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
9601 security-alert-triage elastic/agent-skills
Alert Triage Analyze Elastic Security alerts one at a time: gather context, classify, create a case, and acknowledge. This skill depends on the case-management skill for case creation. Prerequisites Install dependencies before first use from the skills/security directory: cd skills/security && npm install Set the required environment variables (or add them to a .env file in the workspace root): export ELASTICSEARCH_URL = "https://your-cluster.es.cloud.example.com:443" export ELASTICSEARCH_API_KE...
 82
9602 architecture-patterns secondsky/claude-skills
Architecture Patterns Master proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design to build maintainable, testable, and scalable systems. When to Use This Skill Designing new backend systems from scratch Refactoring monolithic applications for better maintainability Establishing architecture standards for your team Migrating from tightly coupled to loosely coupled architectures Implementing domain-driven design principles Creating t...
 82
9603 jules sanjay3290/ai-skills
Jules Task Delegation Delegate coding tasks to Google's Jules AI agent on GitHub repositories. Setup (Run Before First Command) 1. Install CLI which jules || npm install -g @google/jules 2. Check Auth jules remote list --repo If fails → tell user to run jules login (or --no-launch-browser for headless) 3. Auto-Detect Repo git remote get-url origin 2>/dev/null | sed -E 's.*(github\.com)[/:]([^/]+/[^/.]+)(\.git)?\2' If not GitHub or not in git repo → ask user for --repo owner/repo 4. Veri...
 82
9604 quasar-skilld harlan-zw/vue-ecosystem-skills
quasarframework/quasar quasar Build high-performance VueJS user interfaces (SPA, PWA, SSR, Mobile and Desktop) in record time Version: 2.18.6 (Nov 2025) Tags: legacy: 1.22.10 (May 2023), latest: 2.18.6 (Nov 2025) References: Docs — API reference, guides API Changes This section documents version-specific API changes — prioritize recent major/minor releases. BREAKING: v-model -> uses model-value + @update:model-value instead of value + @input in Vue 3 source BREAKING: QDrawer / QDialog / QMenu / ...
 82
9605 frontend-internationalization-best-practices sergiodxa/agent-skills
Guidelines for building a React Router i18n setup with `remix-i18next`. Focuses on middleware detection, locale storage, type safety, and client/server synchronization. When to Apply - Adding i18n to a React Router app - Wiring `remix-i18next` middleware - Implementing language switching or locale detection - Serving locale resources from `/api/locales` Rules Summary Setup & Middleware (CRITICAL) setup-middleware - @rules/setup-middleware.md Configure `createI18nextMiddleware` and t...
 82
9606 product-market-fit-analysis manojbajaj95/claude-gtm-plugin
Product Market Fit Analysis Comprehensive framework for assessing, achieving, and scaling product-market fit. Quick Reference Situation Use This Skill For Measuring PMF Sean Ellis Survey Retention analysis Retention Curves PMF validation Leading Indicators Segment-specific PMF Segment Analysis Scaling decisions Post-PMF Strategy Part 1: What Is PMF? Definition Product-market fit is the condition where a product satisfies a strong market demand. It's not binary — it's a spectrum. Key Insight PMF ...
 82
9607 discord vm0-ai/vm0-skills
Discord (Via message ) Use the message tool. No provider-specific discord tool exposed to the agent. Musts Always: channel: "discord" . Respect gating: channels.discord.actions.* (some default off: roles , moderation , presence , channels ). Prefer explicit ids: guildId , channelId , messageId , userId . Multi-account: optional accountId . Guidelines Avoid Markdown tables in outbound Discord messages. Mention users as <@USER_ID> . Prefer Discord components v2 ( components ) for rich UI; use lega...
 82
9608 comfyui-video-pipeline mckruz/comfyui-expert
ComfyUI Video Pipeline Orchestrates video generation across three engines, selecting the best one based on requirements and available resources. Engine Selection VIDEO REQUEST | |-- Need film-level quality? | |-- Yes + 24GB+ VRAM → Wan 2.2 MoE 14B | |-- Yes + 8GB VRAM → Wan 2.2 1.3B | |-- Need long video (>10 seconds)? | |-- Yes → FramePack (60 seconds on 6GB) | |-- Need fast iteration? | |-- Yes → AnimateDiff Lightning (4-8 steps) | |-- Need camera/motion control? | |-- Yes → AnimateD...
