skills/progressive-disclosure-docs/SKILL.md
Design, create, split, or revise Markdown/project documentation using progressive disclosure so agents and humans can find the right level of detail without context bloat. Use when writing docs, README files, runbooks, architecture notes, deployment guides, troubleshooting docs, rules, skills, or when deciding whether content belongs in an existing document or should become a new document.
npx skillsauth add nangongwentian-fe/agent-skills progressive-disclosure-docsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use this skill to make documentation easy for both humans and agents to discover, load, and act on. Preserve the target document's language and style unless the user asks to change it.
Structure documentation like Agent Skills:
| Layer | Purpose | Document Equivalent | | ---- | ------- | ------------------- | | Discovery | Decide whether to read | Filename, title, summary, table of contents | | Activation | Complete the common task | Scope, decision rules, shortest working path | | Execution | Handle details only when needed | Commands, config blocks, examples, troubleshooting | | References | Keep depth available without clutter | Links to topic docs, appendices, source docs |
Never expand an existing document just because it is nearby. Put content where a future reader would naturally look for it.
Inspect existing docs before editing.
Classify the new content.
Choose placement.
Write from shallow to deep.
Verify structure.
| Signal | Action | | ------ | ------ | | A section introduces a new topic | Create a new doc and link to it | | One doc serves different reader intents | Split by task or audience | | Config or logs dominate a process doc | Move details to a topic doc or appendix | | The filename no longer predicts the content | Rename or split | | The user corrects document placement | Record the rule and update the structure | | The content is a short note directly supporting the doc | Keep it in the existing doc |
Prefer this shape for topic docs:
# Clear Topic Name
One short paragraph: what this doc covers and when to use it.
## Summary
Key decisions or current facts.
## Common Path
The shortest safe workflow.
## Details
Config, commands, examples, or deeper explanation.
## Verification
How to know it worked.
## Related Docs
Links to adjacent topics.
For rule docs, use:
# Rule Name
## Core Principles
## Classification Rules
## Checklist
## Examples
## References
Do not force these templates when the repo already has a stronger local convention.
Avoid:
notes.md, misc.md, temp.md, or other vague filenames.artemis-video-gateway.md.When editing docs:
git diff --check when working in a git repo.development
网页内容获取技巧集合。当用户需要抓取网页内容、提取文章正文、获取社交媒体帖子内容、读取任意 URL 的文本或 Markdown 格式内容时使用。 无论用户是想"获取某个网页的内容"、"抓取这个链接"、"读取这篇文章"、"把这个页面转成 Markdown",还是想访问 X/Twitter、微信、知乎、Medium 等平台的内容,都应触发此 skill。 包含多种方法,覆盖不同场景:Markdown 提取、绕过付费墙、结构化数据抓取等。持续迭代更新中。
tools
更新 Claude Code CLI 到最新版本。当用户说"更新 Claude Code"、"升级 Claude Code"、"update claude code"、"claude code 太旧了"、"执行 install.sh 更新",或者想让 Claude 自我更新时,立即使用此 skill。不要等用户明确说"用 npm"——只要涉及更新 Claude Code 本身,就使用这个 skill。
tools
Post-action workflow that triggers automatically after creating a new skill or updating an existing skill. Ask the user whether to sync the skill to the jay-skills repository and publish to remote. Use whenever a SKILL.md has just been created or modified.
tools
信息可视化呈现行为准则。当模型回复中包含对比、步骤、配置、架构等结构化信息时自动激活,确保优先使用表格、代码块、列表、树形结构等可视化格式,而不是纯文字堆砌。触发词:「用表格」「画个图」「列个表」「结构化一下」「别光用文字」「可视化」「对比一下」。即使没有触发词,只要回复中包含适合可视化的结构化信息,本 skill 的规则就应生效。也适用于:「太多字了看不下去」「能不能更直观一点」「整理成表格」等场景。