news-digest SKILL.md skillA
news-digest from kendrick-stein/mcislab_deepread is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add kendrick-stein/mcislab_deepread/news-digest@git:20260714.527a950Pins git:20260714.527a950 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- kendrick-stein/mcislab_deepread
- Path
skills/1-literature/news-digest/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260714.527a950, committed Jul 14, 2026
- First version recorded
- Jul 6, 2026
- Size
- 5,063 bytes
- Repository stars
- 12
- License
- none declared
当 Supervisor 说"看看最近有什么 AI 新闻""news 总结"，或 autoresearch 检测到 News/ 超期未更新时，抓取 config 中的博客/新闻/公众号源，按研究兴趣筛选点评， 产出 News/YYYY-MM-DD.md 并把重要线索回链进 vault。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
## Purpose
非论文信息源（官方博客、技术媒体、公众号）的摄入端，架构与 daily-papers 相同的三段式：
脚本抓取打分（零 token）→ 分流 → 精读点评。产出周报式 News 摘要；真正有信息量的条目
（新工具/重要发布/研究 idea 线索）沉淀为可 wikilink 的小节回链进 survey/agenda，
让网络信息也进入知识复利循环。
## Steps
### Step 0：解析时间范围
"今日" → `--days 1`；"过去N天/一周" → 对应天数；未指定 → 省略参数（用 config news.days）。
### Step 1：抓取打分（零 token）
```bash
python3 skills/1-literature/news-digest/fetch_news.py --days {DAYS} \
--output Workbench/daily/.news-candidates.json
```
Read 输出 JSON：`candidates`（RSS 已打分排序；`title_only: true` 的条目来自无摘要 feed，
脚本无从预筛而全量保留，分流时需自行判断相关性）、`web_sources`（需 agent 抓取的网页源）、
`errors`（失败源）。对每个 web_source 用 WebFetch（或 `scripts/lexmount_fetch.py` fallback，
见 references/network-fetch-fallback.md）抓首页，人工筛出时间范围内的条目并入候选。
**公众号源（若 config `news.wechat.enabled`）**：再跑一次微信搜索（爬搜狗，零 token）：
```bash
python3 scripts/wechat_search/fetch_wechat.py --days {DAYS} \
--output Workbench/daily/.wechat-candidates.json
```
Read 输出 JSON：`candidates` 已按 `watched`（是否来自关注账号）+ 打分排序，字段与上面的
news candidates 对齐（title/link/summary/source/published/score），可直接并入候选池。
`errors` 记录被搜狗限流/失败的关键词。**首次运行**若报 `node_modules 缺失`，先
`cd scripts/wechat_search && npm install`（依赖 Node 18+ 与 cheerio）。搜狗返回的是中间链，
精读时若打不开可提示用户在浏览器打开或据标题+摘要判断。
…Read the whole file at its exact version.
How to install
mdr add kendrick-stein/mcislab_deepread/news-digest@sha256:4258d6fbd4b1bd2aThe line at the top of this page pins the label git:20260714.527a950, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_phcr6kxrpz4xmown)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Jul 6, 2026 and Jul 14, 2026, about one every 3 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260714.527a950 latest | 2026-07-14 | 527a950 | 5,063 B | A | view · diff |
| git:20260708.9d6bcbe | 2026-07-08 | 9d6bcbe | 4,939 B | A | view · diff |
| git:20260706.cdb883e | 2026-07-06 | cdb883e | 3,932 B | A | view · diff |
| git:20260706.1fb9c65 | 2026-07-06 | 1fb9c65 | 3,485 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5063 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
kendrick-stein/mcislab_deepread · 12 stars · license none declared · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_phcr6kxrpz4xmown GET https://markdownregistry.com/api/v1/resolve?ref=kendrick-stein/mcislab_deepread/news-digest GET https://markdownregistry.com/api/v1/blob/4258d6fbd4b1bd2adc14794c7ac69a68163ffb5b9fe25d8840603b301d8eda0a
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from kendrick-stein/mcislab_deepread
Every file in kendrick-stein/mcislab_deepread