rxa3c/chat2skill

Name: rxa3c/chat2skill
Author: rxa3c

Plugin插件 Native原生 ⭐ 2 MIT Models & Routing模型与路由 Sessions & Context会话与上下文 Prompts & Skills提示词与技能

从日常与AI的对话中提取并迭代技能

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

Chat2Skill is a cross-agent tool that automatically extracts reusable knowledge from AI assistant conversations. It builds a local SQLite database of project memory and generates atomic SKILL.md files for generalizable preferences, procedures, constraints, and patterns. It natively integrates with Claude Code, Codex, and Cursor, and can work with any other AI agent that supports lifecycle hooks or can run the included CLI scripts, including DSH. It requires only Python 3.10+ to run the core workflow, with no extra pip packages needed for basic use.

Chat2Skill follows a continuous feedback learning loop. After each assistant session completes, it extracts learning signals from the conversation, makes a decision to create, edit, or discard a skill candidate, then validates and merges new or updated skills into the active skill bank. It updates the synthesized PROJECT_SKILL.md file after each loop, which can be reviewed by the user to adjust project-level response policies. Skills are namespaced per user and project to prevent cross-repo knowledge leaks. Coding workflows are the first-class target, but the tool works for any domain that produces conversational transcripts.

The tool prioritizes user privacy by default. All conversation transcripts are filtered locally to remove agent noise before any content is sent to the Chat2Skill API for analysis. Content is processed in-memory on the server and never persisted, only metadata is logged server-side. All skill and memory data is stored locally on the user's machine in the ~/.chat2skill directory. If you do not want any content uploaded, just unset the API URL config to disable all uploads. Node.js is optional for local embedding support, and the entire project is released under the permissive MIT license.

Chat2Skill是一款跨AI编码代理平台的对话记忆提取工具，可从每次助手对话中自动提炼可复用的技能、项目偏好、约束条件、项目事实等信息，存储为本地SKILL.md文件和SQLite项目记忆库，在后续对话中自动注入相关上下文。它原生支持Claude Code、Codex、Cursor等多款主流代理，也可适配DSH等其他支持生命周期钩子或CLI脚本的代理平台。

它的核心工作流是闭环反馈学习，每次会话结束后提取学习信号，创建、编辑或废弃技能候选，验证合并后更新活跃技能库，最后重构项目级技能文件供人工审核。它支持领域通用场景，编码工作流是优先适配目标，也可用于支持、研究、写作、运营等其他产生对话记录的领域。

该工具要求Python 3.10以上，仅使用标准库无需额外pip安装，可选Node.js用于本地嵌入。所有对话内容会先在本地过滤噪声后再上传分析，服务端不持久化存储内容，仅在本地存储技能和记忆数据，遵循MIT开源许可，可免费使用修改。

View on GitHub在 GitHub 查看

Send to your DSH发给你的 DSH 安装

请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：chat2skill（rxa3c/chat2skill）
仓库：https://github.com/rxa3c/chat2skill
本站详情页：https://www.yhbd.top/plugins/rxa3c-chat2skill/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 2 · 最近提交 2026-08-27 · 主语言 Python

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意

Only 2 stars - very few users, little community feedback星标只有 2，几乎没人在用，遇到问题缺少社区反馈

DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时（Electron / Python / Docker 等）是否齐备
Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突：命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致，是否归档或长期停更
Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需（filesystem / network / shell / clipboard）
Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限，以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照，不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装（适合开发者）

CLI Install命令行安装

dsh plugin --profile web add github:rxa3c/chat2skill

把 rxa3c/chat2skill 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

27.4 KB · 缓存于 2026-08-25 04:53:52 · 27.4 KB

Chat2Skill

Automatically learn reusable skills and project memory from your assistant conversations.

After each session, Chat2Skill analyzes the conversation for corrections, preferences, constraints, and project facts, distills them into local memory and SKILL.md files, and injects the relevant ones into your future sessions. It is domain-general: coding workflows are the first-class integration target, while the same mechanism works for support, research, writing, operations, sales, education, and other assistant domains that produce usable transcripts.

Works best with Claude Code, Codex, and Cursor. Other agents can use Chat2Skill when they support lifecycle hooks or can run the included CLI scripts.

What the Algorithm Produces

Chat2Skill extracts reusable project context in two stores:

Atomized skills: focused SKILL.md files for one interaction preference, procedure, constraint, success pattern, or failure pattern.
Project memory: project facts, decisions, procedures, and warnings stored in the local SQLite database and retrieved dynamically.
Project skill: a synthesized PROJECT_SKILL.md that merges active atomized skills into a compact project-level instruction file for human review and response-guard policy.

A skill is not meant to remember one transcript. It captures a generalizable behavior that would change future assistant behavior across similar situations.

Core Concepts

Concept	Meaning
Conversation	Recent assistant/user messages for one session. Long sessions are trimmed to the latest analysis window.
Signal	Evidence that something should be learned: correction, explicit constraint, negative feedback, or stable behavioral preference.
Analysis	A structured diagnosis of what went wrong or what worked, including failure type, root cause, confidence, and proposed action.
Proposal	The create/edit/discard decision for a skill candidate.
Memory item	Evidence extracted before materializing a skill, such as failure cause, failure memory, success, or constraint.
Skill	A validated, actionable `SKILL.md` with metadata such as confidence, evidence count, language, replay score, and status.
Response guard	Optional frontmatter policy for hard wording constraints, such as evidence-based deterministic wording.

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要，完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

渲染基于仓库 rxa3c/chat2skill 的 README.md。在 GitHub 查看原文 →