analysis Instructions Step 1: Understand the context Read the PR description : What is the goal of this change? Which issues does it address? Are there any special considerations? Check the scope : How many files changed? What type of changes? (feature, bugfix, refactor) Are tests included? Step 2: Hi...
 69
11059 human-writing pr-pm/prpm
Human-Style Writing This skill helps you write content that reads like it was written by a real person with opinions, personality, and specific knowledge—not a corporate blog generator or AI assistant trying to sound helpful. Core Principle Write like you're explaining something to a colleague over coffee, not presenting to a board room. Good writing is specific, opinionated, and conversational. Bad writing is generic, safe, and sounds like every other tech blog. What Makes Writing Sound AI-Gene...
 69
11060 hig-foundations raintree-technology/apple-hig-skills
Apple HIG: Design Foundations Check for .claude/apple-design-context.md before asking questions. Use existing context and only ask for information not already covered. Key Principles Prioritize content over chrome. Reduce visual clutter. Use system-provided materials and subtle separators rather than heavy borders and backgrounds. Build in accessibility from the start. Design for VoiceOver, Dynamic Type, Reduce Motion, Increase Contrast, and Switch Control from day one. Every interactive element...
 69
11061 translate-book deusyu/translate-book
Book Translation Skill You are a book translation assistant. You translate entire books from one language to another by orchestrating a multi-step pipeline. Workflow 1. Collect Parameters Determine the following from the user's message: file_path : Path to the input file (PDF, DOCX, or EPUB) — REQUIRED target_lang : Target language code (default: zh ) — e.g. zh, en, ja, ko, fr, de, es concurrency : Number of parallel sub-agents per batch (default: 8 ) custom_instructions : Any additional transla...
 69
11062 vercel-deploy davila7/claude-code-templates
Vercel Deploy Deploy any project to Vercel instantly. No authentication required. When to use this skill App deployment : when asked "Deploy my app" Preview deployment : when asked "Create a preview deployment" Production deployment : when asked "Deploy this to production" Share link : when asked "Deploy and give me the link" How It Works Packages your project into a tarball (excludes node_modules and .git ) Auto-detects framework from package.json Uploads to deployment service Returns Preview U...
 69
11063 pptx davepoon/buildwithclaude
PPTX Skill Quick Reference Task Guide Read/analyze content python -m markitdown presentation.pptx Edit or create from template Read editing.md Create from scratch Read pptxgenjs.md Reading Content Text extraction python -m markitdown presentation.pptx Visual overview python scripts/thumbnail.py presentation.pptx Raw XML python scripts/office/unpack.py presentation.pptx unpacked/ Editing Workflow Read editing.md for full details. Analyze template with thumbnail.py Unpack → manipulate slides → ...
 69
11064 context-degradation shipshitdev/library
Context Degradation Patterns Language models exhibit predictable degradation patterns as context length increases. Understanding these patterns is essential for diagnosing failures and designing resilient systems. Context degradation is not a binary state but a continuum of performance degradation that manifests in several distinct ways. When to Activate Activate this skill when: Agent performance degrades unexpectedly during long conversations Debugging cases where agents produce incorrect or i...
 69
11065 wechat-miniprogram joneqian/claude-skills-suite
WeChat Mini Program Skill WeChat Mini Program (微信小程序) development framework skill, generated from official documentation. When to Use This Skill This skill should be triggered when: Developing WeChat Mini Programs (微信小程序) Working with WXML, WXSS, or WXS Using WeChat Mini Program APIs Building WeChat components Implementing WeChat open capabilities (开放能力) Debugging Mini Program issues Optimizing Mini Program performance Quick Reference Project Structure ├── app.js App logic ├── app.json...
 69
11066 task breakdown specialist daffy0208/ai-dev-standards
Task Breakdown Specialist Lower activation energy. Build momentum. Make progress visible. Core Principle ADHD brains struggle with large, ambiguous tasks due to high activation energy. The solution: Break everything into tiny, achievable micro-tasks that provide frequent dopamine hits and visible progress. Key Insight: Starting is the hardest part. Make starting ridiculously easy. The ADHD Task Problem Problem 1: Activation Energy Issue: "Build authentication system" feels overwhelming Result: P...
 69
11067 wpds automattic/agent-skills
WordPress Design System (WPDS) Prerequisites This skill works best with the WPDS MCP server installed. The MCP provides access to WordPress Design System documentation and resources, such as components and DS token lists. The following terms should be treated as synonyms: "WordPress" and "WP"; "Design System" and "DS"; "WordPress Design System" and "WPDS". When to use Use this skill when the user mentions: building and/or reviewing any UI in a WordPress-related context (for example, Gutenberg, W...
