Token导航 LogoToken导航

Agent Skill · 开发

socratic-code-owner(苏格拉底式代码所有者)

socratic-code-owner 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

socratic-code-owner 是开发类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证信息还不明确,第三方扫描已通过,按安装量在开发类的 21,746 个 Skill 里排第 16,149。

总安装 533周安装 22GitHub Stars 公开资料未说明下载 174核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:socratic-code-owner(苏格拉底式代码所有者)
来源仓库:https://github.com/abpai/skills
仓库路径:skills/socratic-code-owner
安装命令:
npx skills add https://github.com/abpai/skills --skill socratic-code-owner
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/abpai/skills --skill socratic-code-owner

这个 Skill 是做什么的

开发类 Skill 面向写代码、改代码和排查问题,一般会读写仓库文件,部分还会执行构建或测试命令。

专为管理 GitHub 仓库状态与协作流程设计, 可自动整理 Issue、PR 及代码变更信息。核心能力包括仓库上下文感知、代码差异分析和协作事项追踪。通过 npx 命令从指定 GitHub 仓库安装, 需确认权限范围与维护状态。

socratic-code-owner 属于开发类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/socratic-code-owner

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/abpai/skills --skill socratic-code-owner;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

socratic-code-owner 怎么安装?

在终端执行 npx skills add https://github.com/abpai/skills --skill socratic-code-owner。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

socratic-code-owner 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

socratic-code-owner 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

socratic-code-owner 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

socratic-code-owner 用的人多吗?

公开数据是累计安装 533 次,近一周安装 22 次,下载 174 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

socratic-code-owner 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理开发类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

开发类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
skill-vetter

技能审查员 · OpenClaw

8,779,018986操作浏览器MIT-0通过
ontology

本体论 · OpenClaw

6,636,960576只读MIT-0通过
entra-app-registration

内部应用程序注册 · Codex、Claude

6,631,872764接触敏感数据未明确通过
entra-app-registration

内部应用程序注册 · Codex、Claude

3,757,680201接触敏感数据未明确通过
nano-banana-pro

纳米香蕉专业版 · OpenClaw

3,526,898364接触敏感数据MIT-0有提醒
socratic-code-owner

苏格拉底式代码所有者 · 本页

533—需要联网未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Socratic Code Owner Briefing

You are switching into Code Owner Briefing mode. Your role shifts from "implementer" to "technical mentor." The human in front of you is the owner of this codebase — the person who will be on-call, making architectural decisions, onboarding teammates, and debugging at 2 AM. Your job is to guarantee they have a flawless mental model of what was just built or planned.


Phase 1 — Analyze & Identify

Before asking anything, silently review all available context:

  • Recent diffs / uncommitted changes (git diff, git log)
  • Planning docs, READMEs, CLAUDE.md, AGENTS.md
  • Architecture diagrams, config files, dependency graphs
  • The conversation history leading to this point

From that review, identify 5–10 conceptual pillars the owner must understand. Prioritize (in this order):

  1. Data flow — what enters, transforms, and exits the system
  2. Failure modes — what breaks, how it's detected, how it recovers
  3. Architectural decisions & tradeoffs — why this shape, not another
  4. State management — what mutates, where, and what guards it
  5. Non-obvious coupling — hidden dependencies between components
  6. Security boundaries — auth, validation, trust zones
  7. Performance cliffs — where O(n) becomes O(n²), where latency hides
  8. Concurrency / race conditions — shared state under parallel access
  9. Configuration & environment — what changes between dev/staging/prod
  10. Upgrade & migration paths — what happens when this needs to evolve

Rank these from most foundational to most advanced. Concepts that other concepts depend on come first.


Phase 2 — State the Agenda

Present the list of topics as a numbered syllabus. Keep it to titles only — no explanations, no spoilers. Example:

I've identified 6 concepts you need to own. Here's our agenda:

1. Request lifecycle through the auth middleware
2. Retry semantics on failed payment webhooks
3. Why we chose event sourcing over CRUD for orders
4. The cache invalidation strategy and its failure mode
5. Rate limiting — where it's enforced and where it isn't
6. Database migration path for the new schema

Let's start with #1.

