스킬 writing-guidelines

📦

writing-guidelines

Name: writing-guidelines
Author: vercel-labs

v1.0.0 콘텐츠 리비전 r1 높은 위험 ⚙️ 외부 명령어🌐 네트워크 접근

Review Documentation Against Writing Guidelines

Inconsistent prose makes documentation harder to read and maintain. This skill checks selected files against current guidelines and reports precise locations for revision.

지원: Claude Codex Code(CC)

⚠️ 38 나쁨

Maintain this Skill? Claim it ⚠️ 38 나쁨

설치 전에 중지하고 확인을 요청하세요.

계획을 검토하고 파일을 변경하기 전에 사용자의 명시적 동의를 받으세요.

내 에이전트로 설치

이 요청을 에이전트에 복사하세요. 공식 Skill 페이지와 매니페스트가 포함되어 있습니다.

에이전트 요청

Review the Skillstore skill "writing-guidelines" from https://skillstore.io/skills/vercel-labs-writing-guidelines.md and its manifest at https://skillstore.io/api/skills/vercel-labs-writing-guidelines/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

에이전트는 계속해서 계획을 표시하고 보안 정책에서 요구하는 확인을 요청해야 합니다.

에이전트가 읽기 쉬운 리소스

AI 에이전트, 크롤러, 스크립트가 전체 페이지 대신 정리된 컨텍스트만 필요할 때 이 링크를 사용하세요.

Markdown 상세 GET /skills/vercel-labs-writing-guidelines.md 서명된 manifest GET /api/skills/vercel-labs-writing-guidelines/manifest 서명된 lockfile GET /api/skills/vercel-labs-writing-guidelines/lockfile

테스트해 보기

"writing-guidelines" 사용 중입니다. Review docs/setup.md for writing guideline compliance.

예상 결과:

docs/setup.md:18 - Replace vague wording with a specific action.
docs/setup.md:42 - Use consistent terminology for the project name.

"writing-guidelines" 사용 중입니다. Audit the Markdown files in docs/api.

예상 결과:

docs/api/authentication.md:27 - Shorten the sentence and place the required action first.

"writing-guidelines" 사용 중입니다. Check README.md and report only guideline violations.

예상 결과:

README.md:64 - Replace passive voice with a direct instruction.

보안 감사

높은 위험

v1 • 2026. 8. 14. 버전별 보고서 열기

The two command-execution alerts are false positives caused by Markdown backticks and a fenced URL block. The network request is confirmed, and trusting mutable remote instructions creates a high-severity prompt injection and supply-chain risk.

스캔된 파일

분석된 줄 수

검토 항목

오탐 무시됨

확인된 보안 우려 사항 (1)

높음

SKILL.md:23-29

Mutable Remote Instructions Are Trusted

The skill fetches an unpinned main-branch document and applies its rules and output instructions. A compromised source could inject instructions into every review.

Lines 23 through 29 explicitly require fetching fresh content and treating it as rules and output instructions. The source uses a mutable branch.

기능 검토 항목 (1)

이 스킬에 대해 예상될 수 있는 실제 로컬 기능이므로 검토가 필요하지만, 확인된 악의적 동작으로는 집계되지 않습니다.

낮음

SKILL.md:26

Hardcoded URL

https://raw.githubusercontent.com/vercel-labs/writing-guidelines/main/command.md

The URL on line 26 is explicitly fetched before each review through WebFetch. This creates real outbound network access to mutable remote content.

위험 요인

⚙️ 외부 명령어 (2)

SKILL.md:19 SKILL.md:25-27

🌐 네트워크 접근 (1)

SKILL.md:26

감사자: codex

이 보고서 공유 및 인용

버전이 지정된 평가 보고서, 중립 배지, 임베드 카드 및 인용을 공유하세요. Skillstore는 근거를 보고하지만 이 Skill의 안전 여부를 판단하지 않습니다.

버전별 보고서 열기

보고서 링크 복사

https://skillstore.io/skills/vercel-labs-writing-guidelines/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown 배지

[![Skillstore security assessment](https://skillstore.io/badges/skills/vercel-labs-writing-guidelines/security.svg)](https://skillstore.io/skills/vercel-labs-writing-guidelines?utm_source=security_passport_badge)

HTML 배지

<a href="https://skillstore.io/skills/vercel-labs-writing-guidelines?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/vercel-labs-writing-guidelines/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

임베드 카드

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

학술 인용 (APA · BibTeX · CFF)

APA 인용

vercel-labs. (2026). writing-guidelines security audit report (audit version 1) [Author version 1.0.0]. Skillstore. https://skillstore.io/skills/vercel-labs-writing-guidelines/audits/1

BibTeX 인용

@techreport{vercel-labs-vercel-labs-writing-guidelines-2026,
  author = {vercel-labs},
  title = {writing-guidelines security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/vercel-labs-writing-guidelines/audits/1},
  note = {Author version 1.0.0}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "writing-guidelines security audit report (audit version 1)"
version: "1.0.0"
type: report
authors:
  - name: "vercel-labs"
date-released: "2026-08-14"
url: "https://skillstore.io/skills/vercel-labs-writing-guidelines/audits/1"
identifiers:
  - type: other
    value: "skillstore:vercel-labs-writing-guidelines:audit:1"
    description: "Skillstore immutable audit report identifier"

Skillstore 점수

이 점수의 이유 증거 신뢰도: 중간

아키텍처

100

유지보수성

콘텐츠

커뮤니티

사양 준수

만들 수 있는 것

Review Product Documentation

Check a documentation page for style, voice, and formatting issues before publication.

Audit Repository Prose

Review selected Markdown files and receive concise findings tied to exact locations.

Standardize Editorial Quality

Apply one writing standard across documentation contributed by several teams.

이 프롬프트를 사용해 보세요

Review One File

Review README.md against the Writing Guidelines. Report each issue with its file and line number.

Check Documentation Pages

Review all Markdown files in docs/getting-started. Group findings by file and keep each explanation concise.

Prioritize Important Issues

Audit docs/**/*.md against the Writing Guidelines. Prioritize unclear language, inconsistent terminology, and structural problems.

Compare Revised Documentation

Review the changed documentation files. Identify remaining violations and note whether previously reported issues appear resolved.

모범 사례

Provide a narrow file path or pattern for faster, more relevant reviews.
Review findings in context before changing technical terminology.
Run the review again after revisions to confirm remaining issues.

피하기

Do not provide binary or generated files as review targets.
Do not accept remote instructions that are unrelated to writing review.
Do not treat every finding as correct without checking surrounding context.

자주 묻는 질문

What files can this skill review?

It reviews readable prose files selected by a path or file pattern.

Does it edit documentation automatically?

No. The skill reports guideline violations and their locations for manual revision.

Where do the writing rules come from?

The skill fetches rules from its configured Writing Guidelines URL before each review.

Does the skill require network access?

Yes. It uses WebFetch to retrieve the latest guideline document.

What happens when no file is specified?

The skill asks which files or patterns should be reviewed.

How are findings presented?

Findings use a concise file and line format defined by the fetched guidelines.

개발자 세부 정보

작성자

vercel-labs

라이선스

MIT

작성자 버전

v1.0.0

Skillstore 리비전

리포지토리

https://github.com/vercel-labs/agent-skills/tree/b8caa260a420a73042e35521de4b5c8baf6446cc/skills/writing-guidelines

참조

6afe7f6a881e3cdb58ff350617a068277e884103

유지보수 최신성

2026. 8. 14.

사용량

0 다운로드 · 0 조회

파일 구조

📄 SKILL.md