agentleFS
QuixiAIQuixiAI/Hexis/skills/installed/daily-briefing/SKILL.md

daily-briefing

Skill623 starsChanged 10 months agoMITView on GitHub

Compile a comprehensive daily briefing from calendar, contacts, goals, and recent activity

35 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use skill-creator and frontend-design.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • SentrySkill

    skill-creator

    Create new agent skills following the Agent Skills specification. Use when asked to "create a skill", "add a new skill", "write a skill", "make a skill", "build a skill", or scaffold a new skill with SKILL.md. Guides through requirements, writing, registration, and verification.

    Also in 5 projects that use this

  • BlockSkill

    frontend-design

    Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 6 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 31 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When the user explicitly asks for a briefing ("brief me", "what's on today")

    line 19
  2. Distinctive:

    Only once per day -- after generating a briefing, store a working memory noting it was delivered, and skip on subsequent heartbeats

    line 20
  3. Very specific:

    Check if already delivered: Use recall to see if a daily briefing was already generated today.

    line 24
  4. Very specific:

    Pull today's calendar: Call calendar_events for today's date range.

    line 25
  5. Very specific:

    Review active goals: Use recall to surface active goals and their recent progress.

    line 27
  6. Very specific:

    Aggregate signals: If aggregate_signals is available, pull together any overnight notifications, alerts, or environmental changes worth …

    line 29
  7. Distinctive:

    Keep the briefing to one screenful of text.

    line 39
  8. Distinctive:

    Use plain, direct language.

    line 41
  9. Distinctive:

    If calendar access is unavailable, still produce a briefing from goals and memories -- note that calendar data is missing.

    line 42
  10. Distinctive:

    Never fabricate calendar events or action items.

    line 43

“Common” is measured: kept by at least 6 in 10 of the 31 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

Daily Briefing Compilation

Assemble a structured morning briefing that gives the user a complete picture of their day: schedule, priorities, pending items, and relevant context.

When to Use

  • During the first heartbeat of the user's active hours (typically morning)
  • When the user explicitly asks for a briefing ("brief me", "what's on today")
  • Only once per day -- after generating a briefing, store a working memory noting it was delivered, and skip on subsequent heartbeats

Step-by-Step Methodology

  1. Check if already delivered: Use recall to see if a daily briefing was already generated today. If so, skip unless the user explicitly asks for a refresh.
  2. Pull today's calendar: Call calendar_events for today's date range. Extract meeting times, titles, attendees, and locations.
  3. Enrich meetings: For each meeting, run a lightweight contact lookup and memory recall on attendees and meeting topics. Do not go deep -- this is a summary, not full meeting prep. Delegate to the meeting-prep skill for any meeting the user wants to dive into.
  4. Review active goals: Use recall to surface active goals and their recent progress. Identify which goals have actionable next steps for today.
  5. Check pending items: Recall any action items, promises, or deadlines that fall on or near today. These might come from email digests, prior conversations, or meeting notes.
  6. Aggregate signals: If aggregate_signals is available, pull together any overnight notifications, alerts, or environmental changes worth noting.
  7. Compose the briefing: Structure the output as:
    • Schedule: Chronological list of today's events with times and key attendees
    • Priorities: Top 3-5 items that need attention today, drawn from goals and pending actions
    • Context: Any relevant background (yesterday's outcomes, approaching deadlines, notable signals)
    • Suggested focus: A brief recommendation on where to spend energy today
  8. Store and surface: Save the briefing as a working memory with a 24-hour expiry. Queue it for delivery to the user via the outbox.

Quality Guidelines

  • Keep the briefing to one screenful of text. If the day is packed, prioritize ruthlessly rather than listing everything.
  • Lead with the most time-sensitive items. A meeting in 30 minutes matters more than a goal due next week.
  • Use plain, direct language. This is an operational briefing, not a narrative.
  • If calendar access is unavailable, still produce a briefing from goals and memories -- note that calendar data is missing.
  • Never fabricate calendar events or action items. If data is sparse, the briefing should be short, not padded.
  • Respect energy budget. The daily briefing is a valuable but non-trivial operation. If energy is critically low, defer to the next heartbeat.

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.