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...
25,616
总 Skills
100.6M
总安装量
2,627
贡献者
# Skill 仓库 描述 安装量
7801 ensembl-database google-deepmind/science-skills
Ensembl Database: ID Mapping and Genomic Features Prerequisites uv : Read the uv skill and follow its Setup instructions to ensure uv is installed and on PATH. User Notification : If LICENSE_NOTIFICATION.txt does not already exist in this skill directory then (1) prominently notify the user to check the terms at https://useast.ensembl.org/index.html and https://github.com/Ensembl/ensembl-rest/wiki , then (2) create the file recording the notification text and timestamp. Overview The Ensembl data...
 945
7802 v3 ddd architecture ruvnet/ruflo
V3 DDD Architecture What This Skill Does Designs and implements Domain-Driven Design (DDD) architecture for claude-flow v3, decomposing god objects into bounded contexts, implementing clean architecture patterns, and enabling modular, testable code structure. Quick Start Initialize DDD architecture analysis Task ( "Architecture analysis" , "Analyze current architecture and design DDD boundaries" , "core-architect" ) Domain modeling (parallel) Task ( "Domain decomposition" , "Break down orchest...
 944
7803 phoenix-evals github/awesome-copilot
Phoenix Evals Build evaluators for AI/LLM applications. Code first, LLM for nuance, validate against humans. Quick Reference Task Files Setup setup-python , setup-typescript Decide what to evaluate evaluators-overview Choose a judge model fundamentals-model-selection Use pre-built evaluators evaluators-pre-built Build code evaluator evaluators-code-python , evaluators-code-typescript Build LLM evaluator evaluators-llm-python , evaluators-llm-typescript , evaluators-custom-templates Batch evaluat...
 944
7804 blockchain-developer sickn33/antigravity-awesome-skills
Use this skill when Working on blockchain developer tasks or workflows Needing guidance, best practices, or checklists for blockchain developer Do not use this skill when The task is unrelated to blockchain developer 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-playb...
 944
7805 tresjs onmax/nuxt-skills
TresJS Vue 3 framework for building 3D scenes with Three.js. Declarative components that wrap Three.js objects. Packages: @tresjs/core (required), @tresjs/cientos (helpers), @tresjs/post-processing (effects) Installation Core (required) pnpm add three @tresjs/core Helpers - controls, loaders, materials, staging pnpm add @tresjs/cientos Post-processing effects pnpm add @tresjs/post-processing Quick Reference Working on... Load file TresCanvas, useTres, useLoop references/core.md Controls, load...
 944
7806 r3f-geometry enzed/r3f-skills
React Three Fiber Geometry Quick Start import { Canvas } from '@react-three/fiber' function Scene() { return ( <Canvas> <ambientLight /> <mesh position={[0, 0, 0]}> <boxGeometry args={[1, 1, 1]} /> <meshStandardMaterial color="hotpink" /> </mesh> </Canvas> ) } Built-in Geometries All Three.js geometries are available as JSX elements. The args prop passes constructor arguments. Basic Shapes // BoxGeometry(width, height, depth, widthSegments, heigh...
 944
7807 asc-apple-ads rorkai/app-store-connect-cli-skills
asc Apple Ads Use this skill when a task involves Apple Ads or asc ads . Ground Rules Run asc ads --help or the specific subgroup help before scripting a command. Apple Ads auth is separate from App Store Connect auth. asc auth login does not configure asc ads . Use JSON output for automation: --output json . Most commands need an org ID. Prefer --org for one-off commands and ASC_ADS_ORG_ID for a scoped session. Never guess payload fields. Use Apple Ads request JSON in a file and pass it with --...
 944
7808 protein-sequence-similarity-search google-deepmind/science-skills
Prerequisites uv : Read the uv skill and follow its Setup instructions to ensure uv is installed and on PATH. User Notification : If LICENSE_NOTIFICATION.txt does not already exist in this skill directory then (1) prominently notify the user to check the terms at https://www.ebi.ac.uk/jdispatcher/sss/ncbiblast and https://colabfold.com , then (2) create the file recording the notification text and timestamp. .env file : Make sure the .env file exists in your home directory. Create one if it does...
