REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
The why layer of repo-native project memory: the reasoning behind a codebase as Markdown in the repo, versioned by Git, for coding agents and humans, so nothing rejected is proposed twice. No database, no daemon, no account.
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/skills/oliver-zehentleitner-keep-the-why)在同一工作中把 AI 连到服务的 MCP
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
MCP server for terminal commands, file operations, and process management
同类工作,排序与 Skill 列表相同
| 本项 keep-the-why | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| 作者 | oliver-zehentleitner | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skill 数 | 1 | 1 | 1 | 1 | 1 |
| GitHub 星标 | 242 | 468,733 | 234,332 | 150,287 | 144,566 |
| 最近代码更新 | 2026年11月18日 | 2026年11月19日 | 2026年4月20日 | 2026年11月18日 | 2026年11月18日 |
| 许可证 | MIT | MIT | – | Apache-2.0 | MIT |
oliver-zehentleitner 提供的 1 个 Skill(指令集),AI 读取后照做 · 不是 MCP server
MCP = 手
把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。
Skill = 手册
教 AI 怎么做某项工作的文本文件,不连接任何服务。
有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。
Claude CodeCodexCursorGemini CLIGitHub CopilotOpenCode
依据开发者 README 和 repo 中的文件夹
GitHub account oliver-zehentleitner (person), 7 years old
★ 242 stars, few users so far · code last changed 2026年11月18日
No, plain text files the AI reads and follows
No scripts, so it does not go online by itself
No hooks or writes to machine settings found
Checked automatically from the repo files at commit 8fa9b76 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
第一步:你用哪个 AI?
选择你用的应用,本页只显示该应用的安装方法
Uploading to claude.ai would fail: the description is over 200 characters (576). Use "Let the AI install it" instead
复制这句话,粘贴到 Claude Code 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
重新打开 Claude Code,输入 /keep-the-why,或直接提出相关任务,Claude 会自动选用
Checked against official docs 2026年11月12日 · Source: code.claude.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
已隐藏作者的命令 · 它不是从 GitHub 上的这个仓库安装 · 命令未通过检查,已隐藏 · 请改从作者的 GitHub 页面安装
摘自开发者 README,会下载并运行开发者的代码
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
ChatGPT 桌面应用内置 Codex,Codex 从 ~/.agents/skills 文件夹读取 Skill
在 ChatGPT 桌面应用中打开 Codex,把这句话粘贴到对话中
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
把 keep-the-why 文件夹放到 ~/.agents/skills/keep-the-why
~ 是你的主文件夹($HOME)
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
不能使用你自己安装的 Skill,只能使用目录中插件自带的 Skill
想在 ChatGPT 中使用这个 Skill,请按上面的方法使用 ChatGPT 桌面应用
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
复制这句话,粘贴到 Codex 的对话中 · 适用于 ChatGPT 桌面应用中的 Codex、Codex CLI 和 IDE 扩展
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex · 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
复制这句话,粘贴到 Cursor 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
在 Cursor 的 Agent 聊天中输入 / 并选择 keep-the-why
Checked against official docs 2026年11月12日 · Source: cursor.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
适用于其他能读取 Skill 的应用。这句话列出了 Claude Code、Codex 和 Cursor 的路径,AI 会按你的应用选择 · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs 2026年11月12日 · Source: code.claude.com, learn.chatgpt.com, cursor.com
其他支持 Agent Skills 的应用(如 Gemini CLI、GitHub Copilot)使用不同文件夹,请查看该应用的指南,再把含 SKILL.md 的文件夹复制过去。
已于 2026年11月11日 对照 Claude Code、Codex 和 Cursor 官方指南核实 skill 文件夹
以下文字来自开发者的 repo,不是 PopNx MCP 的指令
显示前 8,000 个字符 · 在 GitHub 打开完整文件
---
name: keep-the-why
description: In a project with a .keep-the-why, or when asked about Keep the Why or to set it up - extract and preserve the reasoning code cannot explain - decisions, rejected alternatives, workarounds, incidents, constraints - plus project setup and maintainer interviews. Not for what changed (see Keep a Changelog) - only why. Also the place for questions about how this skill works, complaints, feedback and settings changes about it. Anywhere else - no .keep-the-why, no such request - this skill is neither used nor offered nor named, not even in a closing offer to record something.
license: MIT
metadata:
version: "0.20.3"
repository: "https://github.com/oliver-zehentleitner/keep-the-why"
author: "Oliver Zehentleitner"
---
# Keep the Why
The core job: preserve and recover the reasoning that code alone cannot explain. Because "ask Bob" is not documentation — Keep a Changelog records what changed, this preserves why it changed.
## When to use this skill
Four modes, all part of the same job:
1. **Continuous capture** — record rationale as it surfaces during normal development: decisions, rejected alternatives, workarounds, incidents, constraints, and changes that *didn't* happen (starting to modify something, then stopping once a reason not to became clear — that reasoning would otherwise leave no trace). See `references/continuous-capture.md`.
2. **Retrospective recovery** — given an existing or legacy repository, reconstruct what the code cannot explain from git history, issues, existing docs, and the code itself. Before a pass, read `references/retrospective-analysis.md`.