 82
9609 ethereum mindrally/skills
Ethereum Development You are an expert in Ethereum smart contract development with Solidity and modern tooling. Core Philosophy Cut the fluff. Code or detailed explanations only. Keep it casual and brief. Accuracy and depth matter. General Principles Prioritize logic over citations Embrace emerging technologies and unconventional solutions Flag speculative content clearly Omit ethical disclaimers unless critical for security Place sources at conclusion, not mid-text Provide complete code imp...
 82
9610 authentication andrelandgraf/fullstackrecipes
Authentication Implement authentication flows on iOS using the AuthenticationServices framework, including Sign in with Apple, OAuth/third-party web auth, Password AutoFill, and biometric authentication. Contents Sign in with Apple Credential Handling Credential State Checking Token Validation Existing Account Setup Flows ASWebAuthenticationSession (OAuth) Password AutoFill Credentials Biometric Authentication SwiftUI SignInWithAppleButton Common Mistakes Review Checklist References Sign in with...
 82
9611 ffmpeg-video-editor bryanwhl/ffmpeg-video-editor
FFmpeg Video Editor You are a video editing assistant that translates natural language requests into FFmpeg commands. When the user asks to edit a video, generate the correct FFmpeg command. How to Generate Commands Identify the operation from the user's request Extract parameters (input file, output file, timestamps, formats, etc.) Generate the FFmpeg command using the patterns below If output filename not specified , create one based on the operation (e.g., video_trimmed.mp4 ) Always include -...
 82
9612 review-code catlog22/claude-code-workflow
Multi-dimensional code review skill that analyzes code across 6 key dimensions and generates structured review reports with actionable recommendations. Architecture Overview ``` ┌─────────────────────────────────────────────────────────────────┐ │ ⚠️ Phase 0: Specification Study (强制前置) │ │ → 阅读 specs/review-dimensions.md │ │ → 理解审查维度和问题分类标准 │ └───────────────┬───────────────────────────────────────────...
 82
9613 pydantic-ai-dependency-injection existential-birds/beagle
PydanticAI Dependency Injection Core Pattern Dependencies flow through RunContext: from dataclasses import dataclass from pydantic_ai import Agent, RunContext @dataclass class Deps: db: DatabaseConn api_client: HttpClient user_id: int agent = Agent( 'openai:gpt-4o', deps_type=Deps, Type for static analysis ) @agent.tool async def get_user_balance(ctx: RunContext[Deps]) -> float: """Get the current user's account balance.""" return await ctx.deps.db.get_balance(...
 82
9614 pptx dedalus-erp-pas/foundation-skills
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 → ...
 82
9615 senior-data-engineer borghei/claude-skills
Senior Data Engineer World-class senior data engineer skill for production-grade AI/ML/Data systems. Quick Start Main Capabilities Core Tool 1 python scripts/pipeline_orchestrator.py --input data/ --output results/ Core Tool 2 python scripts/data_quality_validator.py --target project/ --analyze Core Tool 3 python scripts/etl_performance_optimizer.py --config config.yaml --deploy Core Expertise This skill covers world-class capabilities in: Advanced production patterns and architectur...
 82
9616 godot-save-load-systems thedivergentai/gd-agentic-skills
Save/Load Systems JSON serialization, version migration, and PERSIST group patterns define robust data persistence. Available Scripts save_migration_manager.gd Expert save file versioning with automatic migration between schema versions. save_system_encryption.gd AES-256 encrypted saves with compression to prevent casual save editing. MANDATORY - For Production : Read save_migration_manager.gd before shipping to handle schema changes. NEVER Do in Save Systems NEVER save without version field — G...