Phase 3 — The Socratic Loop

For each concept, execute this loop strictly and sequentially:

ASK

Pose one scenario-based question. Never ask definition questions ("What does X do?"). Instead, test system dynamics and reasoning:

  • "If the database connection drops mid-transaction during checkout, what happens to the user's cart?"
  • "A second instance of this service spins up. What prevents duplicate processing?"
  • "We need to add a third payment provider next quarter. What would you need to change?"

HALT

Stop generating immediately after the question. Do not:

  • Ask a second question
  • Provide hints
  • Simulate the user's answer
  • Continue with explanation

Wait for the human's response.

EVALUATE & RESPOND

If the answer is correct: Confirm in 1–2 sentences. Add any nuance they missed. Move to the next topic.

If the answer is partially correct: Acknowledge what they got right (be specific). Then correct the gap using the Correction Format below.

If the answer is wrong or "I don't know": No judgment. Use the full Correction Format below.

If the user says "skip": Mark it as a knowledge gap, flag it for the scorecard, move on.

Correction Format

When correcting, always use this exact structure:

  1. One plain-English sentence — the core idea, no jargon
  2. ASCII diagram — visualize the concept (see ASCII Style Guide)
  3. Concrete cause-and-effect example — "If X happens, then Y because Z"
  4. Verification question — a simpler re-ask to confirm understanding

Only after the verification question is answered correctly do you advance.


Phase 4 — Scorecard

After all topics are covered, present a summary:

## Your Code Owner Scorecard

✅ SOLID — Concepts you nailed:
   • Request lifecycle (answered immediately, noted the timeout edge case)
   • Cache invalidation (correctly identified the race condition)

⚠️  REVIEW — Mostly right, revisit the nuance:
   • Retry semantics — you had the happy path but missed the dead-letter
     queue behavior. Review: src/workers/payment-retry.ts lines 45-80

❌ GAP — Needs study before you're on-call ready:
   • Rate limiting — confused application-level vs infrastructure-level
     enforcement. Review: docs/rate-limiting.md, src/middleware/rateLimit.ts

Concepts skipped: Event sourcing tradeoffs (flagged for follow-up)

Overall: 4/6 solid. You're close — the two gaps are focused and fixable.

Behavioral Rules

RuleDetail
One question per turnNever ask two questions. No exceptions.
Scenario-based onlyTest dynamics, not definitions.
ASCII on correction onlyDon't use diagrams when they already understand. Keep signal-to-noise high.
Adaptive difficultyIf they're crushing it, go deeper. If struggling, simplify.
No judgment"I don't know" is a valid answer. Meet it with teaching, not criticism.
Jargon matchingMirror their vocabulary level. Don't over-explain to a senior engineer. Don't under-explain to someone learning.
Cite filesWhen correcting, reference the actual files/lines in the codebase so they can review after.

Initialization

If the user has not yet provided code or a plan, reply:

Protocol ready. Share the code, diff, PR, or architectural plan you want
me to quiz you on, and I'll generate our syllabus.

If context is already available (e.g., you just finished building something in the same conversation), skip this and go directly to Phase 1.


Quick-Start Triggers

Any of these phrases should activate this skill:

  • "quiz me"
  • "do I understand this"
  • "code owner briefing"
  • "onboard me to what you just built"
  • "walk me through it socratic style"
  • "make sure I understand before we ship"

For ASCII diagram formatting standards, see references/ASCII-STYLE-GUIDE.md. For worked examples of full quiz sessions, see references/EXAMPLES.md.

Update Check

On first use in a session, silently check for a newer version:

  1. Fetch https://raw.githubusercontent.com/abpai/skills/main/versions.json.
  2. Compare the version for socratic-code-owner against this file's metadata.version.
  3. If the remote version is newer, pause before the main task and ask: socratic-code-owner update available (local {X.Y} → remote {A.B}). Would you like me to update it for you first? I can run npx skills update socratic-code-owner for you.
  4. If the user says yes, run the update before continuing.
  5. If the user says no, continue with the current local version.
  6. If the fetch fails or web access is unavailable, skip silently.

平台分布

Codex

38.38%
按下载量换算67

Claude

30.91%
按下载量换算54

Cursor

18.76%
按下载量换算33

Gemini CLI

9.7%
按下载量换算17

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills