morning-brief
Skill5 starsChanged 6 months agoMITView on GitHub
Produces a short morning briefing from the user's calendar, inbox, and messaging apps — today's schedule, the emails that actually need attention, the top three priorities for the day. Use when the user asks for a morning brief, daily summary, start-of-day briefing, or variations. Best run as a scheduled task weekday mornings.
We split this skill into the rules it gives an agent
10 rules. 0 are common, 9 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 18 edited versions we read keep these.
9
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
- Distinctive: line 12
Read these in order. Skip any that don't exist.
- Distinctive: line 18
If none of those exist, tell the user this skill works better with context files set up, and offer to help create them.
- Distinctive: line 31
Do not include every email.
- Distinctive: line 32
Do not draft replies. This is a brief, not an action.
- Distinctive: line 33
Do not include marketing emails, newsletters, automated notifications, or CC-ed threads where the user isn't the primary recipient.
- Distinctive: line 34
Do not speculate on priorities without evidence.
- Distinctive: line 49
Read the prior brief if one exists, note any "to follow up on tomorrow" items
- Distinctive: line 84
If the user works outside a standard 9–5, ask them what window to pull the inbox over.
- Distinctive: line 85
If they use a non-Google / non-Microsoft calendar, you'll need a compatible connector or an iCal export workflow.
- Very specific: line 86
If the "inbox that matters" filter is too aggressive or too loose, tell them to save feedback to memory.md and this skill will tune over …
“Common” is measured: kept by at least 6 in 10 of the 18 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.
Files
Morning Brief
Turn calendar + inbox + messaging chaos into one readable page the user can scan while drinking coffee.
Before starting
Read these in order. Skip any that don't exist.
context/about-me.md— who the user iscontext/preferences.md— how they want reports formattedcontext/voice.md— only if the brief includes any drafted messages
If none of those exist, tell the user this skill works better with context files set up, and offer to help create them. Then proceed with sensible defaults.
What to produce
A single markdown file, saved to /output/morning-brief-{YYYY-MM-DD}.md, with four sections:
- Today at a glance — the day's calendar, one line per event. Highlight the first event and any back-to-backs.
- Inbox that matters — emails received since the last brief (or the last 18 hours if no prior brief exists) that meet at least one of: (a) from a named priority contact, (b) explicit question directed at the user, (c) deadline in the next 48 hours, (d) reply from an active thread the user started. Summarize each in one line. Skip everything else.
- Messages worth seeing — same filter applied to Slack, Teams, or whichever messaging connector is wired up. Only DMs and @mentions, never channel noise.
- Top three priorities — your best read of what the user should focus on today, based on the calendar, the inbox, and anything flagged in prior briefs. One line each, with a one-line "why."
What not to do
- Do not include every email. If the list is longer than 8 items, you've set the bar too low — raise it.
- Do not draft replies. This is a brief, not an action.
- Do not include marketing emails, newsletters, automated notifications, or CC-ed threads where the user isn't the primary recipient.
- Do not speculate on priorities without evidence. If you can't justify a priority from the data, leave it out.
Inputs (usually connectors)
- Google Calendar or equivalent (required)
- Gmail or equivalent (required)
- Slack / Teams / other messaging (optional but valuable)
- Prior morning briefs in
/output/(optional — use to track continuity)
How it works
- Pull today's calendar events (user's local time zone from
preferences.md, or ask) - Pull unread + recently-read emails in the window (default: since last brief, else 18 hours)
- Apply the "inbox that matters" filter
- Pull messages (if connector available) — DMs and @mentions only
- Read the prior brief if one exists, note any "to follow up on tomorrow" items
- Assemble the four-section brief, save to
/output/morning-brief-{YYYY-MM-DD}.md - Tell the user the file is ready and give a one-sentence top-line ("Big day — three external calls, two flagged emails, one decision due.")
Example output structure
# Morning Brief — 2026-04-18
**TL;DR:** Three external calls, two flagged emails, one decision due by 3pm.
## Today at a glance
- 09:00–09:30 — 1:1 with Morgan *(first event)*
- 10:00–11:00 — Board prep (internal)
- 13:00–14:00 — Acme discovery call *(external — confirm deck is final)*
- 15:00–15:30 — Back-to-back starts: Q2 planning
- 15:30–16:00 — Back-to-back continues: ops review
## Inbox that matters (3)
- **Sarah Chen (Northwind)** — asking for contract redline by EOD Friday
- **Morgan** — sent Q2 priorities doc for review ahead of 9am 1:1
- **Legal (thread reply)** — answered the question about indemnification; needs your sign-off to proceed
## Messages worth seeing (2)
- Slack DM from Taylor: "Need your call on the vendor switch by 3pm"
- Slack @mention in #ops: question about the weekly report format
## Top three priorities
1. **Decision on vendor switch by 3pm** — Taylor is blocked. (from Slack DM)
2. **Read Morgan's Q2 priorities doc before 9am** — better prep for the 1:1. (from inbox)
3. **Redline Northwind contract today or tomorrow** — Friday EOD is the real deadline. (from inbox)Customization notes
- If the user works outside a standard 9–5, ask them what window to pull the inbox over.
- If they use a non-Google / non-Microsoft calendar, you'll need a compatible connector or an iCal export workflow.
- If the "inbox that matters" filter is too aggressive or too loose, tell them to save feedback to
memory.mdand this skill will tune over time.
Other versions22 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 22
- jezweb/vite-flare-starter★ 49same name
- chacosoldier/compabob★ 34same name
- CodeAlive-AI/ceo-ai-os★ 9same name
- MaximeGaudin/second-brain-starter★ 8same name
- rgourley/quant-garage★ 7same name
- megandmartin/agent-skills-repo★ 3same name
- DScardini91/agentic-os★ 2same name
- rami-maalouf/skills★ 2same name
- aakashg/parenting-os★ 1same name
- amanuelmamo7/Skills★ 1same name
12 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- doc-summarizeSkill
- inbox-triageSkill
- meeting-debriefSkill
- meeting-prepSkill
- research-briefSkill
- weekly-reportSkill
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
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.