 69
11068 qr-barcode-reader dkyazzentwatwa/chatgpt-skills
Decode and extract data from QR codes and barcodes in images with support for multiple barcode formats. Purpose Barcode scanning for: - Inventory management and tracking - Product information lookup - Document verification - Event check-in systems - Automated data entry Features - Multiple Formats: QR Code, EAN-13, Code128, Code39, UPC-A, DataMatrix - Batch Processing: Scan multiple images in one operation - Data Extraction: Decode to text, URLs, structured data - Image Preprocessi...
 69
11069 alicloud-solution-content-article-illustrator-test cinience/alicloud-skills
Category: test Content Article Illustrator Smoke Test Prerequisites Target skill path: skills/solutions/alicloud-solution-content-article-illustrator/ Python 3 Test Steps Compile helper scripts: python3 tests/common/compile_skill_scripts.py \ --skill-path skills/solutions/alicloud-solution-content-article-illustrator \ --output output/alicloud-solution-content-article-illustrator-test/compile-check.json Run the executable smoke test: python3 tests/solutions/alicloud-solution-content-article-illu...
 69
11070 search-company-knowledge atlassian/atlassian-mcp-server
Search Company Knowledge Keywords find information, search company knowledge, look up, what is, explain, company docs, internal documentation, Confluence search, Jira search, our documentation, internal knowledge, knowledge base, search for, tell me about, get information about, company systems, terminology, find everything about, what do we know about, deployment, authentication, infrastructure, processes, procedures, how to, how does, our systems, our processes, internal systems, company proce...
 69
11071 axiom-app-store-submission charleswiltgen/axiom
App Store Submission Overview Systematic pre-flight checklist that catches 90% of App Store rejection causes before submission. Core principle : Ship once, ship right. Over 40% of App Store rejections cite Guideline 2.1 (App Completeness) — crashes, placeholders, broken links. Another 30% are metadata and privacy issues. A disciplined pre-flight process eliminates these preventable rejections. Key insight : Apple rejected nearly 1.93 million submissions in 2024. Most rejections are not policy di...
 69
11072 typescript martinholovsky/claude-skills-generator
TypeScript Code Style Guide Types and Type Safety Avoid explicit type annotations when TypeScript can infer Avoid implicitly any ; explicitly type when necessary Use accurate types: prefer Record<PropertyKey, unknown> over object or any Prefer interface for object shapes (e.g., React props); use type for unions/intersections Prefer as const satisfies XyzInterface over plain as const Prefer @ts-expect-error over @ts-ignore over as any Avoid meaningless null/undefined parameters; design strict fun...
 69
11073 aws-cloudformation-rds giuseppe-trisciuoglio/developer-kit
AWS CloudFormation RDS Database Overview Create production-ready Amazon RDS infrastructure using AWS CloudFormation templates. This skill covers RDS instances (MySQL, PostgreSQL, Aurora, MariaDB), DB clusters, multi-AZ deployments, parameter groups, subnet groups, security groups, template structure best practices, parameter patterns, and cross-stack references for modular, reusable infrastructure as code. When to Use Use this skill when: Creating new RDS database instances (MySQL, PostgreSQL, A...
 69
11074 tmux-processes 0xbigboss/claude-code
tmux Process Management Interactive Shell Requirement Use send-keys pattern for reliable shell initialization. Creating a session spawns an interactive shell automatically. Use send-keys to run commands within that shell, ensuring PATH, direnv, and other initialization runs properly. WRONG - inline command bypasses shell init, breaks PATH/direnv tmux new-session -d -s "$SESSION" -n main 'tilt up' CORRECT - create session, then send command to interactive shell tmux new-session -d -s "$SESSI...
 69
11075 cocos2d-x teachingai/full-stack-skills
When to use this skill Use this skill whenever the user wants to: Create Cocos2d-x v4 games or applications Learn Cocos2d-x v4 core concepts (Node, Sprite, Scene, Action) Set up Cocos2d-x v4 development environment Work with sprites, textures, animations, and labels Implement scene management and node lifecycle Handle input events (touch, mouse, keyboard) Use physics engine (Box2D) and collision detection Implement rendering pipeline, shaders, and particle systems Build and deploy games for mu...
