技能 explain-codebase

📦

explain-codebase

Name: explain-codebase
Author: agentkitco

v1.0 內容修訂 r1 中風險 ⚙️ 外部命令

Explain an Unfamiliar Codebase

Unfamiliar repositories make it difficult to find entry points, setup steps, and important dependencies. This skill guides a file-referenced onboarding map with one traced flow and clear open questions.

支援: Claude Codex Code(CC)

📊 70 尚可

Maintain this Skill? Claim it 📊 70 尚可

使用我的智慧代理安裝

將此請求複製給你的智慧代理，其中包含權威 Skill 頁面和清單。

智能體請求

Review the Skillstore skill "explain-codebase" from https://skillstore.io/skills/agentkitco-explain-codebase.md and its manifest at https://skillstore.io/api/skills/agentkitco-explain-codebase/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

你的智慧代理仍應顯示其計畫，並依安全政策請求必要確認。

Agent 可讀資源

當 AI Agent、爬蟲或腳本需要乾淨脈絡、而不是讀取完整頁面時，請使用這些連結。

Markdown 詳情 GET /skills/agentkitco-explain-codebase.md 已簽名 manifest GET /api/skills/agentkitco-explain-codebase/manifest 已簽名 lockfile GET /api/skills/agentkitco-explain-codebase/lockfile

測試它

正在使用「explain-codebase」。 Show the expected outline for a repository onboarding summary.

預期結果:

Purpose: project problem and intended users.
How to run: discovered commands and verification status.
Map: directories and their responsibilities.
Reading order: three inspected files with reasons.
Open questions: details not established from available evidence.

正在使用「explain-codebase」。 What should a central-flow explanation include?

預期結果:

Entry: the inspected request handler, command, or event consumer.
Processing: relevant functions in execution order, with file references.
Data boundary: storage or external service calls found in the inspected code.
Result: the response or output, with any unverified behavior identified.

安全審計

中風險

v2 • 2026/10/22 開啟版本化報告

Eight findings are false positives involving Markdown formatting, read-only history inspection, citation rules, or explicit secret protections. One finding is confirmed because the skill directs execution of unfamiliar repository tests and lint commands without requiring review or isolation. No evidence found of data exfiltration, destructive intent, or prompt injection.

已掃描檔案

分析行數

複核項目

已忽略的誤報

已確認的安全問題 (1)

中

SKILL.md:17

System reconnaissance

2. **Run it**: install, run, test commands from manifests, Makefile and CI config. Run the cheap one

The instruction runs repository-defined tests and lint commands without requiring prior review or isolation. These commands can execute arbitrary code from an unfamiliar repository.

風險因素

⚙️ 外部命令 (6)

SKILL.md:18 SKILL.md:19 SKILL.md:23 SKILL.md:27-38 SKILL.md:38-42 SKILL.md:42

偵測到的模式

System reconnaissance

審計單位: codex 檢視審計紀錄 →

分享與引用此報告

分享版本化評估報告、中性徽章、嵌入卡片與引用。Skillstore 只報告證據，不判斷該 Skill 是否安全。

開啟版本化報告

複製報告連結

https://skillstore.io/skills/agentkitco-explain-codebase/audits/2?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown 徽章

[![Skillstore security assessment](https://skillstore.io/badges/skills/agentkitco-explain-codebase/security.svg)](https://skillstore.io/skills/agentkitco-explain-codebase?utm_source=security_passport_badge)

HTML 徽章

<a href="https://skillstore.io/skills/agentkitco-explain-codebase?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/agentkitco-explain-codebase/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

嵌入卡片

<iframe src="https://skillstore.io/embed/skills/agentkitco-explain-codebase.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

學術引用 (APA · BibTeX · CFF)

APA 引用

agentkitco. (2026). explain-codebase security audit report (audit version 2) [Author version 1.0]. Skillstore. https://skillstore.io/skills/agentkitco-explain-codebase/audits/2

BibTeX 引用

@techreport{agentkitco-agentkitco-explain-codebase-2026,
  author = {agentkitco},
  title = {explain-codebase security audit report (audit version 2)},
  institution = {Skillstore},
  year = {2026},
  number = {2},
  url = {https://skillstore.io/skills/agentkitco-explain-codebase/audits/2},
  note = {Author version 1.0}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "explain-codebase security audit report (audit version 2)"
version: "1.0"
type: report
authors:
  - name: "agentkitco"
date-released: "2026-10-22"
url: "https://skillstore.io/skills/agentkitco-explain-codebase/audits/2"
identifiers:
  - type: other
    value: "skillstore:agentkitco-explain-codebase:audit:2"
    description: "Skillstore immutable audit report identifier"

Skillstore 評分

評分依據證據置信度: 中

架構

可維護性

內容

社群

規範符合度

你可以打造什麼

Orient a New Developer

Find setup steps, entry points, and three useful files to read before starting a first contribution.