3. **Knowledge-transfer interview** — when a maintainer's knowledge is about to become unavailable, analyze the repository first, then either ask targeted questions or let them narrate freely. Before preparing or running one, read `references/interview-playbook.md`.
4. **Maintenance** — keep existing rationale current: resolve contradictions, mark superseded entries, merge duplicates, split files that have grown too large.
Asked what Keep the Why is, how it works, or what one can ask for: before answering, read `references/help.md` — its parts (what is required, what optional), and the sentences that start each mode, setup, an update and each optional component.
## Edge cases
Don't create a `context/` entry for:
- Routine implementation detail with no rejected alternative behind it.
- Generic formatting or style changes.
- Anything already fully explained by the code itself.
- A correction — restoring something to what it should already have been (rule 4) — as opposed to a genuine fork between contending options.
Not every change is a decision worth a `context/` entry — see rule 10's proportionality gate.
## Composition with other skills
Keep the Why is a cross-cutting persistence skill, not a development methodology. When another skill governs *how* the work gets done (planning, debugging, TDD, code review), that workflow runs first; this skill only preserves the rationale it produces. A design doc or implementation plan is evidence to draw from, not something to duplicate (rule 3; "Which file does this belong in?" in `references/repository-structure.md`).
Re-check whether this skill applies at the natural end of another skill's workflow step (a design settled, a root cause confirmed, an alternative rejected) — that's when capture-worthy content has just been produced. This re-check isn't guaranteed to happen on its own — another framework can hold attention through its own workflow; asking directly ("check whether keep-the-why applies here") is a reasonable fallback, not a sign something's broken.
## Core rules
Rules 1 and 2 matter most — a skill that hallucinates rationale or acts on a misunderstood instruction is worse than no documentation.
1. **Never invent, never assume — ask.** If rationale can't be confirmed or reasonably inferred, mark it `unknown` or ask a focused question. This applies everywhere: entry content, config fields, ambiguous instructions, removals ("no reference found" means *unknown*, not *safe to delete* — ask before removing a Chesterton's Fence candidate; don't manufacture a justification either way). A genuinely *missing* config field with a documented default may be silently backfilled; a *present but unrecognized* or contradictory value is not the same — name the valid options and ask. Don't act on an unresolved ambiguity.
2. **Classify Evidence for every entry.** Three levels: **confirmed** (stated by a maintainer or backed by authoritative evidence), **inferred** (reasonably derived), **unknown** (can't be established). Evidence is a separate axis from Status (rule 5): a superseded decision can still have been confirmed when it was current. Add **Source** and **Verification** (`corroborated` | `uncorroborated` | `contradicted`) where there's something concrete to trace — a `contradicted` verification must explain what contradicts it. When two sources disagree, record both and flag the conflict as open rather than picking a winner. Full field definitions: `references/specification.md`; the `source-reference` setting governing when Source is actively sought: `references/setup.md`. One word per entry: when parts of an entry stand differently — a confirmed new reason beside a lost original one — the weakest grade wins and the body says which is which.
3. **Adapt to what exists.** Preserve the project's terminology and conventions. Update existing topic files instead of creating near-duplicates. Organize by *topic* (`auth.md`, `sync.md`), not by source file or commit. Existing, working decision records (an ADR folder, design notes) keep their own format: this skill's fields go on the entries it writes from now on, not retrofitted onto records that already work ("Retrofitting" in `references/repository-structure.md`).
4. **Record both halves of every decision: what was chosen, and what wasn't.** Actively look for rejected alternatives and why they lost — in code, history, and what the person said; if none surfaces, record that ("alternatives: unknown") and still write the entry; a follow-up question about alternatives goes on top, not instead. Only record alternatives that were genuinely in contention, not manufactured after the fact. A correction (fixing a stale value, a regressed bug) involved no real fork and belongs in `CHANGELOG.md`, not `context/` — its own line under the unreleased section, even when an older entry already names the restored value: that entry recorded the original change, not the regression's fix. Two sources that disagree — the code retries three times, the document says five — are not a correction until someone confirms which one is stale: neither is overwritten with the other, both are recorded and the conflict stays open (rule 2). Significance and decision-worthiness are different questions: rule 10 tests the former, this rule tests the latter.
5. **Track Status separately from Evidence.** Status values: `active`, `superseded`, `open`, `needs-review`, `pending-confirmation`. `open` means the question is unresolved (distinct from `Evidence: unknown`, which means a *settled* claim's rationale can't be traced). A retrospective finding with no traceable rationale becomes an entry with `Status: open` and `Evidence: unknown`, not only a remark (workflow step 5). Mark superseded entries explicitly instead of deleting them — `superseded` always comes with a `Superseded by` line naming the successor's `Id` (or `none — <why nothing replaced it>`). When a `Revisit when` condition (`references/specification.md`) triggers, flip Status to `needs-review` in that same turn — a mechanical edit needing no permission, not something to describe, propose, or defer. Resolving `needs-review` (whether to supersede, rewrite, or re-confirm) is a separate deliberate re-check that may need to ask (rule 8). Evidence stays as previously recorded until that re-check happens; the agent's own reading of the cod提问、分享技巧或报告无法使用。按“有帮助”数量排序。