book2skills

Harness Engineering 第一阶段：扫描现有项目，生成 AGENTS.md（目录文件）和完整的 docs/ 知识库结构。 当用户想要"为项目添加 agent 支持"、"让 AI 更好地理解我的项目"、"开始 harness engineering"、 "创建 AGENTS.md"、"搭建 agent 文档结构"、"让 Claude Code 更好地工作"时，立即使用此 skill。 也适用于用户说"帮我把项目文档整理好给 agent 用"、"我想开始用 AI agent 开发"、 "梳理这个项目能解决什么业务问题"或要求建立 business-solution.md 等场景。

Harness Engineering 第一阶段第二步：深度分析项目代码，填充业务解决方案、架构、约定、技术决策和质量标准等 docs/ 知识库内容。 在 harness-step1-create-agents-md 创建好目录骨架之后使用。当用户说"填充文档内容"、 "完善 docs/ 文件"、"让文档有实质内容"、"分析项目写架构文档"、"写 ARCHITECTURE.md"、 "写技术决策文档"、"从业务视角理解项目"、"完善 business-solution.md"时，立即使用此 skill。 前置条件：项目中已有 AGENTS.md 和 docs/ 目录骨架（由 harness-step1 创建）。

Developer implementation guide for building hierarchical (folded) memory into an Agent. Three-layer architecture where recent turns stay detailed, older content compresses into episodes, and the oldest distills into durable semantic facts. Use when compact-memory-implementation is not retaining enough, or when agents need to recall decisions from many sessions ago.

Design and implement a layered, configurable permission/safety system for agent tools. Use this skill when building an agent that needs to control which tool calls are auto-allowed, which require user confirmation, and which are denied — especially when the system must be configurable across multiple scopes (project/user/enterprise) and extensible via hooks. Triggers on: "权限系统", "工具安全", "tool permission", "permission system", "tool safety", "allow/deny rules", "hook system", "构建安全机制".

Define agent tools using the fail-closed design pattern — unified name/schema/security/execution in one class, with three-layer execution (validate → permission → call). Use this skill whenever the user wants to define a new agent tool, add permission or validation logic to an existing tool, or asks about 'build a tool', '定义一个工具', 'create a tool for X', '工具定义'. Framework-agnostic: works with hermes-agent, LangChain, or any Python agent framework.

Build LangChain (Python) tools using Claude Code's fail-closed design pattern — unified name/schema/security/execution in one class, with automatic three-layer execution (validate → permission → call). Use this skill whenever the user wants to define a new LangChain tool, add permission or validation logic to an existing tool, set up the ClaudeStyleTool base class in a project, or asks about "build_tool", "Claude Code style tool", "工具定义", or "langchain tool with permissions". Also trigger when the user says "create a tool for X" or "定义一个工具" in a LangChain Python project context, even without mentioning Claude Code explicitly.

Developer implementation guide for adding compact memory to an Agent — covers fork agent pattern for compaction, trigger strategy, summary format design, and memory restoration in subsequent sessions. Use when a developer asks how to implement compact memory, context compression, or memory persistence in their agent built with Claude Agent SDK or Anthropic API.

Restructures a chaotic or overgrown MEMORY.md into a clean 2-layer architecture based on how Claude Code's autoDream system organizes memory — a lightweight pointer index (always loaded) and topic files (loaded on demand). Stale or superseded memories are deleted or corrected in place — not archived. Use this skill whenever the user says "clean up MEMORY.md", "reorganize my memory files", "MEMORY.md is getting too long", "fix my memory structure", or when you observe that MEMORY.md exceeds 200 lines, contains full paragraphs instead of pointers, or mixes index entries with topic content.

End-of-session memory distillation — extracts key decisions, eliminated approaches, new discoveries, and current blockers from the current conversation and writes them to MEMORY.md topic files. Based on Claude Code's autoDream background consolidation service. Activate when the user says "dream", "/dream", "save session memories", "distill this session", "what should I remember from this session", or when a long productive session is ending and the user wants to preserve what was learned.

Implement a production-ready LLM query loop / agent loop for AI applications. Use this skill whenever the user wants to add tool calling, ReAct-style reasoning-action-observation cycles, function calling loops, query engines, agent runtimes, tool_result feedback, max-turn exits, or Claude Code-like Agent Loop behavior to their own product or codebase.

Apply Jonah Berger's STEPPS framework. Trigger on: "why is this not spreading?", "make this campaign contagious", "diagnose viral content".

Analyze Wall Street conflicts. Trigger on: "can I trust this advisor?", "is this forecast reliable?", "whose interest does this serve?".

