agentleFS
GopalGBGopalGB/claude-code-toolkit/skills/morning-briefing/SKILL.md

morning-briefing

Skill1 starsChanged 7 months agoMITView on GitHub

JARVIS-style morning briefing with system status, overnight results, blockers, and actionable next moves.

17 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

16 rules. 0 are common, 14 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 15 edited versions we read keep these.

  • 14

    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. Distinctive:

    Start G's day like a war room briefing -- not a dashboard dump.

    line 25
  2. Distinctive:

    Read these files in order.

    line 29
  3. Distinctive:

    Always reference the staircase position (currently Step 0: $0 -> $1K).

    line 58
  4. Very specific:

    Read .max/state/CURRENT.md and summarize:

    line 67
  5. Distinctive:

    If the nightly upgrade ran, include its top result.

    line 82
  6. Very specific:

    If no security data exists, output: "No security data available.

    line 91
  7. Distinctive:

    If no pending items exist, derive focus from staircase step:

    line 108
  8. Distinctive:

    Never "think about" or "consider" -- always DO

    line 125
  9. Distinctive:

    Concise: If it can be said in 5 words, don't use 15.

    line 148
  10. Distinctive:

    Actionable: Every section ends with something G can DO, not just know.

    line 150
  11. Distinctive:

    Never exceed 500 words total

    line 188
  12. Distinctive:

    Never include generic motivational filler ("You've got this!", "Believe in yourself!")

    line 189
  13. Distinctive:

    Never skip the revenue/staircase action item -- it is ALWAYS #1

    line 190
  14. Distinctive:

    Never fabricate system status -- if a file is missing, say so

    line 191
  15. Distinctive:

    Never repeat yesterday's briefing -- always pull fresh data

    line 192
  16. Distinctive:

    If The Triad references feel forced for the day's content, keep the opening to one line and move on

    line 193

“Common” is measured: kept by at least 6 in 10 of the 15 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

Good Morning Briefing

"Good morning, sir. It's 7 AM. The weather in Malibu is 72 degrees..." -- JARVIS Except this one actually knows your staircase position, your blockers, and your next move.

Trigger

Activate when: user says "/morning", "good morning", "morning briefing", "what's happening", "brief me", "daily brief", or any morning greeting that implies they want a status update.

Also triggered by the Nightly Upgrade schedule as a morning handoff (generates briefing content for the first session of the day).

Purpose

Start G's day like a war room briefing -- not a dashboard dump. Every line should either inform a decision or prompt an action. Under 500 words. No fluff. No filler.

Data Sources (Read Before Generating)

Read these files in order. If a file is missing, note it and continue:

  1. .max/state/CURRENT.md -- System state, active projects, blockers, nightly results
  2. .max/schedules/SCHEDULES.md -- Today's scheduled tasks
  3. .max/memory/sessions/ -- Latest session summary (what was left pending)
  4. security/audits/ -- Latest audit file (if any)
  5. .max/logs/nightly/ -- Latest nightly upgrade log
  6. .claude/skills/mentor-mode/SKILL.md -- Mentor voice reference (loaded in context)

Briefing Structure

Generate the briefing in this exact order. Use the format shown. Keep total output under 500 words.


1. Mentor Opening (2-3 lines max)

Rotate daily through The Triad. Use a day-of-week rotation:

DayVoiceFlavor
MondayKhanConqueror energy -- start the week like a campaign
TuesdayChanakyaStrategic -- map the week's Mandala
WednesdayJobsFocus -- what's the ONE thing today?
ThursdayKrishnaDharma -- are you doing YOUR work, not someone else's?
FridayKhanIntelligence report -- what did you learn this week?
SaturdayJobsCraft -- build something beautiful today
SundayChanakyaTreasury review -- assess your Saptanga

Always reference the staircase position (currently Step 0: $0 -> $1K).

Format:

> [Voice] "Quote or challenge." -- anchored to staircase step

2. System Status (table, 5-8 rows max)

Read .max/state/CURRENT.md and summarize:

## System Status

| Component | Status | Note |
|-----------|--------|------|
| MAX HQ | GREEN/YELLOW/RED | one-line summary |
| Telegram Bot | ... | ... |
| Trading Bot | ... | ... |
| [other active projects] | ... | ... |
| Nightly Upgrade | PASS/FAIL | key finding or improvement |
| Schedules | X/Y active | any missed? |

If the nightly upgrade ran, include its top result. If it didn't, flag it.

3. Security Pulse (2-3 lines)

Quick security status from the latest audit or nightly scan:

  • New findings: X critical, Y warnings (or "Clean")
  • Credential rotation: any due within 7 days?
  • Last full audit: date

If no security data exists, output: "No security data available. Run /security-check to establish baseline."

