agentleFS
mariagorskikhmariagorskikh/open-instinct/skills/daily-brief/SKILL.md

daily-brief

Skill428 starsChanged 31 days agoMITView on GitHub

Proactive morning text for the owner. Use when a scheduled job says to run the daily brief, when the owner asks "what's my day", or when setting up or changing the morning text. Pulls weather, today's calendar, unread mail that matters, open threads and pending approvals into one short message. Created with schedule_create during onboarding.

30 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use weekly-review, setup 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

  • VercelSkill

    setup

    Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".

    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

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

  • 0

    Common

    Most of the 23 edited versions we read keep these.

  • 6

    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:

    Do these in order; skip any source that is not connected and do not mention the gap unless the owner has asked for it before.

    line 22
  2. Distinctive:

    If the owner already texted you this morning before the job fires, fold the brief into that thread instead of sending a second text.

    line 58
  3. Distinctive:

    Never include the content of other people's messages beyond sender and topic.

    line 60
  4. Distinctive:

    Do not send more than one brief a day unless asked.

    line 70
  5. Distinctive:

    Do not read mail bodies aloud.

    line 71
  6. Distinctive:

    Do not add tasks the owner did not ask for.

    line 72

“Common” is measured: kept by at least 6 in 10 of the 23 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

One text, sent at the time the owner chose, that lets them start the day without opening anything. It is a scheduled run in the owner conversation, so the principal is the owner and all owner tools are available.

Setup

During onboarding, or when asked: schedule_create with a 5-field cron in the owner's timezone and the prompt "Run the daily-brief skill for the owner." Example for 8am Eastern: cron 0 8 * * *, tz America/New_York. Weekdays only is 0 8 * * 1-5. To change the time, schedule_list, schedule_delete the old job, create the new one, and confirm in one line.

Collect

Do these in order; skip any source that is not connected and do not mention the gap unless the owner has asked for it before.

  1. Weather: web_fetch https://wttr.in/<city>?format=3 for a one-line summary, or ?format=j1 for the high, low and rain chance. City from memory.
  2. Calendar: today's events via the calendar app tool. Note the first event's time, anything with a location that needs travel, and video calls.
  3. Mail: unread since yesterday evening that needs a reply or decision (skill email-triage, read step only). Count the rest.
  4. Open threads: memory_read and yesterday's journal for things you are waiting on (a reply from Sam's Instinct, a delivery, a booking hold).
  5. Approvals: anything you asked the owner that is still unanswered. Repeat the ask in one line with the same wording.
  6. Scheduled items for today you created (check-ins, rides) so the owner knows you have them.

Write

4 to 8 lines, plain prose, no markdown, no headings, no emojis unless the owner uses them. Order: greeting with weather, calendar, mail, waiting on, approvals, one offer. Times in the owner's timezone. Skip empty sections. If nothing at all is happening, send two lines.

Agent: Morning, Maria. 61 and clear, rain after 4. Three things today: Lena at 10 on Zoom, dentist at 2:30 on Mass Ave, and dinner with Sam at Nopa, 7pm. Two emails need you, both from the bookstore about the reading date. Still waiting on Priya's Instinct about Saturday brunch. One thing pending: book the JetBlue flight for $412, want me to go ahead? Want me to order a car for the dentist?

Agent: Morning. 48 and grey. Nothing on the calendar and nothing in mail needs you. I'm around if anything comes up.

Quiet rules

  • Respect quiet hours from memory. If the scheduled time falls inside them, do not send; tell the owner once and offer to move the job.
  • If the owner already texted you this morning before the job fires, fold the brief into that thread instead of sending a second text.
  • Never include the content of other people's messages beyond sender and topic.

After sending

journal_append one line: "Daily brief sent, N events, N emails flagged, N approvals open." Do not write to memory from the brief.

Do not

  • Do not send more than one brief a day unless asked.
  • Do not read mail bodies aloud. Sender and ask only.
  • Do not add tasks the owner did not ask for; offers are fine, actions are not.

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.