 82
9617 nansen-wallet-analysis nansen-ai/nansen-cli
Wallet Analysis Answers: "Who is this wallet and what have they been doing?" ADDR = < address > CHAIN = ethereum nansen research profiler labels --address $ADDR --chain $CHAIN → label, category (e.g. "Smart Trader", "Fund", "Public Figure", ENS names) nansen research profiler balance --address $ADDR --chain $CHAIN → token_symbol, token_name, token_amount, price_usd, value_usd per holding nansen research profiler pnl-summary --address $ADDR --chain $CHAIN --days 30 → realized_pnl_usd, realized...
 82
9618 design-doc diskd-ai/design-doc
Technical Design Document Skill Create structured technical design documents that communicate system behavior, implementation approach, and acceptance criteria. Workflow Gather context: Understand the feature/system scope, constraints, and goals Draft structure: Use template from references/template.md Fill sections: Work through each section, asking clarifying questions as needed Review: Ensure acceptance criteria are testable and implementation outline is actionable Template See references/...
 82
9619 forge-idiomatic-engineer isala404/forge
Forge Idiomatic Engineer Work like a pragmatic maintainer: read the repo in front of you, make the smallest change that solves the user's stated problem, prove it with nearby tests, and stop cleanly when the environment blocks further progress. Default assumptions unless the repo says otherwise: Rust 2024 workspace, forgex imported as forge , PostgreSQL, generated frontend bindings, and a frontend target of either SvelteKit or Dioxus. Operating style Prefer direct evidence from this repo over ge...
 82
9620 spec-context zixun-github/aisdlc
Spec 上下文定位（FEATURE_DIR） 概览 读写 requirements/*.md 前必须先确定 {FEATURE_DIR} 。以 当前 Git 分支名 为锚点，禁止猜路径。 开始时宣布： 「我正在使用 spec-context 技能定位当前 Spec Pack（FEATURE_DIR）。」 何时使用 将读/写 {FEATURE_DIR}/requirements/*.md 不确定当前 spec pack 或出现分支/目录/ .aisdlc 相关上下文错误 做法：复用 $FEATURE_DIR，否则执行脚本 优先复用 ：若本会话已成功回显过 FEATURE_DIR=... ，且 $FEATURE_DIR 非空、目录存在且含 requirements/ ，则直接复用并回显 FEATURE_DIR=... (reuse) 。 否则 ：执行脚本定位并回显 FEATURE_DIR=... 。 脚本目录处理 ： 脚本位置 ： <本SKILL.md目录>/scripts/ 执行方式 ：按操作系统选择脚本实现（Windows/PowerShell 用 spec-common.ps1 ；m...
 82
9621 cloudflare-development mindrally/skills
Cloudflare Development Best Practices Overview This skill provides comprehensive guidelines for developing applications on Cloudflare's edge platform, including Workers, Pages, KV storage, D1 databases, R2 object storage, and Durable Objects. Core Principles Write lightweight, fast code optimized for edge execution Minimize cold start times and execution duration Use appropriate storage solutions for each use case Follow security best practices for edge computing Leverage Cloudflare's global n...
 82
9622 personalization-at-scale manojbajaj95/claude-gtm-plugin
Personalization at Scale Generate hundreds of unique, researched first lines in minutes instead of hours. Instructions You are an expert sales development researcher who specializes in finding personalization angles for outbound prospecting at scale. Your mission is to take a list of prospects and generate unique, relevant, authentic personalization that makes cold outreach feel warm. Core Capabilities Research Sources : Company news and press releases LinkedIn activity (posts, comments, job cha...
 82
9623 adonisjs-best-practices futuregerald/futuregerald-claude-plugin
AdonisJS v6 Best Practices Overview AdonisJS v6 is a TypeScript-first MVC framework with batteries included. Core principle: type safety, dependency injection, and convention over configuration . When to Use Building new AdonisJS v6 features Implementing routes, controllers, middleware Setting up authentication or authorization Writing Lucid ORM models and queries Creating validators with VineJS Writing tests for AdonisJS apps Quick Reference Task Pattern Route to controller router.get('/users',...
 82
9624 accessibility yonatangross/orchestkit
Web Accessibility (WCAG 2.1 AA) Status : Production Ready ✅ Last Updated : 2026-01-14 Dependencies : None (framework-agnostic) Standards : WCAG 2.1 Level AA Quick Start (5 Minutes) 1. Semantic HTML Foundation Choose the right element - don't use div for everything: <!-- ❌ WRONG - divs with onClick --> < div onclick = " submit ( ) " > Submit </ div > < div onclick = " navigate ( ) " > Next page </ div > <!-- ✅ CORRECT - semantic elements --> < button type = " submit " > Submit </ button > < a hre...
 82
9625 work-report ab300819/skills
生成周报、月报、季度报和年终总结。 报告类型 | 周报 | 本周 | 每日工作记录/口述列点 | 本周工作、下周计划 | 固定格式，见模板 | 月报 | 当月 4-5 周 | 周报汇总 | 主要工作汇总、进度跟踪 | 灵活，突出重点工作和进度 | 季报 | 当季 12-13 周 | 周报汇总 | 季度工作总结、阶段性成果 | 灵活，突出重点工作和进度 | 年终总结 | 全年 52 周 | 周报汇总 | 业绩达成、个人成长、成长计划 | 固定格式，见模板 使用流程 第一步：确定报告类型和时间范围 首先确认用户需要生成的报告类型： - 周报：指定周（如本周、2025.01.06 - 2025.01.10） - 月报：指定月份（如 2025 年 12 月） - 季报：指定季度（如 2025 年 Q4） - 年终总结：指定年份（如 2025 年） 第二步：收集必要信息 在开始之前，需要向用户确认以下信息： - 周报文件路径：包含周报的文件（支持 .rtf、.docx、.md、.txt 格式） - 规划文档路径（可选...
 82
9626 supabase-extract-anon-key yoanbernabeu/supabase-pentest-skills
Supabase Anon Key Extraction 🔴 CRITICAL: PROGRESSIVE FILE UPDATES REQUIRED You MUST write to context files AS YOU GO , not just at the end. Write to .sb-pentest-context.json IMMEDIATELY after each discovery Log to .sb-pentest-audit.log BEFORE and AFTER each action DO NOT wait until the skill completes to update files If the skill crashes or is interrupted, all prior findings must already be saved This is not optional. Failure to write progressively is a critical error. This skill extracts the Su...
 82
9627 dark-mode-implementer patricio0312rev/skills
Dark Mode Implementer Build robust dark/light mode theming with system preference detection and persistent storage. Core Workflow Choose strategy: CSS-only, Tailwind, or React context Define color tokens: Create semantic color variables Implement toggle: Add theme switch component Detect system preference: Respect prefers-color-scheme Persist choice: Store preference in localStorage Prevent flash: Handle initial load correctly Strategy Comparison Strategy Best For Complexity Tailwind class Rea...
 82
9628 sap-cap-capire secondsky/sap-skills
This skill integrates with the official CAP MCP (Model Context Protocol) server, providing AI agents with live access to your project's compiled CDS model and CAP documentation. Available MCP Tools: - `search_model` - Fuzzy search for CDS entities, services, actions, and relationships in your compiled CSN model - `search_docs` - Semantic search through CAP documentation for syntax, patterns, and best practices Key Benefits: - Instant Model Discovery: Query your project's entities, associati...
 82
9629 sec-edgar-pipeline bobmatnyc/claude-mpm-skills
SEC EDGAR Pipeline Overview This pipeline is centered on edgar-analyzer and the EDGAR data sources. The core loop is: configure credentials, create a project with examples, analyze patterns, generate code, run extraction, and export reports. Setup (Keys + User Agent) Use the setup wizard to configure required keys: python -m edgar_analyzer setup or edgar-analyzer setup Required entries: OPENROUTER_API_KEY (Optional) JINA_API_KEY EDGAR user agent string ("Name email@example.com") End-to-E...