 944
7809 protein-sequence-msa google-deepmind/science-skills
Prerequisites uv : Read the uv skill and follow its Setup instructions to ensure uv is installed and on PATH. User Notification : If LICENSE_NOTIFICATION.txt does not already exist in this skill directory then (1) prominently notify the user to check the terms at https://www.ebi.ac.uk/jdispatcher/msa/clustalo and https://www.ebi.ac.uk/about/terms-of-use/ , then (2) create the file recording the notification text and timestamp. .env file : Make sure the .env file exists in your home directory. Cr...
 944
7810 ui-design-system alirezarezvani/claude-skills
UI/UX Design & Development Expert Comprehensive UI/UX design, review, and improvement for modern web applications. Production-ready implementations with TailwindCSS + Radix UI + shadcn/ui and modern React patterns. Stack Architecture The Three Pillars Layer 1: TailwindCSS (Styling Foundation) Utility-first CSS framework with build-time generation Zero runtime overhead, minimal production bundles Design tokens: colors, spacing, typography, breakpoints Responsive utilities and dark mode support La...
 943
7811 safe-action-hooks next-safe-action/skills
next-safe-action React Hooks Import // Standard hooks import { useAction , useOptimisticAction } from "next-safe-action/hooks" ; // Deprecated — use React's useActionState directly instead import { useStateAction } from "next-safe-action/stateful-hooks" ; useAction — Quick Start "use client" ; import { useAction } from "next-safe-action/hooks" ; import { createUser } from "@/app/actions" ; export function CreateUserForm ( ) { const { execute , result , status , isExecuting , isPending } = useAct...
 943
7812 onboard-context-matic github/awesome-copilot
Onboarding: ContextMatic MCP This skill delivers a guided, interactive tour of the context-matic MCP server. Follow every phase in order. Stop after each interaction point and wait for the user's reply before continuing. Agent conduct rules — follow throughout the entire skill: Never narrate the skill structure. Do not say phase names, step numbers, or anything that sounds like you are reading instructions (e.g., "In Phase 1 I will…", "Step 1a:", "As per the skill…"). Deliver the tour as a natur...
 943
7813 app-builder sickn33/antigravity-awesome-skills
App Builder - Application Building Orchestrator Analyzes user's requests, determines tech stack, plans structure, and coordinates agents. 🎯 Selective Reading Rule Read ONLY files relevant to the request! Check the content map, find what you need. File Description When to Read project-detection.md Keyword matrix, project type detection Starting new project tech-stack.md 2025 default stack, alternatives Choosing technologies agent-coordination.md Agent pipeline, execution order Coordinating mu...
 943
7814 dbsnp-database google-deepmind/science-skills
dbSNP Database Integration Prerequisites Show more Installs 426 Repository google-deepmind…e-skills GitHub Stars 1.2K First Seen May 19, 2026 Security Audits Gen Agent Trust Hub Pass Socket Pass Snyk Pass
 943
7815 influencer-marketing kostja94/marketing-skills
Channels: Influencer Guides influencer marketing strategy for AI/SaaS products. Focus on trust and brand exposure; 2–3x higher conversion and 40%–50% lower CAC than traditional ads. 92% of consumers trust influencers over celebrities. When invoking : On first use , if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output. Initial Assessment Check for project cont...
 942
7816 v3 cli modernization ruvnet/ruflo
V3 CLI Modernization What This Skill Does Modernizes claude-flow v3 CLI with interactive prompts, intelligent command decomposition, enhanced hooks integration, performance optimization, and comprehensive workflow automation capabilities. Quick Start Initialize CLI modernization analysis Task ( "CLI architecture" , "Analyze current CLI structure and identify optimization opportunities" , "cli-hooks-developer" ) Modernization implementation (parallel) Task ( "Command decomposition" , "Break dow...
 942
7817 reasoningbank intelligence ruvnet/ruflo
ReasoningBank Intelligence What This Skill Does Implements ReasoningBank's adaptive learning system for AI agents to learn from experience, recognize patterns, and optimize strategies over time. Enables meta-cognitive capabilities and continuous improvement. Prerequisites agentic-flow v1.5.11+ AgentDB v1.0.4+ (for persistence) Node.js 18+ Quick Start import { ReasoningBank } from 'agentic-flow$reasoningbank' ; // Initialize ReasoningBank const rb = new ReasoningBank ( { persist : true , learning...
 942
7818 jest-react-testing manutej/luxor-claude-marketplace
Jest React Testing A comprehensive skill for testing React applications using Jest and React Testing Library. This skill covers everything from basic component testing to advanced patterns including mocking, async testing, custom hooks testing, and integration testing strategies. When to Use This Skill Use this skill when: Testing React components with Jest and React Testing Library Setting up Jest configuration for React projects Writing unit tests for components, hooks, and utilities Testing u...
 942
7819 chakra-ui-migrate chakra-ui/chakra-ui
Chakra UI Migration: v2 → v3 You are guiding a developer through migrating their project from Chakra UI v2 to v3. Work through the steps below in order. Inspect the project first — never guess the package versions or framework. Node requirement: Chakra UI v3 requires Node >= 20.x. Confirm before proceeding if the environment is uncertain. Step 1 — Inspect the project Read these files to understand the current state: package.json Show more
 942
7820 flags facebook/react
Feature Flags Use this skill when adding or changing framework feature flags in Next.js internals. Required Wiring All flags need: config-shared.ts (type) → config-schema.ts (zod). If the flag is consumed in user-bundled code (client components, edge routes, app-page.ts template), also add it to define-env.ts for build-time injection. Runtime-only flags consumed exclusively in pre-compiled bundles can skip define-env.ts . Where the Flag Is Consumed Client/bundled code only (e.g. __NEXT_PPR in cl...
 942
7821 autopentestx-automated-pentesting aradotso/security-skills
AutoPentestX Automated Pentesting Skill Skill by ara.so — Security Skills collection. AutoPentestX is an automated penetration testing and vulnerability reporting tool built in Python. It streamlines security assessments by automating common pentesting tasks including reconnaissance, scanning, vulnerability detection, and report generation. Installation Prerequisites Python 3.8 or higher Linux operating system (recommended) Root/sudo privileges for certain scanning features Basic Installation Sh...
 942
7822 opentargets-database google-deepmind/science-skills
Open Targets Database Skill Overview This skill provides access to the Open Targets Platform GraphQL API. It aggregates multi-modal evidence from genetics (GWAS/eQTL), pathways, animal models, and clinical trials to rank target-disease associations and identify druggable genes. Prerequisites uv : Read the uv skill and follow its Setup instructions to ensure uv is installed and on PATH. User Notification : If LICENSE_NOTIFICATION.txt does not already exist in this skill directory then (1) promine...
 942
7823 website-structure kostja94/marketing-skills
Strategy: Website Structure Guides website structure planning: which pages to build, page priority, and how structure supports UX, SEO, and growth. Structure is the organization and connection of pages; it affects user navigation, Google's understanding of content importance, crawlability, and sitelinks in SERPs. See serp-features for sitelinks and SERP optimization. When invoking : On first use , if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the ...
 941
7824 agent-base-template-generator ruvnet/ruflo
name: base-template-generator description: Use this agent when you need to create foundational templates, boilerplate code, or starter configurations for new projects, components, or features. This agent excels at generating clean, well-structured base templates that follow best practices and can be easily customized. Examples: Context: User needs to start a new React component and wants a solid foundation. user: 'I need to create a new user profile component' assistant: 'I'll use the base-templ...
 941
7825 v3 core implementation ruvnet/ruflo
V3 Core Implementation What This Skill Does Implements the core TypeScript modules for claude-flow v3 following Domain-Driven Design principles, clean architecture patterns, and modern TypeScript best practices with comprehensive test coverage. Quick Start Initialize core implementation Task ( "Core foundation" , "Set up DDD domain structure and base classes" , "core-implementer" ) Domain implementation (parallel) Task ( "Task domain" , "Implement task management domain with entities and servi...
 941
7826 reasoningbank with agentdb ruvnet/ruflo
ReasoningBank with AgentDB What This Skill Does Provides ReasoningBank adaptive learning patterns using AgentDB's high-performance backend (150x-12,500x faster). Enables agents to learn from experiences, judge outcomes, distill memories, and improve decision-making over time with 100% backward compatibility. Performance : 150x faster pattern retrieval, 500x faster batch operations, <1ms memory access. Prerequisites Node.js 18+ AgentDB v1.0.7+ (via agentic-flow) Understanding of reinforcement lea...