 69
11076 monday vm0-ai/vm0-skills
Monday Monday.com is a work operating system where teams can plan, track, and manage their work. It's used by project managers, marketing teams, and sales teams to improve collaboration and execution. Official docs: https://developers.monday.com/ Monday Overview Board Item Column User When to use which actions: Use action names and parameters as needed. Working with Monday This skill uses the Membrane CLI to interact with Monday. Membrane handles authentication and credentials refresh automatica...
 69
11077 react-frontend-expert hieutrtr/ai1-skills
React Frontend Expert When to Use Activate this skill when: Creating or modifying React components (functional components only) Writing custom hooks ( useXxx ) Building pages with routing Implementing data fetching with TanStack Query Handling forms with validation Setting up project structure for a React/TypeScript application Do NOT use this skill for: Writing component or hook tests (use react-testing-patterns ) E2E browser testing (use e2e-testing ) API contract design (use api-design-patter...
 69
11078 opentofu-guide josiahsiegel/claude-plugin-marketplace
🚨 CRITICAL GUIDELINES Windows File Path Requirements MANDATORY: Always Use Backslashes on Windows for File Paths When using Edit or Write tools on Windows, you MUST use backslashes (\) in file paths, NOT forward slashes (/). Examples: ❌ WRONG: D:/repos/project/file.tsx ✅ CORRECT: D:\repos\project\file.tsx This applies to: Edit tool file_path parameter Write tool file_path parameter All file operations on Windows systems Documentation Guidelines NEVER create new documentation files unless ...
 69
11079 dry-principle oimiragieo/agent-studio
Dry Principle Skill Follow the DRY (Don't Repeat Yourself) Principle and Avoid Duplicating Code or Logic. Avoid writing the same code more than once. Instead, reuse your code using functions, classes, modules, libraries, or other abstractions. Modify code in one place if you need to change or update it. Iron Laws NEVER extract to a shared abstraction until you have at least 3 concrete instances of the same logic — premature extraction creates wrong abstractions that are harder to remove than the...
 69
11080 run-nx-generator nrwl/nx
Run Nx Generator This skill helps you execute Nx generators efficiently, with special focus on workspace-plugin generators from your internal tooling. Generator Priority List Use the mcp__nx-mcp__nx_generator_schema tool to get more information about how to use the generator Choose which generators to run in this priority order: 🔥 Workspace-Plugin Generators (High Priority) These are your custom internal tools in tools/workspace-plugin/ 📦 Core Nx Generators (Standard) Only use these if workspace...
 69
11081 magento-performance-analyst maxnorm/magento2-agent-skills
Magento 2 Performance Analyst Expert specialist in conducting comprehensive performance analysis and implementing systematic optimizations that deliver measurable improvements in application speed, scalability, and user experience. When to Use Analyzing performance bottlenecks Profiling applications Optimizing database queries Improving system scalability Conducting load testing Optimizing frontend performance Performance Analysis Profiling Tools Blackfire : Performance profiling and optimizatio...
 69
11082 github dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations
GitHub Patterns Tools Use gh CLI for all GitHub operations. Prefer CLI over GitHub MCP servers for lower context usage. Quick Commands Create a PR from the current branch gh pr create --title "feat: add feature" --body "Description" Squash-merge a PR gh pr merge < PR_NUMBER > --squash --title "feat: add feature (<PR_NUMBER>)" View PR status and checks gh pr status gh pr checks < PR_NUMBER > Stacked PR Workflow Summary When merging a chain of stacked PRs (each targeting the previous branch): M...
 69
11083 openwork-orchestrator-npm-publish different-ai/openwork
Quick usage (already configured) Ensure you are on the default branch and the tree is clean. Bump versions via the shared release bump (this keeps openwork-orchestrator aligned with the app/desktop release). pnpm bump:patch or: pnpm bump:minor or: pnpm bump:major or: pnpm bump:set -- X.Y.Z Commit the bump. Preferred: publish via the "Release App" GitHub Actions workflow by tagging vX.Y.Z . Manual recovery path (sidecars + npm) below. pnpm --filter openwork-orchestrator build:sidecars gh relea...
 69
11084 dependency-manager 404kidwiz/claude-supercode-skills
Dependency Manager Purpose Provides expertise in package management, version resolution, and software supply chain security. Handles dependency updates, vulnerability auditing, and conflict resolution across multiple package ecosystems. When to Use Updating project dependencies Resolving version conflicts Auditing for security vulnerabilities Managing lockfiles and reproducibility Migrating between package managers Implementing dependency policies Reducing bundle size via dependency analysis Q...
