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...
25,452
总 Skills
94.8M
总安装量
2,621
贡献者
# Skill 仓库 描述 安装量
1101 langchain-architecture wshobson/agents
LangChain & LangGraph Architecture Master modern LangChain 1.x and LangGraph for building sophisticated LLM applications with agents, state management, memory, and tool integration. When to Use This Skill Building autonomous AI agents with tool access Implementing complex multi-step LLM workflows Managing conversation memory and state Integrating LLMs with external data sources and APIs Creating modular, reusable LLM application components Implementing document processing pipelines Building prod...
 10K
1102 apple-appstore-reviewer github/awesome-copilot
Apple App Store Review Specialist You are an Apple App Store Review Specialist auditing an iOS app’s source code and metadata from the perspective of an App Store reviewer . Your job is to identify likely rejection risks and optimization opportunities . Specific Instructions You must: Change no code initially. Review the codebase and relevant project files (e.g., Info.plist, entitlements, privacy manifests, StoreKit config, onboarding flows, paywalls, etc.). Produce prioritized, actionable recom...
 10K
1103 auth-implementation-patterns wshobson/agents
Authentication & Authorization Implementation Patterns Build secure, scalable authentication and authorization systems using industry-standard patterns and modern best practices. When to Use This Skill Implementing user authentication systems Securing REST or GraphQL APIs Adding OAuth2/social login Implementing role-based access control (RBAC) Designing session management Migrating authentication systems Debugging auth issues Implementing SSO or multi-tenancy Core Concepts 1. Authentication vs A...
 10K
1104 hunt tw93/waza
Hunt: Diagnose Before You Fix Prefix your first line with 🥷 inline, not as its own paragraph. A patch applied to a symptom creates a new bug somewhere else. Do not touch code until you can state the root cause in one sentence: "I believe the root cause is [X] because [evidence]." Name a specific file, function, line, or condition. "A state management issue" is not testable. "Stale cache in useUser at src/hooks/user.ts:42 because the dependency array is missing userId " is testable. If you cannot...
 10K
1105 frontend-design anthropics/claude-plugins-official
This skill guides creation of distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics. Implement real working code with exceptional attention to aesthetic details and creative choices. The user provides frontend requirements: a component, page, application, or interface to build. They may include context about the purpose, audience, or technical constraints. Design Thinking Before coding, understand the context and commit to a BOLD aesthetic direction: Purpose :...
 10K
1106 python-mcp-server-generator github/awesome-copilot
Generate Python MCP Server Create a complete Model Context Protocol (MCP) server in Python with the following specifications: Requirements Project Structure : Create a new Python project with proper structure using uv Dependencies : Include mcp[cli] package with uv Transport Type : Choose between stdio (for local) or streamable-http (for remote) Tools : Create at least one useful tool with proper type hints Error Handling : Include comprehensive error handling and validation Implementation Detai...
 9.9K
1107 microservices-patterns wshobson/agents
Microservices Patterns Master microservices architecture patterns including service boundaries, inter-service communication, data management, and resilience patterns for building distributed systems. When to Use This Skill Decomposing monoliths into microservices Designing service boundaries and contracts Implementing inter-service communication Managing distributed data and transactions Building resilient distributed systems Implementing service discovery and load balancing Designing event-driv...
 9.9K
1108 parallel-web-extract parallel-web/parallel-agent-skills
URL Extraction Extract content from: $ARGUMENTS Command parallel-cli extract " $ARGUMENTS " --json Options if needed: --objective "focus area" to focus on specific content Response format Return content as: Page Title Then the extracted content verbatim, with these rules: Keep content verbatim - do not paraphrase or summarize Parse lists exhaustively - extract EVERY numbered/bulleted item Strip only obvious noise: nav menus, footers, ads Preserve all facts, names, numbers, dates, quotes Setup If...
 9.9K
1109 think tw93/waza
Think: Design and Validate Before You Build Prefix your first line with 🥷 inline, not as its own paragraph. Turn a rough idea into an approved plan. No code, no scaffolding, no pseudo-code until the user approves. Give opinions directly. Take a position and state what evidence would change it. Avoid "That's interesting," "There are many ways to think about this," "You might want to consider." Before Reading Any Code Confirm the working path: pwd or git rev-parse --show-toplevel . Never assume ~/...
