Daily SRE News Digest

Generate a categorized and rated news digest from sre.news. Use for creating SRE/DevOps/Solution Architect daily or periodic news summaries with expert scori...

MIT-0 · Free to use, modify, and redistribute. No attribution required.
1 · 79 · 0 current installs · 0 all-time installs
MIT-0
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description match the included files: a small Python scraper (scripts/scrape_sre_news.py), a scoring rubric, and a markdown template. All required artifacts are appropriate for generating a news digest from sre.news; no unrelated credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md stays focused on scraping sre.news, reading article URLs, rating and categorizing, and producing a markdown file. It explicitly references local rubric and template files. One notable operational point: the runtime instructions expect the agent (or user) to open and read each article URL on external sites — this necessarily causes network fetches of third-party pages. That is coherent with the purpose but means the agent will access arbitrary external sites while summarizing.
Install Mechanism
No install spec; the skill is instruction-only with a small included Python script. The script uses Python stdlib urllib/html.parser and does a single network fetch to https://sre.news. There are no downloads from unknown hosts or archive extraction steps.
Credentials
The skill requests no environment variables, no credentials, and no config paths. This is proportionate to its stated function. The included script only performs network reads of sre.news and derives external article URLs but does not attempt to read local secrets or environment.
Persistence & Privilege
always is false and the skill does not request persistent system-wide changes. It writes output to a local markdown file per SKILL.md; that is reasonable for the task and within expected scope.
Assessment
This skill appears to do what it says: it scrapes sre.news, collects article links, and guides the agent to read and summarize articles into a markdown digest. Before installing, consider: (1) running the included Python script in a sandbox or reviewing it yourself (it's small and uses only stdlib network calls to https://sre.news); (2) the agent will fetch and read arbitrary external article pages when producing summaries — avoid letting the agent access any local files or secrets during that process; (3) no credentials are requested, so there is no secret-exfiltration signal in the manifest, but network fetching of third-party pages can expose your agent's IP and user-agent. If you are comfortable with those behaviors, the skill is coherent and proportionate to its purpose.

Like a lobster shell, security has layers — review code before you run it.

Current versionv1.0.2
Download zip
latestvk973pkahn7bxpg4hdb535afvf983dxyd

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

SKILL.md

SRE News Digest

Generate a professionally curated, categorized, and rated news digest from sre.news with a senior SRE/DevOps/Solution Architect perspective.

Workflow

  1. Scrape — Fetch recent news from sre.news
  2. Read — Open and read each article to understand its content
  3. Rate — Score each article (1-5 ⭐) using the scoring rubric
  4. Categorize — Assign categories from the taxonomy
  5. Format — Generate the final markdown digest grouped by category

Step 1: Scrape sre.news

Run the helper script (path relative to this skill's directory):

python scripts/scrape_sre_news.py [days]

The script outputs a JSON array. Each item contains title, url, source, and optionally date. The days argument filters articles to the requested time range (default: 1 day). If date metadata is unavailable on the page, all articles are returned.

If the script output is incomplete or titles are missing, use the browser to visit https://sre.news directly and collect articles manually. When browsing, capture the original article title, URL, and source/publication name for each item.

Step 2: Read Each Article

Open each article URL and read the content to understand key points, technical depth, and relevance to SRE/DevOps practice. Focus on the article body; avoid following tracker links, ad networks, or unrelated external resources embedded in the page. This step is critical for accurate rating and summarization.

Step 3: Rate Articles

Rate each article from 1 to 5 stars from a senior SRE/DevOps/Solution Architect perspective. Consult the scoring rubric for detailed criteria:

references/scoring-rubric.md

Step 4: Categorize Articles

Assign one or two categories to each article. The scoring rubric file also contains the category taxonomy. Create new categories if existing ones do not fit.

Group articles by their primary category in the final output.

Step 5: Format Output

Generate the digest in English as a Markdown file. Follow the template structure in:

templates/digest_template.md

Key formatting rules:

  • Title includes the date of the digest
  • Articles grouped by category (use ## for category headers)
  • Each article includes: title with link, source, star rating, and a 2-3 sentence expert summary
  • Preserve original article titles and URLs exactly as found
  • Write summaries from an SRE/DevOps/Solution Architect perspective, highlighting operational impact and practical relevance
  • End with a footer crediting sre.news as the source

Save the output to sre_news_digest.md in the current working directory, or a user-specified path.

Files

4 total
Select a file
Select a file to preview.

Comments

Loading comments…