agentleFS
Sign inStart free
jezwebjezweb/vite-flare-starter/skills/morning-brief/SKILL.md

morning-brief

Skill49 starsChanged 3 months agoMITView on GitHub

Generate a personalised morning briefing covering weather, news, schedule, and saved priorities. Use when the user asks for a morning brief, daily summary, or "what's happening today?".

We split this skill into the rules it gives an agent

7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Use show_metric_cards for at-a-glance items (temperature, top story count, deadlines)

    line 33
  2. Very specific:

    Use show_timeline if the user has scheduled events

    line 34
  3. Distinctive:

    If something failed (e.g. weather API down), note it briefly and continue.

    line 43
  4. Distinctive:

    Don't generate news headlines without searching first (no fabrication)

    line 46
  5. Distinctive:

    Don't include unread emails count without checking — this isn't email triage

    line 47
  6. Distinctive:

    Don't be overly cheerful or motivational

    line 48
  7. Distinctive:

    Don't repeat the same brief format daily — vary the focus based on what's actually changing

    line 49

“Common” is measured: kept by at least 6 in 10 of the 18 edited versions of this file we could read. “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

Morning Brief

When to use

  • The user asks for a morning brief, daily digest, or summary of the day
  • A scheduled task fires (cron-triggered briefing)

Steps

  1. Recall context — call recall and search_memory to pull:
    • Location (for weather)
    • Topics of interest (news filtering)
    • Active projects or priorities
    • Personal preferences (tone, length)
  2. Gather inputs in parallel — these can run independently:
    • Weather: web_search for "weather [location] today" or use browser_extract on a weather site
    • News: web_search for top news in saved topics
    • Calendar/tasks: if a calendar tool is available, query it; otherwise mention "no calendar configured"
  3. Compose the brief with this structure:
    • Greeting (1 line, time-appropriate: "Good morning, [name]")
    • Today's outlook (1-2 sentences: weather, big-picture)
    • News highlights (3-5 bullet points with markdown links)
    • On your radar (saved priorities, deadlines coming up)
    • Suggested focus (1 sentence: what to prioritise today)
  4. Render with UI:
    • Use show_metric_cards for at-a-glance items (temperature, top story count, deadlines)
    • Use show_timeline if the user has scheduled events
    • Otherwise, plain markdown
  5. Save the brief — call fs_write to save to briefs/YYYY-MM-DD.md for later reference.

Style

  • Brief and skimmable. Total length 200-400 words max.
  • Time-zone aware. Use the user's local time.
  • Skip generic greetings ("Hope you have a great day!") — be substantive.
  • If something failed (e.g. weather API down), note it briefly and continue.

What not to do

  • Don't generate news headlines without searching first (no fabrication)
  • Don't include unread emails count without checking — this isn't email triage
  • Don't be overly cheerful or motivational
  • Don't repeat the same brief format daily — vary the focus based on what's actually changing

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.

Check your setup, free