Apply Keynes policy reasoning. Trigger on: "will austerity work?", "inflation or deflation?", "analyze this economic crisis".

Apply Ryan Holiday's perennial seller framework. Trigger on: "will this work last?", "position my book/product", "build an enduring launch".

Apply Austin Kleon's sharing framework. Trigger on: "what should I share?", "build an audience", "document my creative process".

Apply Seth Godin's marketing framework. Trigger on: "find my smallest viable audience", "position this offer", "earn trust".

Apply John Bogle stewardship capitalism logic to separate investing from speculation, diagnose financial-system costs, and critique Wall Street incentives.

Apply John Bogle index investing rules for low-cost funds, asset allocation, fees, taxes, ETFs, advisers, and buy-hold discipline.

Use Graham value investing for Is this investment or speculation, defensive stock screens, margin of safety, Mr. Market, allocation, funds, IPOs.

Apply Pulak Prasad evolutionary investing rules for avoiding big losses, buying resilient quality, rejecting fragile forecasts, and being very lazy.

Apply Gary Vaynerchuk social content rules for native jabs, right hooks, platform fit, campaign critique, and engagement before conversion.

Apply Howard Marks investing judgment for second-level thinking, price versus value, risk control, cycles, contrarianism, and defensive investing.

Apply The Outsiders CEO framework to assess capital allocation, per-share value creation, buybacks, decentralization, and rational leadership.

Audit SEO metadata such as title, description, headings, alt, robots, canonical, schema, viewport, charset, and social tags.

Apply Austin Kleon creative practice for idea theft, remixing, starting work, sharing process, constraints, and sustainable output.

Apply Steven Pressfield resistance diagnosis for procrastination, turning pro, daily creative discipline, fear, hierarchy, and territory.

Apply China contract drafting review with San Guan Si Bu Fa. Trigger on contract review, drafting, clauses, or deal structure.

Apply Charlie Munger mental models to investments, decisions, and bias diagnosis. Trigger on Munger checklist or spot biases.

Use Business Adventures for "why did this fail?", "analyze this crisis", "what pattern applies?", or "what would Brooks notice?"

Use StoryBrand for "clarify my message", "rewrite my homepage", "create a BrandScript", "what is my one-liner", or "fix my CTA".

Apply Brittany Hodak's SUPER Model for customer loyalty, referrals, word of mouth, personalization, service recovery, and scalable customer experience.

Apply Xiao Xing's financial statement analysis framework from 一本书读懂财报 (Understanding Financial Reports in One Book). Use this skill whenever a user wants to assess whether a company's assets are of high quality, verify whether reported profits are real, diagnose cash flow health, evaluate solvency and turnover efficiency, or judge overall investment value via ROIC. Covers industry context analysis, asset & liability quality check, profit authenticity verification, cash flow diagnosis, solvency analysis, and good-company composite scoring. Trigger phrases: "analyze financials", "is this company healthy", "are profits real", "cash flow diagnosis", "ROIC analysis", "red flags in balance sheet", "good company test", "财报分析", "利润质量", "现金流健康".

Apply Philip Fisher's growth stock investment framework from Common Stocks and Uncommon Profits. Use this skill whenever a user wants to evaluate whether a company is a worthy long-term growth investment, assess management quality, gather competitive intelligence via scuttlebutt, decide when to buy an outstanding stock at the right moment, or decide whether to hold or sell a current position. Covers the 15 Points checklist, management depth analysis, scuttlebutt intelligence gathering, entry timing, and hold/sell decision logic. Trigger phrases: "is X a growth stock", "Fisher framework", "15 points", "scuttlebutt", "should I buy X", "should I sell X", "management quality of X", "growth stock analysis".

Analyzes Chinese public company financial statements (balance sheet, income statement, cash flow) to assess asset quality, profit authenticity, cash flow health, solvency, and overall investment value. Use when the user provides financial data or a company name and asks whether financials are healthy, whether profits are real, whether there are red flags, or whether the company is a good investment. Based on the book "一本书读懂财报" by Xiao Xing (Tsinghua University).

Harness Engineering 第二阶段：建立跨 session 状态管理，解决 agent 每次对话失忆的问题。 创建 tasks.json（任务清单）、progress.md（进度记录）、init.sh（环境初始化脚本）三个文件。 当用户说"建立任务管理"、"让 agent 记住进度"、"创建 tasks.json"、"跨 session 保持状态"、 "agent 每次都不记得上次做了什么"、"建立 progress 文件"、"初始化状态管理"时，立即使用此 skill。 前置条件：harness-step1 和 harness-step2 已完成（项目有 AGENTS.md 和 docs/ 知识库）。