Prepare a Technical Handoff

Summarize module responsibilities, external dependencies, and unresolved questions for a team taking ownership.

Plan an Integration Investigation

Trace a central request through application layers and identify configuration names and service boundaries relevant to an integration.

試試這些提示

Beginner: Get Oriented

Explain this repository in one page. Cover its purpose, directory map, entry points, and three files to read first. Cite files you inspect.

Intermediate: Understand Setup

Map setup, run, and test commands from project files. List environment variable names only. Do not execute commands; mark them unverified.

Advanced: Trace a Central Flow

Trace [request, command, or event] from entry to storage or output. List files and functions in order, cite evidence, and label inferences.

Advanced: Prepare an Ownership Map

Create an onboarding map of [repository]. Include one central flow, external services, quality signals, recent churn, and open questions. Review commands before requesting execution approval.

最佳實務

Specify the repository and one central workflow to keep the map focused.
Review repository commands and hooks before approving execution in an isolated environment.
Require file references, verification status, and explicit labels for inferred behavior.

避免

Running unfamiliar installation, test, or lint commands without review or isolation.
Including secret values when configuration variable names are sufficient.
Treating a concise onboarding map as exhaustive documentation or a completed security audit.

常見問題

What does this skill produce?

A concise onboarding map covering purpose, setup, structure, one central flow, dependencies, reading priorities, and open questions.

Which AI tools are listed as supported?

The marketplace metadata lists Claude, Codex, and Claude Code. Repository access and command permissions depend on the host environment.

Does it execute project commands?

The instructions call for running inexpensive tests and lint checks. Review commands first and isolate execution when the repository is untrusted.

How does it handle environment secrets?

It explicitly prohibits printing secret values from environment files or configuration. Reports should list variable names only.

Will it explain every file?

No. It prioritizes a two-level directory map, key entry points, and one central flow instead of an exhaustive file tour.

How does it handle missing evidence?

Claims must cite inspected files. Inferences receive labels, unexecuted commands remain unverified, and unresolved details become open questions.

開發者詳細資訊

作者

agentkitco

授權

MIT

作者版本

v1.0

Skillstore 修訂

版本提示

作者聲明的版本不符合 SemVer 規範。

儲存庫

https://github.com/agentkitco/agentkit-dev-skills/tree/a5058856442fcb89bd538b1c01f94558488bfac3/skills/explain-codebase

引用

18efac79a818d7e997295839638fdd21906cfd1c

維護新鮮度

2026/10/22

使用量

5 次下載 · 0 次瀏覽

檔案結構

📄 SKILL.md

agentkitco 的更多技能

查看全部

📦

session-handoff

Create Clear Agent Session Handoffs

Long sessions and agent switches can lose decisions, test results, and unfinished work. This skill creates a concise HANDOFF.md with verified state and actionable next steps.

文件查看

📦

security-quick-review

Review Code Changes for Security Risks

Code changes can introduce security problems that routine reviews miss. This skill guides focused AI triage with evidence, realistic severity, and concrete fixes.

安全與法遵查看

📦

review-my-diff

Review Your Diff Before Opening a Pull Request

Local changes can hide bugs, security gaps, and missing tests before human review. This skill guides an evidence-based review with prioritized findings and explicit verification results.

程式開發查看

📦

repro-first-debugging

Debug Bugs With Reproducible Evidence

Speculative fixes can hide causes and leave bugs unresolved. This skill guides assistants through reproduction, hypothesis testing, focused changes, and evidence-based verification.

程式開發查看

📦

safe-refactor

Refactor Code with Tests and Small Changes

Code cleanup can introduce behavior changes that are difficult to detect. This skill guides small refactoring steps with baseline tests, dependency checks, and repeated verification.

程式開發查看

📦

prove-it-ran

Verify Tests Ran Before Reporting Completion

Passing claims can hide skipped tests, stale results, or checks that never exercised a change. This skill guides fresh verification and evidence-based completion reports.

程式開發查看

查看全部

📦