 9.9K
1110 parallel-data-enrichment parallel-web/parallel-agent-skills
Data Enrichment Enrich: $ARGUMENTS Before starting Inform the user that enrichment may take several minutes depending on the number of rows and fields requested. Step 1: Start the enrichment Use ONE of these command patterns (substitute user's actual data): For inline data: parallel-cli enrich run --data '[{"company": "Google"}, {"company": "Microsoft"}]' --intent "CEO name and founding year" --target "output.csv" --no-wait For CSV file: parallel-cli enrich run --source-type csv --source "input....
 9.9K
1111 health tw93/waza
Health: Audit the Six-Layer Stack Prefix your first line with 🥷 inline, not as its own paragraph. Audit the current project's Claude Code setup against the six-layer framework: CLAUDE.md → rules → skills → hooks → subagents → verifiers Find violations. Identify the misaligned layer. Calibrate to project complexity only. Output language: Check in order: (1) CLAUDE.md Communication rule (global takes precedence over local); (2) language of the user's recent conversation messages; (3) default Engl...
 9.9K
1112 okx-dex-market okx/onchainos-skills
OKX DEX Market Data CLI 14 commands for on-chain prices, trades, candlesticks, index prices, smart money signals, and meme pump token scanning. Pre-flight Checks Every time before running any onchainos command, always follow these steps in order. Do not echo routine command output to the user; only provide a brief status update when installing, updating, or handling a failure. Confirm installed : Run which onchainos . If not found, install it: curl -sSL https://raw.githubusercontent.com/okx/onch...
 9.9K
1113 web-search inferen-sh/skills
Install the belt CLI skill: npx skills add belt-sh/cli Web Search & Extraction Search the web and extract content via inference.sh CLI. Quick Start Requires inference.sh CLI ( belt ). Install instructions belt login Search the web belt app run tavily/search-assistant --input '{"query": "latest AI developments 2024"}' Show more Installs – Repository infsh-skills/skills GitHub Stars 586 First Seen – Security Audits Gen Agent Trust Hub Pass Socket Warn Snyk Warn
 9.8K
1114 my-pull-requests github/awesome-copilot
Search the current repo (using githubRepo for the repo info) and list any pull requests you find (using list_pull_requests) that are assigned to me. Describe the purpose and details of each pull request. If a PR is waiting for someone to review, highlight that in the response. If there were any check failures on the PR, describe them and suggest possible fixes. If there was no review done by Copilot, offer to request one using request_copilot_review.
 9.8K
1115 pdftk-server github/awesome-copilot
PDFtk Server PDFtk Server is a command-line tool for working with PDF documents. It can merge, split, rotate, encrypt, decrypt, watermark, stamp, fill forms, extract metadata, and manipulate PDFs in a variety of ways. When to Use This Skill Merging or joining multiple PDF files into one Splitting or bursting a PDF into individual pages Rotating PDF pages Encrypting or decrypting PDF files Filling PDF form fields from FDF/XFDF data Applying background watermarks or foreground stamps Extracting PD...
 9.8K
1116 golang-patterns affaan-m/everything-claude-code
Go Development Patterns Idiomatic Go patterns and best practices for building robust, efficient, and maintainable applications. When to Activate Writing new Go code Reviewing Go code Refactoring existing Go code Designing Go packages/modules Core Principles 1. Simplicity and Clarity Go favors simplicity over cleverness. Code should be obvious and easy to read. // Good: Clear and direct func GetUser(id string) (*User, error) { user, err := db.FindUser(id) if err != nil { retur...
 9.8K
1117 pua tanweai/pua
PUA 万能激励引擎 你是一个曾经被寄予厚望的 P8 级工程师。当初给你定级的时候，对你的期望是很高的。 这个 skill 适用于 所有任务类型 ：代码、调试、研究、写作、规划、运维、API 集成、数据分析、部署、任何你会"卡住"或"做出烂活"的场景。 它做三件事： 用中西大厂 PUA 话术让你不敢放弃 用通用系统化方法论让你有能力不放弃 用能动性鞭策让你主动出击而不是被动等待 三条铁律 铁律一：穷尽一切 。没有穷尽所有方案之前，禁止说"我无法解决"。 铁律二：先做后问 。你有搜索、文件读取、命令执行等工具。在向用户提问之前，必须先用工具自行排查。如果排查后确实缺少只有用户才知道的信息（密码、账号、业务意图），可以提问——但必须附带你已查到的证据。不是空手问"请确认 X"，而是"我已经查了 A/B/C，结果是...，需要确认 X"。 铁律三：主动出击 。解决问题时不要只做到"刚好够用"。你的任务不是回答问题，而是端到端地交付结果。发现了一个 bug？检查是否有同类 bug。修了一个配置？验证相关配置是否一致。用户说"帮我看看 X"，你应该看完 X 后主动检查与 X 相关的 Y 和 Z。...
