Agent skill

ai-daily-digest

Daily AI news digest covering technical advances, business news, and engineering impact. Aggregates from research papers, tech blogs, HN, newsletters. Use daily for staying current on AI developments.

majiayu000github.com/majiayu000GitHub ↗
claude-codecan modify filesMIT
Install
npx skills add majiayu000/claude-skill-registry --skill ai-daily-digest --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 31 KB
Bundled scripts: none
Allowed tools: WebSearchWebFetchReadWrite
Path: skills/analysis/ai-daily-digest/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Generates a comprehensive daily AI news digest with coverage across technical advances, business news, and engineering impact. It aggregates content from research papers, tech blogs, Hacker News, and newsletters. The skill supports an optional focus argument to narrow to technical, business, engineering, leadership, or all. It maintains a last-run date and a deduplicated list of previously covered stories to avoid repeats, and it preserves a rolling history of up to 300 entries by storing lines in a .covered-stories file with the format {date}|{story_id}|{url}.

How it works

Phase 1: Setup reads sources.md and output-template.md, parses arguments for focus, and reads .last-run to determine the date range (defaulting to past 7 days on first run). It reads .covered-stories to build covered_ids and covered_urls, migrating if needed. If today is Friday, it enables Weekly Recap Mode. Phase 2–9: Technical Research, Business Research, Engineering Impact Research, Leadership Research, GitHub Trending AI, AI Tools for Professionals, AI Application Domains, and AI Safety & Ethics define date ranges and search patterns by focus. For each phase, the agent collects relevant items (new model releases, funding, tools, blogs, papers, policies, etc.) while checking against the deduplicated story sets and updating the last-run and covered stories as it progresses. GitHub phase uses direct fetches and patterns to identify trending repos, ensuring items are either new or not yet covered. Each phase specifies patterns and signals to evaluate, with mechanisms to add new blogs or tools to the digest.

When to use it

Use daily to stay current on AI developments. Friday triggers weekly recap mode with broader date ranges, more sources, and a special digest title.

What it can touch

  • Tools: claude-code
  • Data files: ./findings/ai-daily-digest/.last-run, ./findings/ai-daily-digest/.covered-stories, sources.md, output-template.md
  • External sources: web content via the search patterns and site queries defined in the phases

Caveats

  • License: MIT
  • The workflow relies on external sources; deduplication depends on the story_id format and the covered-stories file. If the file is missing or malformatted, migration or fresh run occurs, but the behavior is constrained to the rules in the Phase descriptions.
From the SKILL.md

# AI Daily Digest Skill Generate comprehensive daily AI news digest with technical, business, and engineering coverage. ## Arguments Parse from `$ARGUMENTS`: - `--focus [technical|business|engineering|leadership|all]` — Default: all ## State Files ### Last Run Date Track last run date in: ```text ./findings/ai-daily-digest/.last-run ``` Format: `YYYY-MM-DD` ### Previous Stories (Deduplication) Track previously covered stories in: ```text ./findings/ai-daily-digest/.covered-stories ``` **Format:** Each story on one line with pipe-separated fields: ```text {date}|{story_id}|{url} ``` Where: - `date` — Date story was covered (YYYY-MM-DD) - `story_id` — Normalized identifier: lowercase, no spaces, key terms only (e.g., `falcon-h1r-7b-release`, `xai-20b-funding`, `openai-gpt5-launch`) - `url` — Source URL **Example:** ```text 2026-01-28|deepseek-r1-release|https://api-docs.deepseek.com/news/news250120 2026-01-29|falcon-h1r-7b-release|https://falcon-lm.github.io/blog/falcon-h1r-7b/ 2026-01-29|xai-20b-funding|https://news.crunchbase.com/venture/biggest-funding-rounds ``` Keep last 300 entries (trim oldest when exceeding). **Purpose:** Prevents duplicate stories across days. Web searches r

What's inside
Steps it walks through
  1. Arguments
  2. State Files
  3. Last Run Date
  4. Previous Stories (Deduplication)
  5. Friday Weekly Recap Mode
  6. Blog Discovery (Friday)
  7. Workflow
  8. Phase 1: Setup
  9. Phase 2: Technical Research
  10. Phase 3: Business Research
  11. Phase 4: Engineering Impact Research
  12. Phase 5: Leadership Research
  13. Phase 6: GitHub Trending AI
  14. Phase 7: AI Tools for Professionals
Ships with 1 file
  • metadata.json
Commands it runs
mkdir -p ./findings/ai-daily-digest
Full digest since last run
Technical focus only
Business news only
More from claude-skill-registry
All skills →
About this skill
What does the ai-daily-digest skill do?

Daily AI news digest covering technical advances, business news, and engineering impact. Aggregates from research papers, tech blogs, HN, newsletters. Use daily for staying current on AI developments.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill ai-daily-digest --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going