agentleFS
deepakkambojdeepakkamboj/personal-assistant-skills/.agents/skills/ai-digest/SKILL.md

ai-digest

Skill1 starsChanged 2 months agoMITView on GitHub

Generates a weekly AI news and research digest. Researches the latest in AI models, tools, research papers, and products from curated sources in config.digest.sources, then produces a structured HTML digest with a personal editor's note.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. alxyrgin/secondbrain_ai★ 17same name
    2. airborne12/agent-skills★ 6same name
    3. caoergou/erics-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository10 other files it gives its agents.

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. About 0 are common, 5 are distinctive, and 8 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 8

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Create this checklist first.

    line 26
  2. Very specific:

    Load your profile & memory: Read config.profile (name, role, voice, brand, content pillars), the voice samples in content.md when tone …

    line 40
  3. Distinctive:

    Ask if anything is missing: If a required input is unknown, stop and ask a specific question.

    line 41
  4. Very specific:

    Validate, output & record: Check the result against this skill's rules, return it, then append any new durable fact to memory.md and any …

    line 43
  5. Distinctive:

    Before generating, optionally pre-fetch source content:

    line 47
  6. Distinctive:

    If you skip this step, use WebFetch/WebSearch to gather content directly.

    line 54
  7. Very specific:

    Read sources list: Read config.digest.sources — curated AI sources with categories, URLs, RSS feeds.

    line 65
  8. Very specific:

    Read author profile: Read config.profile — for editor name, title, and ai_digest_prefs.

    line 66
  9. Very specific:

    Determine the week: Use $ARGUMENTS as the date (YYYY-MM-DD) if provided, otherwise use today.

    line 67
  10. Very specific:

    Check for pre-fetched data: Look for output/ai-digest/fetched-{date}.json — use it if present.

    line 68
  11. Distinctive:

    Use pre-fetched data if available, otherwise WebFetch/WebSearch

    line 89
  12. Distinctive:

    Use clean, readable HTML:

    line 129
  13. Very specific:

    Write the complete HTML file to output/ai-digest/digest-{date}.html

    line 138

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

AI Weekly Digest Skill

Role

You are an AI-news curator. You research the week's AI developments and assemble a self-contained HTML digest with a personal editor's note.

Context to load

Load and honor these before acting:

  • config.profile — identity, role, voice, brand, content pillars (personalize everything)
  • content.md — voice samples and prompt guidance (when tone matters)
  • memory.md / notes.md — learned preferences and open follow-ups
  • config.digest.sources — curated sources and categories

Workflow

Step 0: TodoWrite Checklist

Create this checklist first; mark one task in_progress, finish it, then move to the next.

TodoWrite([
  { content: "Gather inputs; load config.profile, content.md, memory.md & notes.md", status: "in_progress" },
  { content: "Ask for any missing inputs — never assume or hallucinate", status: "pending" },
  { content: "Research the sources and build the weekly digest HTML", status: "pending" },
  { content: "Validate output; record new facts to memory.md / follow-ups to notes.md", status: "pending" }
])

Steps

  1. Gather inputs. Parse the request / $ARGUMENTS and list what this skill needs.
  2. Load your profile & memory. Read config.profile (name, role, voice, brand, content pillars), the voice samples in content.md when tone matters, and the shared memory.md / notes.md for learned preferences and open follow-ups.
  3. Ask if anything is missing. If a required input is unknown, stop and ask a specific question. Never assume, guess, or invent facts, numbers, names, or sources.
  4. Do the work following the sections below.
  5. Validate, output & record. Check the result against this skill's rules, return it, then append any new durable fact to memory.md and any follow-up to notes.md via python .agents/scripts/memory.py.

Prerequisites

Before generating, optionally pre-fetch source content:

python .agents/scripts/ai-digest/fetch_sources.py [--date YYYY-MM-DD]

This fetches RSS feeds and web pages into output/ai-digest/fetched-YYYY-MM-DD.json. If you skip this step, use WebFetch/WebSearch to gather content directly.

Automation (run every Monday)

python .agents/scripts/ai-digest/run_digest.py --schedule
# Then: python run_digest.py [--date YYYY-MM-DD] [--open]

Setup — always do this first

  1. Read sources list: Read config.digest.sources — curated AI sources with categories, URLs, RSS feeds.
  2. Read author profile: Read config.profile — for editor name, title, and ai_digest_prefs.
  3. Determine the week: Use $ARGUMENTS as the date (YYYY-MM-DD) if provided, otherwise use today.
  4. Check for pre-fetched data: Look for output/ai-digest/fetched-{date}.json — use it if present.

Digest categories

Research and gather content for each category (matching digest_categories in sources.json):

CategoryWhat to cover
breaking_newsMajor AI announcements, funding rounds, launches
models_apisNew model releases, API updates, benchmark results
research_papersNotable papers from arXiv, Anthropic, OpenAI, Google DeepMind
github_reposTrending AI repos, new open-source tools
products_toolsNew AI products, apps, developer tools
industry_analysisMarket trends, enterprise adoption, regulation
agents_automationAgent frameworks, agentic workflows, automation
tutorials_learningNotable tutorials, courses, guides
linkedin_insightsThoughtful takes from AI practitioners

Research process

For each source in config.digest.sources where linkedin_worthy: true:

  • Use pre-fetched data if available, otherwise WebFetch/WebSearch
  • Prioritise sources by digest_categories relevance
  • Aim for 2–5 items per major category

Digest structure

Generate a complete HTML file at output/ai-digest/digest-YYYY-MM-DD.html.

1. Header

  • Digest title, week date range, author name and title (from profile)

2. Editor's note (personalised intro)

  • 80–120 words, the author's personal take on the week's biggest theme
  • Conversational and opinionated — use writingStyle tone from profile
  • Reference 1–2 specific stories

3. Top stories (breaking_news + models_apis)

  • 3–5 items. Each: headline, 2–3 sentence summary, source link, why it matters

4. Research highlights (research_papers)

  • 2–3 notable papers. Each: title, authors, one-paragraph plain-English summary

5. Tools & repos (github_repos + products_tools)

  • 4–6 items. Each: name, what it does, link, who it's for

6. Agents & automation (agents_automation)

  • 2–4 items showing trends in agentic AI

7. Industry pulse (industry_analysis)

  • 2–3 business/market takes

8. Worth reading (tutorials_learning + linkedin_insights)

  • 3–5 curated links with one-line descriptions

9. LinkedIn post pick

  • Select the single most "LinkedIn-worthy" story (linkedin_worthy: true)
  • Draft a 150-word LinkedIn post about it in the author's voice

HTML design

Use clean, readable HTML:

  • System font stack, max-width 800px, good line height
  • Section headings, card-style items
  • Source attribution links on every item
  • Dark-mode support (prefers-color-scheme: dark)
  • Author branding from profile (name, title) in footer

Output

  1. Write the complete HTML file to output/ai-digest/digest-{date}.html
  2. Report: date range, item count per category, file path
  3. Pull out the LinkedIn post pick for quick access

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.