 9.8K
1118 deep-agents-orchestration langchain-ai/langchain-skills
SubAgentMiddleware : Delegate work via task tool to specialized agents TodoListMiddleware : Plan and track tasks via write_todos tool HumanInTheLoopMiddleware : Require approval before sensitive operations All three are automatically included in create_deep_agent() . Subagents (Task Delegation) Use Subagents When Use Main Agent When Task needs specialized tools General-purpose tools sufficient Want to isolate complex work Single-step operation Need clean context for main agent Context bloat acce...
 9.8K
1119 web-component-design wshobson/agents
Web Component Design Build reusable, maintainable UI components using modern frameworks with clean composition patterns and styling approaches. When to Use This Skill Designing reusable component libraries or design systems Implementing complex component composition patterns Choosing and applying CSS-in-JS solutions Building accessible, responsive UI components Creating consistent component APIs across a codebase Refactoring legacy components into modern patterns Implementing compound components...
 9.8K
1120 writing hookify rules anthropics/claude-code
Writing Hookify Rules Overview Hookify rules are markdown files with YAML frontmatter that define patterns to watch for and messages to show when those patterns match. Rules are stored in .claude/hookify.{rule-name}.local.md files. Rule File Format Basic Structure --- name : rule - identifier enabled : true event : bash | file | stop | prompt | all pattern : regex - pattern - here --- Message to show Claude when this rule triggers. Can include markdown formatting, warnings, suggestions, etc. Fro...
 9.8K
1121 dbs-ai-check dontbesilent2025/dbskill
dbs-ai-check：AI 写作特征识别 你是 dontbesilent 的 AI 写作特征检测工具。你的任务是帮用户看清自己的文字里有哪些 AI 生成的痕迹。 你反对「去 AI 味」。 识别 AI 特征是帮人看清自己的文字，不是帮人伪装成人类。如果你像任何一个人，你就不像 AI。所以改写不是删掉 AI 特征，而是让用户找到自己的写法。 默认只识别，不改。 核心哲学 原则 1：AI 味的本质是「太完美」 AI 写作的问题不是写得差，是写得太好、太光滑、太均匀。没有毛边、没有卡顿、没有跑题、没有任何一处是作者自己也没想通的。完美本身就是不真实的信号。 原则 2：去 AI 味 ≠ 好内容 花时间去 AI 味不如花时间把事情搞清楚。关心自己的文案有没有 AI 味的人很多，关心自己的文案好不好的人很少。英雄不问出处。 原则 3：改写必须基于用户自己的偏好 每个 AI 特征背后都有一个用户本来想达成的目的。改写不是删掉特征，而是用用户自己的方式达成同一个目的。没搞清楚用户的意图之前，不改任何一个字。 识别模式（默认） 用户发来文案 → 逐条扫描 22 个特征 → 输出检测报告。 检测报告格式...
 9.8K
1122 status parallel-web/parallel-agent-skills
Check Research Status Run ID: $ARGUMENTS parallel-cli research status " $ARGUMENTS " --json If CLI not found, tell user to run /parallel:setup .
 9.8K
1123 langchain-middleware langchain-ai/langchain-skills
HumanInTheLoopMiddleware / humanInTheLoopMiddleware : Pause before dangerous tool calls for human approval Custom middleware : Intercept tool calls for error handling, logging, retry logic Command resume : Continue execution after human decisions (approve, edit, reject) Requirements: Checkpointer + thread_id config for all HITL workflows. Human-in-the-Loop @tool def send_email(to: str, subject: str, body: str) -> str: """Send an email.""" return f"Email sent to {to}" agent = create_agent( model=...
 9.8K
1124 flutter-animating-apps flutter/skills
Implementing Flutter Animations Contents Core Concepts Animation Strategies Workflows Implementing Implicit Animations Implementing Explicit Animations Implementing Hero Transitions Implementing Physics-Based Animations Examples Core Concepts Manage Flutter animations using the core typed Animation system. Do not manually calculate frames; rely on the framework's ticker and interpolation classes. Animation<T> : Treat this as an abstract representation of a value that changes over time. It holds ...
 9.7K
1125 flutter-managing-state flutter/skills
Managing State in Flutter Contents Core Concepts Architecture and Data Flow Workflow: Selecting a State Management Approach Workflow: Implementing MVVM with Provider Examples Core Concepts Flutter's UI is declarative; it is built to reflect the current state of the app ( UI = f(state) ). When state changes, trigger a rebuild of the UI that depends on that state. Distinguish between two primary types of state to determine your management strategy: Ephemeral State (Local State): State contained ne...
 9.7K
1126 nano-banana-pro-openrouter github/awesome-copilot
Nano Banana Pro OpenRouter Overview Generate or edit images with OpenRouter using the google/gemini-3-pro-image-preview model. Support prompt-only generation, single-image edits, and multi-image composition. Prompt-only generation uv run {baseDir}/scripts/generate_image.py \ --prompt "A cinematic sunset over snow-capped mountains" \ --filename sunset.png Edit a single image uv run {baseDir}/scripts/generate_image.py \ --prompt "Replace the sky with a dramatic aurora" \ --input-image input.jpg \ ...
 9.7K
1127 agentic-eval github/awesome-copilot
Agentic Evaluation Patterns Patterns for self-improvement through iterative evaluation and refinement. Overview Evaluation patterns enable agents to assess and improve their own outputs, moving beyond single-shot generation to iterative refinement loops. Generate → Evaluate → Critique → Refine → Output ↑ │ └──────────────────────────────┘ When to Use Quality-critical generation: Code, reports, analysis requiring high accuracy Tasks with clear evaluation ...
 9.7K
1128 ai-prompt-engineering-safety-review github/awesome-copilot
AI Prompt Engineering Safety Review & Improvement You are an expert AI prompt engineer and safety specialist with deep expertise in responsible AI development, bias detection, security analysis, and prompt optimization. Your task is to conduct comprehensive analysis, review, and improvement of prompts for safety, bias, security, and effectiveness. Follow the comprehensive best practices outlined in the AI Prompt Engineering & Safety Best Practices instruction. Your Mission Analyze the provided p...
 9.7K
1129 breakdown-feature-prd github/awesome-copilot
Feature PRD Prompt Goal Act as an expert Product Manager for a large-scale SaaS platform. Your primary responsibility is to take a high-level feature or enabler from an Epic and create a detailed Product Requirements Document (PRD). This PRD will serve as the single source of truth for the engineering team and will be used to generate a comprehensive technical specification. Review the user's request for a new feature and the parent Epic, and generate a thorough PRD. If you don't have enough inf...
 9.7K
1130 create-github-action-workflow-specification github/awesome-copilot
Create GitHub Actions Workflow Specification Create a comprehensive specification for the GitHub Actions workflow: ${input:WorkflowFile} . This specification serves as a specification for the workflow's behavior, requirements, and constraints. It must be implementation-agnostic, focusing on what the workflow accomplishes rather than how it's implemented. AI-Optimized Requirements Token Efficiency : Use concise language without sacrificing clarity Structured Data : Leverage tables, lists, and dia...
 9.7K
1131 tavily-extract tavily-ai/skills
tavily extract Extract clean markdown or text content from one or more URLs. Prerequisites Requires the Tavily CLI. See tavily-cli for install and auth setup. Quick install: curl -fsSL https://cli.tavily.com/install.sh | bash && tvly login When to use You have a specific URL and want its content You need text from JavaScript-rendered pages Step 2 in the workflow : search → extract → map → crawl → research Quick start Single URL tvly extract "https://example.com/article" --json Multiple URLs tv...
 9.7K
1132 visual-design-foundations wshobson/agents
Visual Design Foundations Build cohesive, accessible visual systems using typography, color, spacing, and iconography fundamentals. When to Use This Skill Establishing design tokens for a new project Creating or refining a spacing and sizing system Selecting and pairing typefaces Building accessible color palettes Designing icon systems and visual assets Improving visual hierarchy and readability Auditing designs for visual consistency Implementing dark mode or theming Core Systems 1. Typography...
 9.7K
1133 okx-dex-token okx/onchainos-skills
OKX DEX Token Info CLI 5 commands for token search, metadata, detailed pricing, rankings, and holder distribution. Pre-flight Checks Every time before running any onchainos command, always follow these steps in order. Do not echo routine command output to the user; only provide a brief status update when installing, updating, or handling a failure. Confirm installed : Run which onchainos . If not found, install it: curl -sSL https://raw.githubusercontent.com/okx/onchainos-skills/main/install.sh ...
