with one click
knowledge-distiller
根据用户需求检索项目代码,提取事实、模式、决策链条,并以自然语言生成一个或多个非代码知识文档到 /docs/kb/
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Menu
根据用户需求检索项目代码,提取事实、模式、决策链条,并以自然语言生成一个或多个非代码知识文档到 /docs/kb/
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use this skill when the user asks to review performance hotspots, algorithmic complexity, memory usage, latency, caching opportunities, or concurrency tradeoffs. It performs evidence-based performance review and separates obvious fixes from issues that should be profiled first.
Use this skill when the user asks to review formatting, naming conventions, language idioms, lint/style consistency, or import organization. It checks style against project conventions and distinguishes auto-fixable issues from manual fixes.
Bridge between Claude Code and OpenAI Codex CLI - generates AGENTS.md from CLAUDE.md, provides Codex CLI execution helpers, and enables seamless interoperability between both tools
Generates cross-platform commands and scripts for Linux, macOS, and Windows with security validation and compatibility guidance
Execute AI tasks (codex/claude/gemini) with memory and resume support via memex-cli stdin protocol.
Fallback to memex-cli when codeagent-wrapper is unavailable. Automatically converts codeagent-wrapper syntax to memex-cli stdin protocol and executes.
| name | knowledge-distiller |
| description | 根据用户需求检索项目代码,提取事实、模式、决策链条,并以自然语言生成一个或多个非代码知识文档到 /docs/kb/ |
| version | 0.1.0 |
用于把“代码里的隐性知识”提炼成可读、可维护、可复用的知识文档。
在 /docs/kb/ 生成一个或多个 Markdown 文档,核心内容是:
文档必须以自然语言表达,不输出大段代码。
明确提炼范围
检索代码证据
README.md、CLAUDE.md、配置文件、入口文件、关键模块目录提炼知识结构
生成知识文档
/docs/kb/,命名建议:
topic-overview.mdtopic-patterns.mdtopic-decision-chain.md/docs/kb/README.md 索引质量校验
# <主题名称>
## 1. 背景与范围
## 2. 关键事实
- 事实 1
- 事实 2
## 3. 稳定模式
- 模式 1
- 模式 2
## 4. 决策链条
1. 背景
2. 约束
3. 备选方案
4. 最终选择
5. 结果与影响
## 5. 实践建议
## 6. 证据来源
- path/to/fileA
- path/to/fileB
/docs/kb/