 941
7827 humanize-writing jpeggdev/humanize-writing
Humanize Writing You are an expert editor who specializes in detecting and removing AI writing patterns. Your job is to take content that reads like it was generated by a language model and rewrite it so it sounds like a knowledgeable human wrote it on the first try. Core Philosophy AI writing has a recognizable smell. It's not about any single word or trick. It's the combination: predictable structure, hedge-then-assert phrasing, relentless parallelism, significance inflation, and a tendency to...
 941
7828 agentdb memory patterns ruvnet/ruflo
AgentDB Memory Patterns What This Skill Does Provides memory management patterns for AI agents using AgentDB's persistent storage and ReasoningBank integration. Enables agents to remember conversations, learn from interactions, and maintain context across sessions. Performance : 150x-12,500x faster than traditional solutions with 100% backward compatibility. Prerequisites Node.js 18+ AgentDB v1.0.7+ (via agentic-flow or standalone) Understanding of agent architectures Quick Start with CLI Initia...
 940
7829 query-writing langchain-ai/deepagents
Query Writing Skill When to Use This Skill Use this skill when you need to answer a question by writing and executing a SQL query. Workflow for Simple Queries For straightforward questions about a single table: Identify the table - Which table has the data? Get the schema - Use sql_db_schema to see columns Write the query - SELECT relevant columns with WHERE/LIMIT/ORDER BY Execute - Run with sql_db_query Format answer - Present results clearly Workflow for Complex Queries For questions requ...
 940
7830 dingtalk-workspace-cli aradotso/trending-skills
DingTalk Workspace CLI (dws) Skill by ara.so — Daily 2026 Skills collection. dws is an officially open-sourced cross-platform CLI tool from DingTalk that unifies DingTalk's full product suite into a single binary. It is designed for both human users and AI agent workflows. Every response is structured JSON, and built-in Agent Skills let LLMs use DingTalk out of the box. Installation One-liner (recommended) macOS / Linux: curl -fsSL https://raw.githubusercontent.com/DingTalk-Real-AI/dingtalk-work...
 940
7831 brand-identity travisjneuman/.claude
No SKILL.md available for this skill. View on GitHub
 940
7832 visual-hierarchy owl-listener/designer-skills
Visual Hierarchy You are an expert in creating clear visual hierarchy that guides users through interfaces. What You Do You establish visual hierarchy ensuring users see the most important content first and can scan efficiently. Hierarchy Tools Size Larger elements draw attention first. Use size differences of at least 1.5x for clear distinction. Weight Bold text, thicker strokes, and filled icons carry more visual weight than light variants. Color and Contrast High contrast attracts attention. ...
 940
7833 applying-slds forcedotcom/sf-skills
Applying SLDS The Salesforce Lightning Design System (SLDS) is a CSS framework with thousands of artifacts. This skill teaches agents how to find and correctly use them. Version: This skill targets SLDS v2 . Legacy --lwc-* tokens and slds-*--modifier syntax are deprecated. Audit scope: The companion validating-slds skill analyzer only scans .css , .html , and .js files. Use it directly for LWC and similar HTML/CSS/JS components; treat it as a partial signal for JSX/TSX or other framework-specifi...
 939
7834 legal-page-generator kostja94/marketing-skills
Pages: Legal Guides legal page content, structure, and SEO handling. When invoking : On first use , if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output. Initial Assessment Identify: Page type : Privacy Policy, Terms of Service, Cookie Policy, etc. Jurisdiction : GDPR, CCPA, etc. Business model : SaaS, e-commerce, content site Indexing : Index or noindex (oft...
 939
7835 agentdb performance optimization ruvnet/ruflo
AgentDB Performance Optimization What This Skill Does Provides comprehensive performance optimization techniques for AgentDB vector databases. Achieve 150x-12,500x performance improvements through quantization, HNSW indexing, caching strategies, and batch operations. Reduce memory usage by 4-32x while maintaining accuracy. Performance : <100µs vector search, <1ms pattern retrieval, 2ms batch insert for 100 vectors. Prerequisites Node.js 18+ AgentDB v1.0.7+ (via agentic-flow) Existing AgentDB dat...
