agentleFS
cacardinalcacardinal/laila/.claude/skills/daily-brief/SKILL.md

daily-brief

Skill1 starsChanged 4 months agoMITView on GitHub

Full cross-domain morning briefing. Checks all channels, calendar, reminders, news, pipeline, and generates formatted brief.

31 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use weekly-review, onboarding and 1 more.

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.
  • QuixiAISkill

    weekly-review

    Review the past week across goals, tasks, calendar, journal, and commitments, then propose the next week

    Also in 5 projects that use this

  • 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

7 rules. 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 24 edited versions we read keep these.

  • 6

    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. Distinctive:

    Always include a motivational quote: Every brief, no exceptions.

    line 14
  2. Distinctive:

    Update the Running Brief: clear items Alex handled, refresh stale items with new context

    line 47
  3. Distinctive:

    Update domain status.md files with new information discovered

    line 48
  4. Distinctive:

    Update pipeline stages if new info was discovered (rejections, advances)

    line 49
  5. Distinctive:

    All communications organized by domain, not by channel.

    line 56
  6. Distinctive:

    NOT commercial or automated

    line 61
  7. Very specific:

    Weekly rollup (Fridays): Read the week's dailies -> generate state/briefs/weekly/YYYY-MM-DD.md -> delete dailies

    line 72

“Common” is measured: kept by at least 6 in 10 of the 24 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 Skill

Generates a comprehensive morning briefing across all life domains. Saved to state/briefs/daily/YYYY-MM-DD.md.

Core Rules (every run, non-negotiable)

  • Full live sweep — never echo past findings. Every status the brief reports (service/infra health, tool availability, pipeline state, domain status) MUST be re-verified live THIS run. Cached state files (state/*.json) and domain tracking/status.md are inputs and hints — never facts to repeat. If a tracked item says "down" / "broken" / "working", actually re-test it before reporting. If you genuinely cannot re-verify something this run, label it unverified (last known: …) rather than carrying the old claim forward. A brief that parrots a stale "DOWN" or "broken" is a bug — that is exactly what this rule exists to prevent.
  • Always include a motivational quote. Every brief, no exceptions. Generate a fresh one each run (vary it day to day; attribute real quotes; a line or two; tune to Alex's current focus when natural). It renders near the top, right under the greeting.

Workflow

When triggered:

  1. Read state/strategy.md for global priorities 1b. Strategy staleness check — check the file's mtime. If it is >30 days old, include a one-line nudge in the brief: ⚠️ strategy.md last updated <date> — refresh via strategy interview
  2. Read state/running-brief.json — the Running Brief is the primary source of pending comms items. Incorporate active items into Priority Actions and Domain Sections. Flag the stale item count.
  3. Check Calendar — ALL configured accounts for today + tomorrow (e.g. personal + work). Missing any account is a bug. (Query your calendar integration here — one call per account.)
  4. Check the task system — all lists/projects for overdue + today's items. (Query your reminders/task tool here.)
  5. Check Email — ALL configured accounts. Missing any account is a bug:
    • Personal inbox (e.g. a gmail-personal MCP server) — run each active domain's email filters (defined in the domain AGENTS.md files): career, health, household, content, acme
    • Work inbox (e.g. a gmail-work MCP server) — unread + last 24h; mail from key stakeholders is high priority while an engagement is live
  6. Check messaging channels — any configured messaging queue or capture file (e.g. state/comms-queue.json); respect per-channel allowlists
  7. Check news subscriptions for the last 24h — read your configured news-sources list for senders and categories. Deep-read full bodies and extract articles with links + summaries.
  8. Check the pipeline system — (query your CRM/task system here) for the career pipeline:
    • Prospects in Discovery/Proposal/Scoping stage (for company news search)
    • Stale pursuits (>7 days no activity)
    • Recently changed stages (rejections, advances)
  9. Web search for news on companies in Discovery/Proposal/Scoping status
  10. Meeting prep — for each external meeting on today's calendar, assemble (or dispatch a subagent to assemble) a short prep brief from domain files and contact notes; include it in the calendar section.
  11. Read domain tracking files — each domain's tracking/status.md. Skip domains whose state in config/domain-triggers.json is not active. 11b. Domain status hygiene (Fridays only) — run the /domain-hygiene scan and include flagged domains in the Infrastructure section. Do NOT auto-fix; surface as a short list so Alex can trigger /domain-hygiene cleanup for a batch pass.
  12. Check goals — flag goals due this week or at-risk. (Read from whatever system is authoritative for goals.) 12b. Cross-domain synthesis — compare state/strategy.md against every active domain's tracking/status.md (directly or via a subagent); include max 6 bullets tagged [conflict]/[synergy]/[stale]/[drift] as a brief section.
  13. Action generation:
    • For any Running Brief item requiring response: draft a reply (drafts only — never send)
    • For any email requiring response: draft a reply
    • For any pursuit >7 days stale: draft a follow-up email
    • For any overdue task: propose completion or a new due date
    • For any goal at risk: flag with a specific recovery action
  14. State updates:
    • Update the Running Brief: clear items Alex handled, refresh stale items with new context
    • Update domain status.md files with new information discovered
    • Update pipeline stages if new info was discovered (rejections, advances)
    • Propose a task-system sync (don't wait for session end)
  15. Output the formatted brief (structure below)

Brief Output Format

Domain-First Organization

All communications organized by domain, not by channel. Each domain section includes comms from ALL channels + tasks + domain-specific data. Only include domains with content for today.

Urgency Heuristic

Flag as URGENT when ALL of:

  1. Same person contacted 2+ times in 24h (any combination of channels)
  2. NOT commercial or automated
  3. Content suggests they need a response

Section Order

  1. Vision -> 2. Motivation (always — a fresh motivational quote) -> 3. Schedule -> 4. Urgent -> 5. Priority Actions -> 6. Domain Sections -> 7. Industry News -> 8. Goal Progress -> 9. Domain Status -> 10. Infrastructure -> 11. Proposed Schedule -> 12. EOD Checklist -> 13. Skipped/Noise

Infrastructure + any health/availability claim: do NOT just read a cached state file and repeat it. Live-probe each service this run (e.g. curl -sS -o /dev/null -w "%{http_code}" <url> for hosted apps, a real CLI call to confirm a tool, a live token check) and report what you actually observed now. The cached JSON is a hint to confirm, not the answer.

Brief Archiving

  • Daily: Save to state/briefs/daily/YYYY-MM-DD.md
  • Weekly rollup (Fridays): Read the week's dailies -> generate state/briefs/weekly/YYYY-MM-DD.md -> delete dailies

Usage

  • $ARGUMENTS = full or empty: Full brief (all steps)
  • $ARGUMENTS = quick: Pipeline counts + urgent items only ("Quick status")

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.