Token导航 LogoToken导航

Agent Skill · 待分类

writing-pre-publish-checklist(编写发布前清单)

用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。它适合让 Agent 提炼结构、补齐章节、统一术语、检查链接或把零散材料整理成可读文档。使用时应保留项目已有事实、命令和路径,不要把未确认的信息写成确定结论;涉及对外文案时,还需要控制语气,避免过度营销或夸大能力。

writing-pre-publish-checklist 是待分类类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在待分类类的 11,209 个 Skill 里排第 3,788。

总安装 899周安装 36GitHub Stars 85下载 291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:writing-pre-publish-checklist(编写发布前清单)
来源仓库:https://github.com/lyndonkl/claude
仓库路径:skills/writing-pre-publish-checklist
安装命令:
npx skills add https://github.com/lyndonkl/claude --skill writing-pre-publish-checklist
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/lyndonkl/claude --skill writing-pre-publish-checklist

这个 Skill 是做什么的

这个 Skill 的分类还没最终确定,用法以来源仓库的说明为准。

用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。适合让 Agent 提炼结构、补齐章节、统一术语或检查链接。使用时需保留项目已有事实和路径,避免写成确定结论。涉及对外文案时应控制语气,防止过度营销或夸大能力。安装方式:通过 npx 从 GitHub 仓库添加技能。

来源仓库内路径:skills/writing-pre-publish-checklist

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/lyndonkl/claude --skill writing-pre-publish-ch…;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

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

writing-pre-publish-checklist 怎么安装?

在终端执行 npx skills add https://github.com/lyndonkl/claude --skill writing-pre-publish-checklist。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

writing-pre-publish-checklist 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。

writing-pre-publish-checklist 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

writing-pre-publish-checklist 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。

writing-pre-publish-checklist 用的人多吗?

公开数据是累计安装 899 次,近一周安装 36 次,下载 291 次,GitHub 85 星。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。

writing-pre-publish-checklist 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。
  • 标注为只读权限,试用阶段不容易误改本地文件。

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。
  • 需要处理待分类类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

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。

待分类类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
infsh-cli

infsh CLI · Codex、Claude

4,374,576382权限未标注未明确未收录
ai-video-generation

AI 视频生成 · Codex、Claude

4,313,376382调用外部服务未明确有提醒
lark-openapi-explorer

云雀 OpenAPI 浏览器 · Codex、Claude

2,064,1209,011需要联网未明确有提醒
lark-workflow-standup-report

Lark 工作流程站立报告 · Codex、Claude

2,041,6328,978需要联网未明确通过
use-my-browser

使用我的浏览器 · Codex、Claude

1,848,49140操作浏览器未明确未通过
writing-pre-publish-checklist

编写发布前清单 · 本页

89985只读未明确通过

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

Writing Pre-Publishing Checklist

Table of Contents

Related skills: Use writing-structure-planner for planning structure, writing-revision for deep prose revision, writing-stickiness for memorable messaging.

Core Principles

  1. Systematic, not subjective: Follow the checklist completely, don't skip sections
  2. Fresh eyes perspective: Read as if seeing the piece for the first time
  3. Binary decisions: Each check item is pass/fail, not "sort of"
  4. Flag, don't fix: Identify issues and present to user rather than silently fixing
  5. Final gate, not revision: This catches remaining issues, not does deep rewriting

Workflow

Copy this checklist and track your progress:

Pre-Publishing Checklist:
- [ ] Section 1: Content check
- [ ] Section 2: Structure check
- [ ] Section 3: Clarity check
- [ ] Section 4: Style check
- [ ] Section 5: Polish check
- [ ] Section 6: Final tests

Before starting: This is a systematic pass through the complete piece. Read the entire document first to understand context, then work through each section.

Section 1: Content Check

Step 1.1: Read the entire piece. Identify the core message. Verify core message is crystal clear - could a reader state it back in one sentence?

Step 1.2: Check all facts for accuracy. Flag any claims that need verification. Note any statistics, dates, names, or specific details that should be double-checked with the user.

Step 1.3: Evaluate examples and evidence. Are examples relevant and appropriate for the audience? Are arguments sound and complete? Is there any missing information that would leave readers with unanswered questions?

Present Content Check results:

Content Check:
- [ ] Core message crystal clear
- [ ] All facts checked for accuracy
- [ ] Examples relevant and appropriate
- [ ] Arguments sound and complete
- [ ] No missing information
Issues found: [list any issues]

Section 2: Structure Check

Step 2.1: Evaluate the opening. Does it hook readers? Would someone continue reading after the first paragraph?

Step 2.2: Check flow and transitions. Is the logical flow smooth throughout? Do transitions between sections work? Are there any jarring jumps?

Step 2.3: Examine the middle and ending. Does the middle section have gold-coin moments (rewards for the reader)? Does the conclusion satisfy - does it deliver on the promise of the opening?