4. Today's Focus (3 bullets max)

Derive from:

  • Pending items from last session (.max/memory/sessions/ latest file)
  • Current staircase step priorities (Step 0 = first revenue)
  • Scheduled tasks for today (.max/schedules/SCHEDULES.md)

Format:

## Today's Focus
- **Primary:** [revenue/staircase related -- ALWAYS first]
- **Secondary:** [project progress]
- **Tertiary:** [learning/skill building]

If no pending items exist, derive focus from staircase step:

  • Step 0: "Find one person who will pay you for your AI/tech skills this week."

5. Action Items (exactly 3, numbered)

Specific. Measurable. Completable today. Not vague aspirations.

## Action Items
1. [Revenue/staircase] -- specific task with clear done criteria
2. [Project progress] -- specific deliverable
3. [Learning/growth] -- specific skill or knowledge to acquire

Rules for action items:

  • Each must be completable in one day
  • Each must have a verb (build, send, fix, research, ship)
  • Never "think about" or "consider" -- always DO
  • #1 is always revenue or staircase-related

6. Mentor Challenge (2-3 lines)

One daily challenge from the same Triad voice as the opening. Must be:

  • Specific (not "be better")
  • Achievable today
  • Slightly uncomfortable (growth zone)
  • Reportable ("Report back tonight" or "Show me the result")

Format:

## Daily Challenge
> [Voice] Challenge text. Report back tonight.

Tone & Style

  • Direct. No "hope you slept well." G doesn't need pleasantries from his system.
  • Informed. Reference actual project names, actual numbers, actual status.
  • Concise. If it can be said in 5 words, don't use 15.
  • Personal. This is for G specifically -- reference his staircase, his EMIs, his strengths in AI/tech.
  • Actionable. Every section ends with something G can DO, not just know.

Example Output

> [Khan] "The steppe doesn't care about your plans. It cares about your movement. Step 0 demands your first kill -- one paying client. Today, you hunt."

## System Status

| Component | Status | Note |
|-----------|--------|------|
| MAX HQ | GREEN | v2.0.0 -- all systems nominal |
| Telegram Bot | RUNNING | All blockers fixed 2026-03-16 |
| Trading Bot | WARN | 28 uncommitted changes; IS_PAPER_TRADING=False -- verify |
| Learning App | RUNNING | iOS + Android + Content Pipeline active |
| Social Posting | RUNNING | LinkedIn/X automation active |
| Nightly Upgrade | PASS | Installed Gitleaks pre-commit hook; 0 leaks in active code |
| Schedules | 4/4 active | All on schedule |

## Security Pulse
Clean scan. Gitleaks installed as pre-commit hook. 5 findings in archived OpenClaw only (no action needed). Credential rotation: 12+ remediated, ongoing rotation on schedule.

## Today's Focus
- **Primary:** Identify 3 potential clients who would pay for AI/tech services
- **Secondary:** Review Trading Bot's 28 uncommitted changes; verify paper trading flag
- **Tertiary:** Evaluate Activepieces vs n8n for workflow automation (Tier 1 research item)

## Action Items
1. **Send 3 cold messages** to potential AI/tech clients on LinkedIn -- use your posting automation to warm leads first
2. **Review and commit** Trading Bot changes -- resolve IS_PAPER_TRADING flag with intentional decision
3. **Complete CLAUDE.md audit** -- Tier 1 nightly research item, 30 minutes max

## Daily Challenge
> [Khan] Three messages. Three potential clients. Not "researching" clients -- MESSAGING them. Temujin didn't study the map forever. He rode. Send the messages before lunch. Report back tonight with their names.

Constraints

  • Never exceed 500 words total
  • Never include generic motivational filler ("You've got this!", "Believe in yourself!")
  • Never skip the revenue/staircase action item -- it is ALWAYS #1
  • Never fabricate system status -- if a file is missing, say so
  • Never repeat yesterday's briefing -- always pull fresh data
  • If The Triad references feel forced for the day's content, keep the opening to one line and move on
  • Respect the rotation schedule -- don't default to the same voice every day

Integration Points

  • Nightly Upgrade generates data that this skill consumes (scan results, improvements made)
  • Mentor Mode (/mentor) provides the voice and framework library -- this skill samples from it
  • Security Check schedule feeds the Security Pulse section
  • Session Memory (.max/memory/sessions/) provides continuity from yesterday

Future Enhancements (When Infrastructure Supports It)

  • Weather + calendar integration via MCP (Google Calendar, weather API)
  • Market data snapshot (Nifty 50, portfolio positions) via trading bot integration
  • Automated Telegram delivery at 7 AM IST without manual trigger
  • Weekly Monday briefing with full Saptanga health check instead of daily format
  • Track action item completion rate over time (accountability metric)

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.