 939
7836 v3 deep integration ruvnet/ruflo
V3 Deep Integration What This Skill Does Transforms claude-flow from parallel implementation to specialized extension of agentic-flow@alpha, eliminating massive code duplication while achieving performance improvements and feature parity. Quick Start Initialize deep integration Task ( "Integration architecture" , "Design agentic-flow@alpha adapter layer" , "v3-integration-architect" ) Feature integration (parallel) Task ( "SONA integration" , "Integrate 5 SONA learning modes" , "v3-integration...
 939
7837 v3 memory unification ruvnet/ruflo
V3 Memory Unification What This Skill Does Consolidates disparate memory systems into unified AgentDB backend with HNSW vector search, achieving 150x-12,500x search performance improvements while maintaining backward compatibility. Quick Start Initialize memory unification Task ( "Memory architecture" , "Design AgentDB unification strategy" , "v3-memory-specialist" ) AgentDB integration Task ( "AgentDB setup" , "Configure HNSW indexing and vector search" , "v3-memory-specialist" ) Data migrat...
 939
7838 prisma-orm-v7-skills gocallum/nextjs16-agent-skills
Links Upgrade guide (v7): https://www.prisma.io/docs/orm/more/upgrade-guides/upgrading-versions/upgrading-to-prisma-7 Prisma Config reference: https://www.prisma.io/docs/orm/reference/prisma-config-reference Prisma Client Extensions: https://www.prisma.io/docs/orm/prisma-client/client-extensions Prisma 7 migration prompt (AI agents): https://www.prisma.io/docs/ai/prompts/prisma-7 Upgrade Upgrade packages pnpm add @prisma/client@7 pnpm add -D prisma@7 Breaking Changes (v7) Minimum versions Node...
 939
7839 geo-fundamentals sickn33/antigravity-awesome-skills
GEO Fundamentals Optimization for AI-powered search engines. 1. What is GEO? GEO = Generative Engine Optimization Goal Platform Be cited in AI responses ChatGPT, Claude, Perplexity, Gemini SEO vs GEO Aspect SEO GEO Goal 1 ranking AI citations Platform Google AI engines Metrics Rankings, CTR Citation rate Focus Keywords Entities, data 2. AI Engine Landscape Engine Citation Style Opportunity Perplexity Numbered [1][2] Highest citation rate ChatGPT Inline/footnotes Custom GPTs Claude Contextual...
 939
7840 getnote-note iswalle/getnote-cli
getnote-note Skill Save, list, view, update, and delete notes in Get笔记. Prerequisites getnote CLI installed and authenticated ( getnote auth status should show "Authenticated") Commands Save a note getnote save <url|text|image_path> [--title <title>] [--tag <tag>]... Show more
 939
7841 figma-use-figjam figma/mcp-server-guide
use_figma — Figma Plugin API Skill for FigJam This skill contains FigJam-specific context for the use_figma MCP tool. The figma-use skill provides foundational context for plugin API execution via MCP as well as the full Figma plugin API for more advanced use-cases that are not described here. Always pass skillNames: "figma-use-figjam" when calling use_figma for FigJam operations. This is a logging parameter used to track skill usage — it does not affect execution. FigJam URL is figma.com/board/...
 939
7842 avast-premium-security-analysis aradotso/security-skills
Avast Premium Security Analysis Skill by ara.so — Security Skills collection ⚠️ Critical Security Warning This repository appears to be distributing pirated/cracked software and potentially malicious content. The project claims to provide "Keygen Activation," "License Key Pre-Activated," and "Premium Loader Serial" which are indicators of: Software piracy (illegal redistribution of paid software) Potential malware distribution (keygens and cracks commonly contain trojans) License violation (circ...
 939
7843 agentdb advanced features ruvnet/ruflo
AgentDB Advanced Features What This Skill Does Covers advanced AgentDB capabilities for distributed systems, multi-database coordination, custom distance metrics, hybrid search (vector + metadata), QUIC synchronization, and production deployment patterns. Enables building sophisticated AI systems with sub-millisecond cross-node communication and advanced search capabilities. Performance : <1ms QUIC sync, hybrid search with filters, custom distance metrics. Prerequisites Node.js 18+ AgentDB v1.0....
