Individual skill
writing-for-agents
为智能体编写文档。当你正在创建或编辑技能,或者修改 AGENTS.md / CLAUDE.md 时使用。
skills/productivity/writing-for-agents/SKILL.md
Source commit 30fc5dbf9380144598f3593e6c1e22c713a52c2a
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- Yes
- Observed behavior
- Network or broad shell
- Last checked
- Nov 10, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 538
- Repository last updated
- Nov 3, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- ai-agent Repository topic
- chinese Repository topic
- prompt-engineering Repository topic
- skills Repository topic
- translation Repository topic
- writing Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL-MECHANICS.mddoc · 3,079 bytesSKILL.mdcore · 12,001 bytesagents/openai.yamlasset · 105 bytes
Read excerpt
一份用于编写智能体所阅读的任何文档的参考:一个技能、一份 `AGENTS.md` / `CLAUDE.md`、一份通过指针触达的文档。包装方式各异,但写作规则是一致的:同样的杠杆让每份文档都变得可预测,因为智能体每次运行采取的是同一个*流程*,而不是产出同一个输出。
当你正在编写的文档是一个技能时,请阅读 [`SKILL-MECHANICS.md`](SKILL-MECHANICS.md),了解前置元数据、调用方式的选择,以及路由技能。
## 上下文指针
**上下文指针(context pointer)** 是智能体上下文中持有的一条引用,它指向一份"上下文之外"的资料,并编码了触达该资料的条件。技能的 `description` 就是一条;`AGENTS.md` 中指向某份文档的一行也是同一回事。决定智能体何时、以多高的可靠性触达这份资料的,是这条指针的*措辞*,不是它的指向。一个本应被触达的指向目标,却藏在一段措辞含糊的指针背后:这是一个方差 bug:先打磨措辞;只有当打磨失败时,才把资料直接内联进去。
一条指针承担两件事:说明这份资料是什么,以及列出应当触发触达它的**分支**(branch 是这份文档所处理的一种独立情形,所以不同次运行会走不同的路径)。每一条始终加载的指针里的每一个词,在每一次轮次中都在付代价,所以它需要比正文更严格的精简:
- **把"引导词"前移**:指针是触发工作真正发生的地方。
- **一个分支对应一个触发词。** 同义词把同一个分支换了个说法写两遍,本质上是一个分支;把它们合并,只保留真正不同的分支。
- **去掉正文已经承载的身份信息。**