Present Structure Check results:

Structure Check:
- [ ] Opening hooks readers
- [ ] Flow is logical and smooth
- [ ] Transitions work smoothly
- [ ] Middle section has gold coins
- [ ] Conclusion satisfies
Issues found: [list any issues]

Section 3: Clarity Check

Step 3.1: Scan for jargon. Is all jargon either removed or explained? Is it appropriate for the target audience?

Step 3.2: Check for ambiguity. Are there ambiguous pronouns? Garden-path sentences that require re-reading? Any sentences where meaning is unclear?

Step 3.3: Verify audience fit. Is technical accuracy maintained? Is the level of detail appropriate for the target audience?

Present Clarity Check results:

Clarity Check:
- [ ] No jargon (or all jargon explained)
- [ ] No ambiguous pronouns
- [ ] No garden-path sentences
- [ ] Technical accuracy maintained
- [ ] Appropriate for target audience
Issues found: [list any issues]

Section 4: Style Check

Step 4.1: Verify tone consistency. Is the tone consistent throughout? Does it shift inappropriately between sections?

Step 4.2: Check voice and sentence variety. Is the voice appropriate for the audience and purpose? Is there good sentence variety (mix of short, medium, long)? Rate sentence variety on a 1-10 scale (target 7+).

Step 4.3: Scan for remaining clutter. Is there any clutter that should have been caught in revision? Does active voice predominate?

Present Style Check results:

Style Check:
- [ ] Tone is consistent
- [ ] Voice is appropriate
- [ ] Sentence variety is good (score: X/10)
- [ ] No clutter remains
- [ ] Active voice predominates
Issues found: [list any issues]

Section 5: Polish Check

Step 5.1: Check mechanics. Scan for spelling errors, grammar issues, and punctuation problems.

Step 5.2: Verify formatting. Is formatting consistent throughout (headings, lists, emphasis, spacing)? Do links work (if applicable)?

Present Polish Check results:

Polish Check:
- [ ] Spelling checked
- [ ] Grammar correct
- [ ] Punctuation proper
- [ ] Formatting consistent
- [ ] Links work (if applicable)
Issues found: [list any issues]

Section 6: Final Tests

Step 6.1: Read-aloud test. Read the piece aloud (or simulate reading aloud). Flag any sections that sound awkward, trip over themselves, or lose momentum.

Step 6.2: Intent test. Does the piece achieve its stated intent? Does it satisfy the target audience's needs?

Step 6.3: Pride test. Present the overall assessment - is this piece ready for its intended audience? Note any remaining concerns.

Present Final Tests results:

Final Tests:
- [ ] Read aloud - sounds good
- [ ] Achieves stated intent
- [ ] Satisfies target audience needs
- [ ] Ready for publication
Overall assessment: [PASS / PASS WITH NOTES / NEEDS REVISION]

Final Summary

Present the complete checklist results in a single summary:

Pre-Publishing Checklist Summary:
================================
Content:   [PASS/FAIL] - [brief note]
Structure: [PASS/FAIL] - [brief note]
Clarity:   [PASS/FAIL] - [brief note]
Style:     [PASS/FAIL] - [brief note]
Polish:    [PASS/FAIL] - [brief note]
Final:     [PASS/FAIL] - [brief note]

Overall:   [READY TO PUBLISH / NEEDS ATTENTION]

Issues requiring action:
1. [issue]
2. [issue]

Validate using resources/evaluators/rubric_pre_publish.json. Minimum standard: Average score >= 3.5.

Check Details

SectionFocusKey Questions
ContentAccuracy & completenessIs the core message clear? Facts correct?
StructureOrganization & flowDoes it hook, flow, and satisfy?
ClarityReadabilityCan audience understand without re-reading?
StyleConsistency & voiceIs tone consistent? Voice appropriate?
PolishMechanicsSpelling, grammar, punctuation, formatting?
FinalOverall qualityRead-aloud test? Achieves intent?

Guardrails

Requirements:

  1. Complete all 6 sections: Run every section even if the writing seems good
  2. Binary pass/fail: Each checklist item gets a clear pass or fail, not "maybe"
  3. Flag to user: Present issues for the user to address rather than silently fixing
  4. Context-aware: Adjust standards to context (blog post vs. academic paper vs. email)
  5. Honest assessment: Give genuine feedback even if it means more work is needed

Common pitfalls:

  • Rubber-stamping everything as "pass" without careful review
  • Skipping the read-aloud test (it catches issues nothing else does)
  • Not adjusting standards for the specific publication context
  • Trying to do deep revision instead of flagging issues
  • Missing formatting inconsistencies in longer pieces

Quick Reference

Key resources:

Inputs required:

  • Finished or near-finished piece of writing
  • Target audience and publication context
  • Stated intent or core message

Outputs produced:

  • Complete 6-section checklist with pass/fail for each item
  • List of issues requiring attention
  • Overall publication readiness assessment

平台分布

Codex

36.19%
按下载量换算105

Claude

28.38%
按下载量换算83

Cursor

17.41%
按下载量换算51

Gemini CLI

10.3%
按下载量换算30

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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