Use this skill when the user wants to deep-read a specific BestBlogs resource (article / podcast / video / tweet) — fetch its metadata + markdown so a local LLM or reader can consume it, and automatically report the read behavior back to BestBlogs. Triggers include "深度阅读这篇 / 拉这篇内容的 markdown / bestblogs read / 给我看看 RAW_xxx 的正文", "deep read this BestBlogs article", "pull markdown for resource RAW_...". Invokes the `bestblogs` CLI.
80
100%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
| 原语 | CLI | 说明 |
|---|---|---|
bestblogs.resource.meta.get | 内部调用 /resources/{id}/meta | meta |
bestblogs.resource.markdown.get | 内部调用 /resources/{id}/markdown | 正文 markdown |
bestblogs.resource.read.mark | 内部调用 POST /resources/{id}/read | 回传已读 |
bestblogs.resource.deep_read.prepare | bestblogs read deep <id> | 一次完成 meta + markdown + mark read |
只暴露 deep_read.prepare 作为主原语——它是 CLI bestblogs read deep 的 wrap,并行拉 meta+markdown,串行 mark read。
bestblogs read deep RAW_xxx --json返回:
{
"success": true,
"data": {
"meta": {
"resourceId": "RAW_xxx",
"title": "...",
"url": "...",
"resourceType": "ARTICLE",
"language": "en_US",
"score": 88,
"sourceName": "..."
},
"markdown": "# Title\n\n...",
"readMarked": true,
"markError": null
}
}bestblogs read deep RAW_xxx --markdown-only输出纯 Markdown(stdout),适合 | anthropic / | llm 等管道。
bestblogs read deep RAW_xxx --no-mark-read --json404 / NOT_FOUND → 资源不存在或已下架;告诉用户sourceVisibility=PRIVATE)且当前用户未订阅 → meta 可能返回 null;提示用户订阅对应源readMarked=false, markError="..." 而不是整体失败,skill 应保留正文给用户并告知 "已读回传失败,不影响阅读"bestblogs-discover today → 从 candidates[] 挑一条 → bestblogs-read deep <id> --json → 把 markdown 喂给本地 LLM 做总结/提问 → bestblogs-capture 做笔记保存756ffbd
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.