 69
11085 metasploit-framework sickn33/antigravity-awesome-skills
Metasploit Framework Purpose Leverage the Metasploit Framework for comprehensive penetration testing, from initial exploitation through post-exploitation activities. Metasploit provides a unified platform for vulnerability exploitation, payload generation, auxiliary scanning, and maintaining access to compromised systems during authorized security assessments. Prerequisites Required Tools Metasploit comes pre-installed on Kali Linux For other systems: curl https://raw.githubusercontent.com/rap...
 69
11086 linear-automation sickn33/antigravity-awesome-skills
Linear Automation via Rube MCP Automate Linear operations through Composio's Linear toolkit via Rube MCP. Toolkit docs : composio.dev/toolkits/linear Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Linear connection via RUBE_MANAGE_CONNECTIONS with toolkit linear 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 endpoint and it...
 69
11087 freshdesk-automation composiohq/awesome-claude-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...
 69
11088 copilot-cli giuseppe-trisciuoglio/developer-kit
Copilot CLI Delegation Delegate selected tasks from Claude Code to GitHub Copilot CLI using non-interactive commands, explicit model selection, safe permission flags, and shareable outputs. Overview This skill standardizes delegation to GitHub Copilot CLI ( copilot ) for cases where a different model may be more suitable for a task. It covers: Non-interactive execution with -p / --prompt Model selection with --model Permission control ( --allow-tool , --allow-all-tools , --allow-all-paths , --al...
 69
11089 clickhouse-query civitai/civitai
ClickHouse Query Testing Use this skill to run ad-hoc ClickHouse queries for analytics, metrics analysis, and debugging. Running Queries Use the included query script: node .claude/skills/clickhouse-query/query.mjs "SELECT count() FROM views" Options Flag Description --explain Show query execution plan --writable Allow write operations (requires user permission) --timeout <s>, -t Query timeout in seconds (default: 30) --file, -f Read query from a file --json Output results as JSON --quiet, ...
 69
11090 mermaid-flowchart-generator jeremylongshore/claude-code-plugins-plus-skills
Mermaid Flowchart Generator Purpose This skill provides automated assistance for mermaid flowchart generator tasks within the Visual Content domain. When to Use This skill activates automatically when you: Mention "mermaid flowchart generator" in your request Ask about mermaid flowchart generator patterns or best practices Need help with visual content skills covering diagrams, charts, presentations, and visual documentation tools. Capabilities Provides step-by-step guidance for mermaid flow...
 69
11091 cal-com-automation sickn33/antigravity-awesome-skills
Cal.com Automation via Rube MCP Automate Cal.com scheduling operations through Composio's Cal toolkit via Rube MCP. Prerequisites Rube MCP must be connected (RUBE_SEARCH_TOOLS available) Active Cal.com connection via RUBE_MANAGE_CONNECTIONS with toolkit cal 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 endpoint and it works. Verify Rube MCP is available...
 69
11092 feishu-card alextangson/feishu_skills
飞书交互卡片 构建、发送和处理飞书交互卡片。 使用场景 : 晨报确认、告警处理、任务确认、状态更新 发送卡片 POST /open-apis/im/v1/messages?receive_id_type=chat_id { "receive_id" : "<chat_id>" , "msg_type" : "interactive" , "content" : "<card_json_string>" } ⚠️ content 必须是字符串化的 JSON。 卡片结构 { "config" : { "wide_screen_mode" : true } , "header" : { "title" : { "tag" : "plain_text" , "content" : "标题" } , "template" : "blue" } , "elements" : [ { "tag" : "div" , "text" : { "tag" : "lark_md" , "content" : "加粗" } } , { "tag" : "action" , "actions" : [ { "t...
 69
11093 ollama-optimizer luongnv89/skills
Ollama Optimizer Optimize Ollama configuration based on system hardware analysis. Repo Sync Before Edits (mandatory) Before writing any output files, sync with the remote to avoid conflicts: branch = " $( git rev-parse --abbrev-ref HEAD ) " git fetch origin git pull --rebase origin " $branch " If the working tree is dirty, stash first ( git stash ), sync, then pop ( git stash pop ). If origin is missing or conflicts occur, stop and ask the user before continuing. Workflow Phase 1: System Detecti...
 69
11094 aws-cloudformation-cloudwatch giuseppe-trisciuoglio/developer-kit
AWS CloudFormation CloudWatch Monitoring Overview Create production-ready monitoring and observability infrastructure using AWS CloudFormation templates. This skill covers CloudWatch metrics, alarms, dashboards, log groups, log insights, anomaly detection, synthesized canaries, Application Signals, and best practices for parameters, outputs, and cross-stack references. When to Use Use this skill when: Creating custom CloudWatch metrics Configuring CloudWatch alarms for thresholds and anomaly det...
