agentleFS
Sign inStart free
teemutuoteemutuo/super-intelligent-AI-setup/skills/07-morning-brief/SKILL.md

morning-brief

Skill0 starsChanged 6 months agoMITView on GitHub

Scheduled morning briefing skill. Pulls overnight news, peer moves, regulatory updates, calendar, and top risks into a sub-five-minute read delivered before the working day starts. Designed to run as a daily scheduled task at 07:00 to 07:30 local time.

25 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use meeting-prep.

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.
  • OpenAISkill

    meeting-prep

    Use when creating Public Equity Investing meeting prep briefs. Do not use for private diligence, IB, FP&A, legal, or scheduling-only tasks.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 20 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No filler. If a section is empty today, omit it

    line 57
  2. Distinctive:

    After two weeks of daily briefs, prompt the user:

    line 71

“Common” is measured: kept by at least 6 in 10 of the 20 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

Morning Brief · Scheduled Skill

When to Trigger

  • Scheduled task, runs daily at [[YOUR PREFERRED TIME, typically 07:00]]
  • Manually invoked when the user says: morning brief, daily brief, start my day, briefing

What Goes In

Configure your sources by replacing placeholders:

  • News connectors: [[YOUR NEWS MCP, e.g., a curated RSS, web fetch of trusted sources]]
  • Peer monitoring: [[YOUR PEER LIST, NAMED COMPANIES OR TICKERS]]
  • Regulatory tracking: [[YOUR JURISDICTION-SPECIFIC SOURCES, e.g., EUR-Lex, ESMA, EBA, national DPA]]
  • Calendar connector: [[YOUR CALENDAR MCP, e.g., M365, Google Workspace]]
  • Risk register: [[POINTER TO YOUR INTERNAL RISK LOG]]

What Comes Out

A single-page brief organized as:

1. The headline (one sentence)

What is the most important thing for the user to know today?

2. Peer moves (3 bullets)

  • [[PEER 1]] did X. Implication for us: Y.
  • [[PEER 2]] did X. Implication: Y.
  • [[PEER 3]] did X. Implication: Y.

3. Regulatory radar (only if material)

Anything in the user's jurisdiction or industry that changed yesterday and has a deadline or action implication.

4. Calendar today

  • Three most important meetings, who is in them, and one line each on what the user needs to bring
  • Any meeting where the user is the decision maker is flagged

5. Top three risks

From the risk register, the three items closest to triggering. New developments highlighted.

6. Quick wins

One or two things the user could close out before noon today that have been sitting too long.

Style

  • Three minutes to read, max
  • Plain language, no jargon unless it is the user's own jargon
  • Numbers always sourced
  • No filler. If a section is empty today, omit it

Scheduled Task Configuration

Schedule: daily at 07:00 (user's timezone)
Output: deliver to user's preferred channel (email, Teams DM, Slack DM)
Failure mode: if a source is unreachable, deliver what is available and flag the gap
Memory: store the brief for retro review
Privacy: never include personal data of others; never include market-sensitive material before publication

Iteration

After two weeks of daily briefs, prompt the user:

  • Which sections do you skip every time? Remove them.
  • Which sections do you re-read? Expand them.
  • What did you wish was in the brief but was not? Add a source.

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.

Check your setup, free