alchaincyf avatar

Huashu Article Edit

This tackles a real problem: losing editing work when Claude's context window fills up or conversations get cut off. It enforces a structured workflow where Claude reads the full article, lists all planned changes upfront for your approval, then makes edits in small batches with incremental saves after every few modifications. You get progress reports showing what's done and what's pending. The goal is to prevent the frustration of requesting five changes, having Claude make three, then losing everything when the session times out. It's designed for multi-step article revisions where you need clear change tracking and want to avoid redoing work.

skills.sh installs
698
GitHub stars
2.2K
last updated
Aug 21, 2026

Install

$ npx -y skills add alchaincyf/huashu-skills --skill huashu-article-edit --agent claude-code

Installs into .claude/skills of the current project.

Files

文章编辑 Skill

标准化的文章编辑流程,解决会话截断导致编辑工作丢失的问题。

何时使用

  • 用户要求编辑、修改、优化已有文章
  • 需要对文章进行多处修改
  • 内容删减、语气调整、结构重组等编辑工作

执行流程

Step 1: 完整阅读目标文章

  • 用 Read 工具完整阅读文章
  • 快速理解文章主题、结构、当前状态

Step 2: 列出所有修改项

  • 根据用户需求,列出所有需要修改的项目
  • 每项标明:位置(哪个段落)、修改类型(删除/重写/调整)、具体内容
  • 等待用户确认范围后再动手

Step 3: 增量编辑 + 实时保存

  • 每完成一组相关修改就保存文件
  • 每完成3-5项修改,向用户汇报进度:
    进度:已完成 X/Y 项
    ✅ 已完成:[列表]
    ⏳ 待完成:[列表]
    

Step 4: 完成后总结

  • 列出所有变更的摘要
  • 说明每处修改的理由
  • 如有引用外部信息,附上来源

关键原则

  • 先确认再动手:不假设修改范围
  • 边改边存:每批修改后立即保存,防截断丢失
  • 变更透明:用户清楚知道改了什么、为什么改
  • 保持风格:修改后仍需符合花生的写作风格(参见 SHARED-RULES.md)

与审校流程的关系

  • 编辑完成后,如用户需要可触发三遍审校(/AI味审校)
  • 编辑 Skill 聚焦「按需求改」,审校 Skill 聚焦「降AI味」

最后更新: 2026-02-06


花叔出品 | AI Native Coder · 独立开发者 公众号「花叔」| 30万+粉丝 | AI工具与效率提升 代表作:小猫补光灯(AppStore付费榜Top1)·《一本书玩转DeepSeek》

Sponsors

Details

Repository
github.com/alchaincyf/huashu-skills
First seen
Jun 3, 2026

More from alchaincyf/huashu-skills

All 21

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs