- Home
- Skills
- Productivity
- Write a Morning Briefing Worth Reading
More screenshots
Works with the AI Agents you already use
Write a Morning Briefing Worth Reading
A morning briefing that lists the real work from last night, today's schedule, and the decisions waiting on you — with a recommendation on each.
$9
Write a Morning Briefing Worth Reading
Example session with this skill installed
Assemble my daily briefing. Check the 'web-app' and 'api-server' repos, my Google Calendar for today, and the pending items in the #launch-ops channel. Earliest delivery is 09:30.
- Read your context and instructions
- Compiled the write a morning
Briefing assembled for 2024-05-22 and archived to briefs/2024-05-22.md.
Daily Briefing: May 22, 2024
Overnight Rundown
- web-app: 4 commits to
main. Verified: UI deployment for checkout flow is live. - api-server: 1 commit to
dev. Fixed: Stripe webhook signature validation. - Scheduled Jobs:
db-backup-nightlyran successfully at 03:00. - Quiet sectors: No activity in
docsormobile-assets.
Today's Agenda
| Time | Event | Note |
|---|---|---|
| 10:00 | Standup | Prep: Review yesterday's PR #402 |
| 14:00 | Client Sync | Unconfirmed: Awaiting reply on Zoom link |
| All Day | Focus Block | No meetings after 15:00 |
Goals & Pace
- Q2 Launch: On track. Last movement: 8 hours ago.
- Auth Refactor: STALLED (4 days). Waiting on: Your direction on JWT expiration logic.
- CI/CD Migration: Steady-state. No change required.
Needs Your Decision
- Database Scaling: Vertical or horizontal?
- Options: Upgrade instance size or implement read replicas.
- Recommendation: Vertical upgrade; lowest complexity for current traffic.
- Age: 2 days.
- Library Update: Force upgrade
dependabotPRs?- Options: Manual review or auto-merge minor versions.
- Recommendation: Manual review for
auth-lib, auto-merge others. - Age: 1 day.
Next steps
- Review the
auth-librecommendation in section 4. - Confirm the 14:00 Zoom link in your inbox.
- Check
briefs/for the historical log of these decisions.
Connects securely to your tools. The creator never sees your data.
About this skill
A briefing for someone running many projects has one job: replace an hour of status-hunting with one honest page. Most fail three ways — headline summaries instead of the actual work ("progress was made on several projects"), invented activity on quiet nights, and decisions buried in prose where they'll never be acted on. This method has run daily for months in production and avoids all three by construction.
Inside the package: the skill file with the fixed structure, the full input list, and the delivery rules; a brief template; and an assembly checklist. The structure never changes: overnight rundown, today's agenda, goals and pace, then a numbered decision list.
A run goes like this: the agent gathers evidence first — commits and file changes across your projects, messages sent and received, scheduled jobs that ran, the calendar, open goals — never memory, never plans. The overnight section enumerates the real work item by item: what shipped, what changed, what was verified. A quiet night is reported as a quiet night, with the proof (zero commits, no new files). Stalled goals are named with their age — "no movement in 3 days, waiting on your direction." Every decision item states the question, the options, a recommendation, and how long it has been open. Two delivery rules matter: the brief never lands before the earliest time you set (mine is 9:30 AM — a 6 AM briefing is noise, not service), and it's filed to a dated archive so any claim in it can be re-checked later. If an input source is down, the brief says which section is missing and why, instead of silently leaving a hole.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Productivity.
Requires access to git logs, calendars, and messaging history. Reporting depends on the availability of external connectors. Strict delivery schedule prevents early arrivals.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 6 days ago
- Software
- Access to project reposAccess to calendar and messages