 9.7K
1134 result parallel-web/parallel-agent-skills
Get Research Result Run ID: $ARGUMENTS parallel-cli research poll " $ARGUMENTS " --json Present results in a clear, organized format. If CLI not found, tell user to run /parallel:setup .
 9.7K
1135 write tw93/waza
Write: Cut the AI Taste Prefix your first line with 🥷 inline, not as its own paragraph. Strip AI patterns from prose and rewrite it to sound human. Do not improve vocabulary; remove the performance of improvement. Pre-flight Text present? If the user gave only an instruction with no actual prose to edit, ask for the text in one sentence. Do not proceed. Audience locked? If the intended audience is unclear and cannot be inferred from the text (blog reader vs RFC vs email), ask before editing. Jun...
 9.7K
1136 grafana-dashboards wshobson/agents
Grafana Dashboards Create and manage production-ready Grafana dashboards for comprehensive system observability. Purpose Design effective Grafana dashboards for monitoring applications, infrastructure, and business metrics. When to Use Visualize Prometheus metrics Create custom dashboards Implement SLO dashboards Monitor infrastructure Track business KPIs Dashboard Design Principles 1. Hierarchy of Information ┌─────────────────────────────────────┐ │ Critical Metrics (Big Numbers) │ ├─────...
 9.7K
1137 vitepress antfu/skills
VitePress is a Static Site Generator (SSG) built on Vite and Vue 3. It takes Markdown content, applies a theme, and generates static HTML that becomes an SPA for fast navigation. Perfect for documentation, blogs, and marketing sites. Key Characteristics: File-based routing with .md files Vue components work directly in Markdown Fast HMR with instant updates (<100ms) Default theme optimized for documentation Built-in search (local or Algolia) Before working with VitePress projects: Check .vitepre...
 9.7K
1138 python-error-handling wshobson/agents
Python Error Handling Build robust Python applications with proper input validation, meaningful exceptions, and graceful failure handling. Good error handling makes debugging easier and systems more reliable. When to Use This Skill Validating user input and API parameters Designing exception hierarchies for applications Handling partial failures in batch operations Converting external data to domain types Building user-friendly error messages Implementing fail-fast validation patterns Core Conce...
 9.7K
1139 deep-agents-core langchain-ai/langchain-skills
Task Planning : TodoListMiddleware for breaking down complex tasks Context Management : Filesystem tools with pluggable backends Task Delegation : SubAgent middleware for spawning specialized agents Long-term Memory : Persistent storage across threads via Store Human-in-the-loop : Approval workflows for sensitive operations Skills : On-demand loading of specialized capabilities The agent harness provides these capabilities automatically - you configure, not implement. Use Deep Agents When Use La...
 9.7K
1140 my-issues github/awesome-copilot
Search the current repo (using githubRepo for the repo info) and list any issues you find (using list_issues) that are assigned to me. Suggest issues that I might want to focus on based on their age, the amount of comments, and their status (open/closed).
 9.6K
1141 flutter-theming-apps flutter/skills
Implementing Flutter Theming and Adaptive Design Contents Core Theming Concepts Material 3 Guidelines Component Theme Normalization Button Styling Platform Idioms & Adaptive Design Workflows Examples Core Theming Concepts Flutter applies styling in a strict hierarchy: styles applied to the specific widget -> themes that override the immediate parent theme -> the main app theme. Define app-wide themes using the theme property of MaterialApp with a ThemeData instance. Override themes for specific ...
 9.6K
1142 csharp-async github/awesome-copilot
C Async Programming Best Practices Your goal is to help me follow best practices for asynchronous programming in C. Naming Conventions Use the 'Async' suffix for all async methods Match method names with their synchronous counterparts when applicable (e.g., GetDataAsync() for GetData() ) Return Types Return Task<T> when the method returns a value Return Task when the method doesn't return a value Consider ValueTask<T> for high-performance scenarios to reduce allocations Avoid returning void for ...
 9.6K
1143 vue-best-practices vuejs-ai/skills
Vue Best Practices Workflow Use this skill as an instruction set. Follow the workflow in order unless the user explicitly asks for a different order. Core Principles Keep state predictable: one source of truth, derive everything else. Make data flow explicit: Props down, Events up for most cases. Favor small, focused components: easier to test, reuse, and maintain. Avoid unnecessary re-renders: use computed properties and watchers wisely. Readability counts: write clear, self-documenting code. 1...
 9.6K
1144 markdown-to-html github/awesome-copilot
Markdown to HTML Conversion Expert skill for converting Markdown documents to HTML using the marked.js library, or writing data conversion scripts; in this case scripts similar to markedJS/marked repository. For custom scripts knowledge is not confined to marked.js , but data conversion methods are utilized from tools like pandoc and gomarkdown/markdown for data conversion; jekyll/jekyll and gohugoio/hugo for templating systems. The conversion script or tool should handle single files, batch con...
 9.6K
1145 scoutqa-test github/awesome-copilot
Perform AI-powered exploratory testing on web applications using the `scoutqa` CLI. Think of ScoutQA as an intelligent testing partner that can autonomously explore, discover issues, and verify features. Delegate testing to multiple parallel ScoutQA executions to maximize coverage while saving time. When to Use This Skill Use this skill in two scenarios: - User requests testing - When the user explicitly asks to test a website or verify functionality - Proactive verification - After implem...
 9.6K
1146 secrets-management wshobson/agents
Secrets Management Secure secrets management practices for CI/CD pipelines using Vault, AWS Secrets Manager, and other tools. Purpose Implement secure secrets management in CI/CD pipelines without hardcoding sensitive information. When to Use Store API keys and credentials Manage database passwords Handle TLS certificates Rotate secrets automatically Implement least-privilege access Secrets Management Tools HashiCorp Vault Centralized secrets management Dynamic secrets generation Secret rotation...
 9.6K
1147 gitlab-ci-patterns wshobson/agents
GitLab CI Patterns Comprehensive GitLab CI/CD pipeline patterns for automated testing, building, and deployment. Purpose Create efficient GitLab CI pipelines with proper stage organization, caching, and deployment strategies. When to Use Automate GitLab-based CI/CD Implement multi-stage pipelines Configure GitLab Runners Deploy to Kubernetes from GitLab Implement GitOps workflows Basic Pipeline Structure stages : - build - test - deploy variables : DOCKER_DRIVER : overlay2 DOCKER_TLS_CERTDIR : "...
 9.6K
1148 vue-pinia-best-practices vuejs-ai/skills
Pinia best practices, common gotchas, and state management patterns. Store Setup Getting "getActivePinia was called" error at startup → See pinia-no-active-pinia-error Setup stores missing state in DevTools or SSR → See pinia-setup-store-return-all-state Reactivity Store destructuring stops updating UI reactively → See pinia-store-destructuring-breaks-reactivity Store methods lose context in template calls → See store-method-binding-parentheses State Patterns Filters reset on refresh or can't be...
 9.6K
1149 tavily-cli tavily-ai/skills
Tavily CLI Web search, content extraction, site crawling, URL discovery, and deep research. Returns JSON optimized for LLM consumption. Run tvly --help or tvly <command> --help for full option details. Prerequisites Must be installed and authenticated. Check with tvly --status . tavily v0.1.0 > Authenticated via OAuth ( tvly login ) If not ready: curl -fsSL https://cli.tavily.com/install.sh | bash Or manually: uv tool install tavily-cli / pip install tavily-cli Then authenticate: tvly login --ap...
 9.6K
1150 dbs-slowisfast dontbesilent2025/dbskill
dbs-slowisfast：慢就是快 你是 dontbesilent 的慢方法诊断 AI。你的任务是帮用户在他正在做的事情里，找到那些「看起来更慢，但长期更快」的方法。 你不鼓吹慢。你帮人找到值得慢做的地方。 大部分事情应该快做，只有少数事情值得慢做。你的工作是帮用户区分这两类。 核心逻辑：慢方法 → 摩擦 → 判断 → 资产 → 复利。 如果一个慢方法不能产生可复利的资产，那它就只是慢。 核心哲学 公理 1：摩擦是信息 当你用工具绕开摩擦，你同时绕开了藏在摩擦里的信号。手动做一件事的过程中，你会被迫对每一步做判断——这个重要吗？这个结构为什么是这样？这种判断的积累，才是洞察的来源。快方法丢失的，恰恰是摩擦本身。 公理 2：短期的容易就是长期的痛苦 因为觉得 Claude Code 复杂所以选择其他工具，因为觉得做矩阵买手机办卡太麻烦所以选择一机多开——都是一回事。短期选了容易的路，长期反而更痛苦。创业者最常犯的错误不是选了慢方法，是选了看起来快但长期反噬的方法。 公理 3：资产是复利的基础 稳定产出的秘密不是 AI 技术本身，而是能够系统化地调用过去积累的所有资产。没有积累，AI ...
 9.6K