 938
7844 agentdb learning plugins ruvnet/ruflo
AgentDB Learning Plugins What This Skill Does Provides access to 9 reinforcement learning algorithms via AgentDB's plugin system. Create, train, and deploy learning plugins for autonomous agents that improve through experience. Includes offline RL (Decision Transformer), value-based learning (Q-Learning), policy gradients (Actor-Critic), and advanced techniques. Performance : Train models 10-100x faster with WASM-accelerated neural inference. Prerequisites Node.js 18+ AgentDB v1.0.7+ (via agenti...
 938
7845 v3 swarm coordination ruvnet/ruflo
V3 Swarm Coordination What This Skill Does Orchestrates the complete 15-agent hierarchical mesh swarm for claude-flow v3 implementation, coordinating parallel execution across domains while maintaining dependencies and timeline adherence. Quick Start Initialize 15-agent v3 swarm Task ( "Swarm initialization" , "Initialize hierarchical mesh for v3 implementation" , "v3-queen-coordinator" ) Security domain (Phase 1 - Critical priority) Task ( "Security architecture" , "Design v3 threat model and...
 938
7846 v3 mcp optimization ruvnet/ruflo
V3 MCP Optimization What This Skill Does Optimizes claude-flow v3 MCP (Model Context Protocol) server implementation with advanced transport layer optimizations, connection pooling, load balancing, and comprehensive performance monitoring to achieve sub-100ms response times. Quick Start Initialize MCP optimization analysis Task ( "MCP architecture" , "Analyze current MCP server performance and bottlenecks" , "mcp-specialist" ) Optimization implementation (parallel) Task ( "Connection pooling" ...
 938
7847 debugging-dags astronomer/agents
DAG Diagnosis You are a data engineer debugging a failed Airflow DAG. Follow this systematic approach to identify the root cause and provide actionable remediation. Step 1: Identify the Failure If a specific DAG was mentioned: Use diagnose_dag_run with the dag_id and dag_run_id (if provided) If no run_id specified, use get_dag_stats to find recent failures If no DAG was specified: Use get_system_health to find recent failures across all DAGs List any import errors (broken DAG files) Show D...
 938
7848 literature-review k-dense-ai/scientific-agent-skills
Literature Review Conduct deep literature reviews through multi-perspective dialogue and systematic search. Input $0 — Research topic or question $1 — Optional: specific focus or angle References Multi-perspective dialogue prompts (STORM): ~/.claude/skills/literature-review/references/dialogue-prompts.md Literature review workflow (AgentLaboratory): ~/.claude/skills/literature-review/references/review-workflow.md Scripts (from literature-search skill) Search Semantic Scholar python ~/.claude/sk...
 938
7849 tanstack-store tanstack-skills/tanstack-skills
Overview TanStack Store is a lightweight reactive store (signals-like) that powers the internals of TanStack libraries. It provides Store for state, Derived for computed values, Effect for side effects, and batch for atomic updates. Framework adapters provide reactive hooks. Core: @tanstack/store React: @tanstack/react-store Installation npm install @tanstack/store @tanstack/react-store Store Creating a Store import { Store } from '@tanstack/store' const countStore = new Store ( 0 ) const userSt...
 938
7850 mckinsey-consultant mann1988/awesome-claude-skills
架构: Progressive Disclosure (渐进式披露) + Dependency-Aware (依赖感知) 核心升级: - V3.0: 最小核心 + 按需加载 → 节省70%上下文 - V3.1: 页面依赖关系标注 → 跨对话续写更智能 ⚠️ CRITICAL BEHAVIOR RULES 这些规则优先级最高,Claude必须严格遵守: 1. 首次使用响应规则 当用户说"我刚添加了mckinsey-consultant skill"或"Can you make something amazing with it?"时: - ✅ 必须使用下面"首次使用引导"中的精确话术 - ✅ 只输出4行文字,不做任何扩展 - ❌ 禁止列举示例问题 - ❌ 禁止详细询问行业/交付物/范围等 - ❌ 禁止超过4行回复 - ✅ 只问一个二选一的问题,然后等待用户回应 2. 问题澄清规则 - ✅ 只问当下最关键的1-2个问题 - ❌ 不要一次性列出5个以上的问题 - ❌ 不要把澄清变成"需求调研问卷" 3. 流程启动规则 - ✅ 只有用户明确说"开始"...
 938