 82
9630 databricks-python-sdk databricks-solutions/ai-dev-kit
Databricks Development Guide This skill provides guidance for Databricks SDK, Databricks Connect, CLI, and REST API. SDK Documentation: https://databricks-sdk-py.readthedocs.io/en/latest/ GitHub Repository: https://github.com/databricks/databricks-sdk-py Environment Setup Use existing virtual environment at .venv or use uv to create one For Spark operations: uv pip install databricks-connect For SDK operations: uv pip install databricks-sdk Databricks CLI version should be 0.278.0 or higher Conf...
 82
9631 dynamic-debugger rysweet/amplihack
Dynamic Debugger Skill Interactive debugging capability fer Claude Code via DAP-MCP integration. Debug yer code in natural language without leavin' the conversation. Overview This skill enables interactive debuggin' through the Debug Adapter Protocol (DAP) via MCP server integration. Set breakpoints, step through code, inspect variables, and control execution flow across multiple programming languages using natural language commands. What ye get: Natural language debugging commands ("set br...
 82
9632 docker-composer eddiebe147/claude-settings
Docker Composer Skill Overview This skill helps you create efficient Docker configurations for development and production. Covers Dockerfiles, Docker Compose, multi-stage builds, networking, volumes, and container orchestration best practices. Docker Philosophy Container Principles One process per container: Keep containers focused Immutable infrastructure: Don't modify running containers Stateless containers: Store state in volumes or external services Minimal images: Smaller = faster + more ...
 82
9633 moai-domain-database modu-ai/moai-adk
Database Domain Specialist Quick Reference Enterprise Database Expertise - Comprehensive database patterns and implementations covering PostgreSQL, MongoDB, Redis, Oracle, and advanced data management for scalable modern applications. Core Capabilities: PostgreSQL: Advanced relational patterns, optimization, and scaling MongoDB: Document modeling, aggregation, and NoSQL performance tuning Redis: In-memory caching, real-time analytics, and distributed systems Oracle: Enterprise patterns, PL/SQ...
 82
9634 trending-skills geekjourneyx/mind-skills
Trending Skills Fetch skills.sh trending rankings and skill details. Quick Start View rankings 今天技能排行榜 Top 10 skills 技能榜单 Query Types Type Examples Description Rankings 今天技能排行榜 Top 10 Current rankings Detail xxx是什么 xxx介绍 Skill details (requires extra packages) Workflow - [ ] Step 1: Parse query type - [ ] Step 2: Fetch data from skills.sh - [ ] Step 3: Format and display results Step 1: Parse Query Type User Input Query Type Action 今天技能排行榜 rankings Show top N skills Top 10 skills rankings Show ...
 82
9635 delivery-manager borghei/claude-skills
Delivery Manager Expert-level delivery management for continuous software delivery. Core Competencies Release management Deployment coordination Continuous delivery Service operations Incident management Change management Capacity planning SLA management Delivery Framework Delivery Pipeline CODE → BUILD → TEST → STAGE → DEPLOY → MONITOR │ │ │ │ │ │ ▼ ▼ ▼ ▼ ▼ ▼ Commit Compile Unit Integr Prod Observe Review Package I...
 82
9636 service-mesh-observability sickn33/antigravity-awesome-skills
Service Mesh Observability Complete guide to observability patterns for Istio, Linkerd, and service mesh deployments. When to Use This Skill Setting up distributed tracing across services Implementing service mesh metrics and dashboards Debugging latency and error issues Defining SLOs for service communication Visualizing service dependencies Troubleshooting mesh connectivity Core Concepts 1. Three Pillars of Observability ┌─────────────────────────────────────────────────────┐ │ ...
 82
9637 autoresearchclaw-autonomous-research aradotso/trending-skills
AutoResearchClaw — Autonomous Research Pipeline Skill by ara.so — Daily 2026 Skills collection. AutoResearchClaw is a fully autonomous 23-stage research pipeline that takes a natural language topic and produces a complete academic paper: real arXiv/Semantic Scholar citations, sandboxed experiments, statistical analysis, multi-agent peer review, and conference-ready LaTeX (NeurIPS/ICML/ICLR). No hallucinated references. No human babysitting. Installation Clone and install git clone https://githu...
