Writing

What it does

When your agent uses it

• Tasks that involve PRD writing
• Tasks that involve Deep research

Example prompts

• “内容→组件→组合”
• “，只要意图是”
• “，都应触发此技能。 本 skill 只负责”
• “/writing”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1决定基调：浅色阅读型（report-template.html）还是深色路演型（templates/report-pitch.html）——也可以混合
2. 2Read 对应的组件示例 HTML 文件（看可用类名）
3. 3按 components.md 挑组件、按内容组装
4. 4调 diagram skill 生成图表（评审场景图带标题，文档配图不带——见 diagram skill）
5. 5Write 输出
6. 6open 命令打开供 review

What it can do on your machine

Read from SKILL.md and the folder at commit 2d4fa49. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • git

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Writing loads about 1.6k tokens when it runs, and up to ~15k if it reads all its reference files. Until then it costs about 113 tokens; SKILL.md has 449 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~113

When it runs · the whole SKILL.md, loaded when a task matches

~1.6k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~15k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from 312362115/claude at commit 2d4fa49, republished under its MIT licence (© 312362115). 449 words, ~1,601 tokens.

name

writing

description

通用写作技能：以"内容→组件→组合"的方式产出技术文档、产品文档、汇报材料。 覆盖 spec / plan / PRD / 用户手册 / 项目汇报 / 方案路演 / 调研报告 等所有结构化文档场景。 核心理念：组件驱动，不预设模板。先看内容形态，再挑能装这种形态的组件， 组合自然成文——不强制章节结构、不预设"必备模块"。 组件库（HTML / Markdown / 图示）见 references/components.md， 常见组合范式（spec / plan / PRD 等）见 references/templates/——但模板是参考不是规定。 触发词：写文档、写方案、写计划、写 PRD、写汇报、项目总结、写指南、帮我写、文档、方案设计。 即使用户没有明确说"写"，只要意图是"产出一份结构化的文档/报告/材料"，都应触发此技能。 本 skill 只负责"写"，不负责"调研"（调研由 deep-research 承担）和"调度"（流程由 task-start 承担）。

version

2.0.0

last_updated

2026-05-07

repository

https://github.com/312362115/claude

传统模板派：先选模板（spec / PRD / 汇报）→ 模板说必备 X 章节 → 内容硬塞进去
本 skill：先看内容形态 → 挑能装这种形态的组件 → 自然组合

我的理解：
- 内容核心：xxx
- 读者：xxx
- 形态识别：含决策（3-4 项）/ 架构图（2 张）/ 风险点（5 个）
- 推荐格式：HTML（路演风格 + 数据指标混合）
- 存放：docs/reviews/

确认开始？

deep-research → 调研结论 → writing（把调研写成文档）
tech-evaluation → 选型结论 → writing（把选型写成方案）
task-start → 对焦结论 → writing（写 spec / plan）
task-finish → 复盘结论 → writing（写 decisions / 汇报）

writing 调用：
  ← diagram skill（生成图表嵌入文档）
  ← preview-md skill（Markdown 文档预览）

© 312362115, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 10 other files (references) in skills/writing of 312362115/claude.

• SKILL.md
• references/components.md
• references/report-template.html
• references/templates/api-doc.md
• references/templates/dev-guide.md
• references/templates/operation-plan.md
• references/templates/plan.md
• references/templates/prd.md
• references/templates/report-pitch.html
• references/templates/spec.md
• references/templates/user-guide.md

Open the folder on GitHubat commit 2d4fa49