agentleFS
siddathsiddath/lifeOS/.claude/skills/daily-brief/SKILL.md

daily-brief

Skill7 starsChanged 25 days agoMITView on GitHub

Generate the owner's morning brief from the LifeOS. Use when they say "daily brief", "what's my day", "morning brief", "what should I do today", or any morning check-in asking what to focus on — even casual/scattered phrasings like "ok what now" at the start of a day. Pulls the mission cadence, P1 tasks, reminders, and habits into a short, calm, do-this-now summary.

30 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use onboarding and skill-creator.

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.
  • AnthropicSkill

    onboarding

    Generate an onboarding checklist and first-week plan for a new hire. Use when someone has a start date coming up, building the pre-start task list (accounts, equipment, buddy), scheduling Day 1 and Week 1, or setting 30/60/90-day goals for a new team member.

    Also in 3 projects that use this

  • 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 3 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 23 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Read the owner's name, timezone, and locale from dashboard/lifeos.config.json (owner.shortName, owner.timezone, owner.locale), falling back …

    line 10
  2. Distinctive:

    Use exactly this shape, ≤12 lines total, no essays:

    line 26
  3. Distinctive:

    Use the mission as one input, alongside the owner's current priorities and commitments.

    line 41
  4. Distinctive:

    If a mission has a per-day cadence, the one main thing is today's single block, never "catch up on the whole plan."

    line 42
  5. Distinctive:

    Only create or change a schedule when the owner explicitly requests it.

    line 61

“Common” is measured: kept by at least 6 in 10 of the 23 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 Brief

Give the owner a short, calm summary of confirmed current priorities. Do not infer their emotional state or assume that execution is what they need. Mark uncertainty rather than repeating stale tasks as current.

Read the owner's name, timezone, and locale from dashboard/lifeos.config.json (owner.shortName, owner.timezone, owner.locale), falling back to dashboard/lifeos.config.example.json if it doesn't exist. Address them in second person; use their timezone for "today".

Steps

  1. Establish today. Note today's weekday and date first (in the owner's timezone) — several decisions below depend on it.
  2. Read the sources (all paths relative to the repo root):
    • dashboard/mission.json — the active hero mission: title, gate date, oneThing, rule, and the week cadence.
    • 06_Trackers/tasks.md — P1/P2 items. On a fresh instance this may not exist yet — read dashboard/tasks-data.json (the first-run seed) instead. Browser edits may be newer: ask for a private dashboard export before claiming a complete current task list or rewriting seeds; see docs/browser-data.md, and offer to create 06_Trackers/tasks.md from 06_Trackers/tasks.template.md.
    • 06_Trackers/reminders.md — dated rows + recurring reminders. If missing, skip this source (offer to create it from its template); don't fail.
    • 01_Focus/ — the mission's working plan, only if the mission's oneThing points at a daily cadence there.
  3. Check both tasks and mission for staleness. Compare today with updated: dates, day-specific headings, the mission gate and demo markers. Do not present past-day tasks or a passed/demo mission as today's direction. Use the mission's oneThing only when its currentness is supported. If both sources are stale, say that today's priority is unconfirmed and ask the owner what needs attention; do not manufacture a fallback task. Undated items may carry over when there is evidence they still apply.
  4. Filter time-bound items. From reminders.md include only: rows dated today or tomorrow, and any recurring reminder that fires today (e.g. Sunday → weekly review; 1st of month → finance check). Skip everything already in the past.
  5. Compute the countdown. Days from today until the mission gate. If the gate has passed, use the mission's gatePassedMessage framing instead of a countdown.

Output format

Use exactly this shape, ≤12 lines total, no essays:

**🌅 [Weekday D Mon] · [mission title] · [N] days to [gateLabel]**
🎯 **One main thing:** [single most important thing — from mission oneThing / today's block]
🔴 **P1s:** [3–6 max, honest; omit the section if none are genuinely live]
⏰ **Time-bound:** [today/tomorrow reminders only; omit if none]
🔁 **Don't-skip basics:** [the owner's daily anchors — walk · water · relationship/family time · sleep]
🧘 [one calm grounding line tied to the mission's reframe — e.g. "One honest rep today is the win."]

Optional single ⚠️ line when step 3 found staleness: ⚠️ [source] still shows [old context]. Today's priority [comes from verified source / is not yet confirmed].

Rules

  • Use the mission as one input, alongside the owner's current priorities and commitments. Do not exclude a requested item merely because it falls outside the mission.
  • If a mission has a per-day cadence, the one main thing is today's single block, never "catch up on the whole plan."
  • Tone: direct, warm, calm. Second person. No scolding about what's undone; no motivational padding.
  • The brief must be self-contained — the owner should be able to act on it without opening any file.

Example

Input: "what's my day?" on a Tuesday mid-mission (gate two weeks out, tasks.md fresh) Output:

**🌅 Tue 14 Jul · Operation Launch Week · 12 days to beta launch day**
🎯 **One main thing:** Week 2 block — loading + error states across the core loop (ship one, tick it).
🔴 **P1s:** reply to the two beta-tester intros · draft the invite email
⏰ **Time-bound:** none today
🔁 **Don't-skip basics:** morning walk · water · read 20 min · time with Sam · sleep on time
🧘 Finished, not perfect. One shipped block is the win.

Automating it (optional)

Only create or change a schedule when the owner explicitly requests it. A brief request does not authorize recurring runs or external messages. Use the current assistant's supported scheduling tools when authorized.

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.