Atlas / Skills / huangjia2019 / Doc Writing

Doc WritingSAFE

skills/huangjia2019/doc-writing

This repository demonstrates how to use Claude Code to do real engineering work, not just writing code. 本项目是极客时间专栏 《Claude Code 工程化实战》 的官方配套示例仓库,目标就是: 👉 把 Claude Code 从“对话式编码工具”,变成 可设计、可复用、可治理的工程系统。

Verdict
SAFE
Grade
B
Trust score
89 /100
Version
—
Hosts
—
License
—
Stars
1,135
01

Overview

This repository demonstrates how to use Claude Code to do real engineering work, not just writing code. 本项目是极客时间专栏 《Claude Code 工程化实战》 的官方配套示例仓库,目标就是: 👉 把 Claude Code 从“对话式编码工具”,变成 可设计、可复用、可治理的工程系统。

Read from source at commit f28f37d82954OBSERVED · 2026-10-12
02

What it tells the agent

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: doc-writing
description: Generate API documentation from a route manifest. Use when you have a list of discovered routes and need to produce markdown documentation.
allowed-tools: [Read, Write, Glob]
---

# Doc Writing Skill

Generate structured API documentation from a route manifest.

## Input

You will receive a route manifest (JSON array) from the previous pipeline stage.
Each entry contains: method, path, file, line, middleware, type.

## Process

### Step 1: Read Source Code

For each route in the manifest, read the source file to understand:
- Request parameters (path, query, body)
- Response format
- Error handling
- Business logic summary

### Step 2: Generate Documentation

Use the template at `templates/endpoint-doc.md` for each route group.

Group routes by their source file (e.g., all product routes together).

### Step 3: Write Files

Write one markdown file per route group to the `docs/` directory:
- `docs/products-api.md`
- `docs/categories-api.md`
- etc.

## Output

Return a manifest of generated documentation files:

```json
{
  "files_generated": ["docs/products-api.md", "docs/categories-api.md"],
  "routes_documented": 8,
  "routes_skipped": [],
  "warnings": []
}
```

This manifest will be consumed by the next pipeline stage (quality-checking).
03

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeNA
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (1)

LOWInventory / provenance · inv.no_license · CWE-1104
Why it matters. no LICENSE file and no repo licence
Fix. add a licence

Gates applied: no_behavioural_pass, no_license.

Audited 2026-10-12 · audit v0.4.1 · source sha f28f37d82954full audit observations/trust-audit/skill/huangjia2019__doc-writing.json · Report an issue / request a re-scan
04

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-12f28f37d82954SAFEB89first audit
05

Questions

What does the Doc Writing skill do?

This repository demonstrates how to use Claude Code to do real engineering work, not just writing code. 本项目是极客时间专栏 《Claude Code 工程化实战》 的官方配套示例仓库,目标就是: 👉 把 Claude Code 从“对话式编码工具”,变成 可设计、可复用、可治理的工程系统。

Is Doc Writing safe to install?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.

What can Doc Writing access on my machine?

The audit observed no filesystem, network or shell use at all in its source.

How current is this page?

The grade is for one exact copy of the source (f28f37d82954), read on 2026-10-12. The repository is watched, and a new audit runs when it changes — this is the first audit.

Advertisement