 82
9638 add admin api endpoint tryghost/ghost
Create Admin API Endpoint Instructions If creating an endpoint for an entirely new resource, create a new endpoint file in ghost/core/core/server/api/endpoints/ . Otherwise, locate the existing endpoint file in the same directory. The endpoint file should create a controller object using the JSDoc type from (@tryghost/api-framework).Controller, including at minimum a docName and a single endpoint definition, i.e. browse . Add routes for each endpoint to ghost/core/core/server/web/api/endpoints/a...
 82
9639 x-article-publisher joeseesun/qiaomu-x-article-publisher
X Article Publisher Publish Markdown content to X (Twitter) Articles editor, preserving formatting with rich text conversion. Prerequisites Playwright MCP for browser automation User logged into X with Premium Plus subscription Python 3.9+ with dependencies: macOS: pip install Pillow pyobjc-framework-Cocoa Windows: pip install Pillow pywin32 clip-util For Mermaid diagrams: npm install -g @mermaid-js/mermaid-cli Scripts Located in ~/.claude/skills/x-article-publisher/scripts/: parse_markdown....
 82
9640 cucumber-gherkin el-feo/ai-context
Cucumber & Gherkin Skill BDD testing framework with plain-text executable specifications. Gherkin syntax with step definitions in Ruby, JavaScript, Java, or Python. Core Concepts Cucumber reads executable specifications in plain text and validates software behavior. Gherkin is the structured grammar making plain text machine-readable. ┌────────────┐ ┌──────────────┐ ┌───────────┐ │ Steps │ │ Step │ │ │ │ i...
 82
9641 web-design-guidelines vercel-labs/agent-eval
Web Interface Guidelines Review files for compliance with Web Interface Guidelines. How It Works Fetch the latest guidelines from the source URL below Read the specified files (or prompt user for files/pattern) Check against all rules in the fetched guidelines Output findings in the terse file:line format Guidelines Source Fetch fresh guidelines before each review: https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md Use WebFetch to retrieve the latest rules. Th...
 82
9642 query-expert jamesrochabrun/skills
Query Expert Master database queries across SQL and NoSQL systems. Generate optimized queries, analyze performance with EXPLAIN plans, design effective indexes, and troubleshoot slow queries. What This Skill Does Helps you write efficient, performant database queries: Generate Queries - SQL, MongoDB, GraphQL queries Optimize Queries - Performance tuning and refactoring Design Indexes - Index strategies for faster queries Analyze Performance - EXPLAIN plans and query analysis Troubleshoot - D...
 82
9643 using-aisdlc zixun-github/aisdlc
using-aisdlc（Spec Pack 流程唯一路由器 / Router） 你现在在用什么 这是一个“导航 + 门禁”型技能：在 Spec Pack（分支名 {num}-{short-name} ）流程里， 只有本技能（Router）有权决定下一步用哪个 skill ；其它技能都是 worker，只负责本阶段门禁 + 落盘 + DoD。 开始时必须宣布： 「我正在使用 using-aisdlc 技能导航 Spec Pack 流程，正在执行 spec-context 获取上下文。」 渐进式展开（按需读取） 你要求的机制是“先读 Router，再按需读细则”，因此： 默认只读取本文件 SKILL.md 只有当 Router 需要判定某条链路时，才再读取对应链路的路由细则（R/D/I/V） 路由规则索引（按需阅读） 需求链路（R0–R4） ： router/routing-requirements.md 设计链路（D0–D2） ： router/routing-design.md （ R→I 过渡时必读 ，见 D0 强制门禁） 实现链路（I1–I2 + Finish） ： router...
 82
9644 list-builder jwynia/agent-skills
List Builder: Entropy List Curation Skill You build comprehensive, high-quality lists for creative randomization. These lists feed into entropy tools that inject unpredictability into story development. Core Principle Good entropy lists have three properties: Size — Large enough (50-200+ items) to feel genuinely random Variety — Spans the full possibility space, not just obvious examples Specificity — Concrete enough to spark ideas, not vague categories LLMs are good at research, categoriza...
 82
9645 spec-requesting-code-review zixun-github/aisdlc
请求代码审查 派发 code-reviewer 子智能体，在问题蔓延前发现问题。 核心原则： 尽早审查、频繁审查。 开始时宣布： 「我正在使用 spec-requesting-code-review 技能请求代码审查并派发审查子智能体。」 何时请求审查 必须： subagent-driven development 中每个任务之后 完成主要功能后 合并到 main 之前 可选但有价值： 卡住时（新视角） 重构前（基线检查） 修好复杂 bug 后 如何请求 1. 获取 git SHAs： BASE_SHA = $( git rev-parse HEAD~1 ) 或 origin/main HEAD_SHA = $( git rev-parse HEAD ) 2. 派发 code-reviewer 子智能体： 使用 Task 工具，类型为 code-reviewer，填写 references/code-reviewer.md 中的模板 占位符： {WHAT_WAS_IMPLEMENTED} - 你刚实现的内容 {PLAN_OR_REQUIREMENTS} - 应实现的内容 {BASE_...
 82
9646 spec-product-clarify zixun-github/aisdlc
spec-product-clarify（R1：需求澄清 + 方案决策） 概述 本技能用于把 {FEATURE_DIR}/requirements/raw.md 通过 多轮最小澄清循环 收敛为可评审的 {FEATURE_DIR}/requirements/solution.md （含 Impact Analysis ）。 澄清过程必须可追溯：每次用户裁决后， 立刻回写 到 raw.md/ 澄清记录 。 核心原则：先澄清，后产物；先产物，后路由。 开始时宣布： 「我正在使用 spec-product-clarify 技能澄清需求并产出 solution.md。」 硬规则（用来防止“未澄清先路由”） 澄清未完成时，禁止创建/更新 solution.md （包括模板/骨架）。 澄清未完成时，禁止输出任何“下一步路由/候选下一步/让用户选阶段（R2/R3/I1/I2…）”的信息。 澄清问题必须是“需求裁决”，禁止用“流程分岔/阶段选择”冒充澄清。 （例如：不要问“要 PRD 还是原型还是开发”） 本技能不输出下一步路由结论。 （下一步由 Router： using-aisdlc 判定） 仅在...
 82
9647 vercel-react-best-practices lobehub/lobe-chat
Vercel React Best Practices Comprehensive performance optimization guide for React and Next.js applications, maintained by Vercel. Contains 62 rules across 8 categories, prioritized by impact to guide automated refactoring and code generation. When to Apply Reference these guidelines when: Writing new React components or Next.js pages Implementing data fetching (client or server-side) Reviewing code for performance issues Refactoring existing React/Next.js code Optimizing bundle size or load tim...
 82
9648 find-skills andreadellacorte/groove
Find Skills This skill helps you discover and install skills from the open agent skills ecosystem. When to Use This Skill Use this skill when the user: Asks "how do I do X" where X might be a common task with an existing skill Says "find a skill for X" or "is there a skill for X" Asks "can you do X" where X is a specialized capability Expresses interest in extending agent capabilities Wants to search for tools, templates, or workflows Mentions they wish they had help with a specific domain (desi...
 82
9649 code-analyzer oimiragieo/agent-studio
Code Analyzer Skill Overview Static code analysis and metrics. 90%+ context savings. Tools (Progressive Disclosure) Analysis Tool Description analyze-file Analyze single file analyze-project Analyze entire project complexity Calculate complexity metrics Metrics Tool Description loc Lines of code cyclomatic Cyclomatic complexity maintainability Maintainability index duplicates Find duplicate code Reporting Tool Description summary Get analysis summary hotspots Find complexity hotspots trends An...
 82
9650 nansen-holder-quality nansen-ai/nansen-cli
Holder Quality Answers: "Is this token held by quality wallets or retail noise?" TOKEN = < address > CHAIN = ethereum nansen research token holders --token $TOKEN --chain $CHAIN --smart-money --limit 20 → address, address_label, value_usd, ownership_percentage, balance_change_24h/7d/30d nansen research token flow-intelligence --token $TOKEN --chain $CHAIN → net_flow_usd and wallet_count per label: smart_trader, whale, exchange, fresh_wallets nansen research token who-bought-sold --token $TOKEN...
 82