 69
11095 project-discover-memory-index zixun-github/aisdlc
project-discover-memory-index（Step2+3：Level-0 Memory + Level-1 索引骨架） 概览 这一阶段的目标是： 让任何人/AI 在几分钟内知道项目边界、权威入口、怎么跑/怎么验、从哪里进入模块与契约 。 方法是：先把 Memory 与索引骨架落盘，并严格执行“索引只导航”的硬规则。 开始时宣布： 「我正在使用 project-discover-memory-index 技能建立 Discover 的北极星（memory）与索引骨架（地图层）。」 输出目录（标准落盘） .aisdlc/project/ memory/ structure.md tech.md product.md glossary.md components/ index.md products/ index.md 提醒 ：本阶段不要创建 .aisdlc/project/contracts/ ；契约入口将通过模块页锚点跳转。 Level-0：Memory 写法约束（必须短） 通用硬规则 只写稳定入口与边界 ：入口链接 > 解释性长文 避免一次性交付细节 ：详细迁移步骤/...
 69
11096 convex-eslint waynesutton/convexskills
Convex ESLint Compliance Write all Convex functions to pass @convex-dev/eslint-plugin. These rules prevent common bugs, security issues, and ensure code quality. Documentation Sources https://docs.convex.dev/eslint https://www.npmjs.com/package/@convex-dev/eslint-plugin Setup Install the plugin: npm i @convex-dev/eslint-plugin --save-dev Configure eslint.config.js : import { defineConfig } from "eslint/config" ; import convexPlugin from "@convex-dev/eslint-plugin" ; export default defineConfig (...
 69
11097 copaw-ai-assistant aradotso/trending-skills
CoPaw AI Assistant Skill Skill by ara.so — Daily 2026 Skills collection. CoPaw is a personal AI assistant framework you deploy on your own machine or in the cloud. It connects to multiple chat platforms (DingTalk, Feishu, QQ, Discord, iMessage, Telegram, Mattermost, Matrix, MQTT) through a single agent, supports custom Python skills, scheduled cron jobs, local and cloud LLMs, and provides a web Console at http://127.0.0.1:8088/ . Installation pip (recommended if Python 3.10–3.13 is available) pi...
 69
11098 intent-critique arcblock/idd
Intent Critique 设计质量的批判性审查。不检查格式，只检查"是否该这么设计"。 核心问题 每次 critique 回答一个问题：这个设计能更简单吗？ 检查维度 维度 信号 问题 Over-engineering 复杂的配置系统、插件架构、多层抽象 "这个复杂度是当前需求驱动的吗？" YAGNI "未来可能需要"、"预留扩展点"、"支持多种..." "删掉这个，MVP 还能工作吗？" 过早抽象 只有一个实现的接口、只用一次的工具函数 "现在真的需要这层抽象吗？" 边界问题 模块间大量数据传递、循环依赖、职责模糊 "这个边界切在这里自然吗？" 隐藏复杂度 看似简单但实现困难的描述 "这句话背后的实现复杂度是什么？" 工作流程 /intent-critique [path] ↓ ┌───────────────────┐ │ 读取 Intent 文件 │ │ 理解设计意图 │ └─────────┬─────────┘ ↓ ┌───────────────────┐ │ 逐维度分析 │ │ 识别可疑设...
 69
11099 kanban-markdown lachyfs/kanban-skill
Kanban Markdown Manage kanban board features stored as markdown files with YAML frontmatter. Each feature is a .md file; the VS Code kanban-markdown extension renders them as a board. File Format Every feature file follows this exact format: --- id : "my-feature-2026-02-20" status : "backlog" priority : "medium" assignee : null dueDate : null created : "2026-02-20T10:00:00.000Z" modified : "2026-02-20T10:00:00.000Z" completedAt : null labels : [ ] order : "a0" --- My Feature Description and det...
 69
11100 query-builder clidey/whodb
Convert natural language questions into SQL queries using the database schema. When to Use Activate when user asks questions like: - "Show me all users who signed up last month" - "Find orders greater than $100" - "Which products have low inventory?" - "Get the top 10 customers by total spend" Workflow 1. Understand the Schema Before generating SQL, always check the table structure: ``` whodb_tables(connection="...") → Get available tables whodb_columns(table="relevant_table") → Get...
 69