agentleFS
BenPremBenPrem/business-brain/.claude/skills/daily-brief/SKILL.md

daily-brief

Skill1 starsChanged 3 months agoMITView on GitHub

Start and end every work session with a structured brief and summary. Use when the operator opens a new session, says "good morning", "what should I work on", "daily review", "wrap up", "end of day", "session summary", or seems unsure what to focus on. Also use on Fridays or on "weekly review". Reads context files, checks records and the task system, and keeps the session on the north star from context/current-priorities.md.

31 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use weekly-review, onboarding and 2 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

  • AnthropicSkill

    onboarding

    Generate an onboarding checklist and first-week plan for a new hire. Use when someone has a start date coming up, building the pre-start task list (accounts, equipment, buddy), scheduling Day 1 and Week 1, or setting 30/60/90-day goals for a new team member.

    Also in 3 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

5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 24 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read active client and venture records (clients/*/_index.md, ventures/*/)

    line 25
  2. Distinctive:

    Check <TASK SYSTEM> for tasks due today, replies waiting, proposals outstanding

    line 26
  3. Very specific:

    Use _templates/session-summary.md as the structure.

    line 66
  4. Very specific:

    Update context/current-priorities.md if priorities shifted

    line 78
  5. Distinctive:

    Read each file from this week.

    line 94

“Common” is measured: kept by at least 6 in 10 of the 24 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

Structure every session: priorities at the start, progress captured at the end.

When to use

  • A new session starts, or the operator asks anything like "what should I do?"
  • "wrap up", "done for today", "end of day"
  • "weekly review", or it's Friday

Session Start

1. Read context files (in this order)

  1. context/current-priorities.md — the north star; wins any conflict
  2. Other context/*.md files that exist (goals, business details)
  3. decisions/log.md — last 5 entries

2. Check records + task system

  • Read active client and venture records (clients/*/_index.md, ventures/*/)
  • Check <TASK SYSTEM> for tasks due today, replies waiting, proposals outstanding
  • Records are durable context; <TASK SYSTEM> is live execution state

3. Present the brief

Morning brief — [Date]
======================

REVENUE ACTIONS (do first):
  1. [Highest-leverage revenue task]
  2. [Second]

CLIENT WORK DUE:
  • <CLIENT>: [deliverable] — due [date]

PIPELINE:
  • [X] follow-ups due today
  • [X] proposals outstanding
  • [X] replies waiting

BUILD QUEUE (after revenue work):
  • [Next system/skill from current-priorities.md]

NORTH STAR:
  [Quote the #1 priority verbatim from context/current-priorities.md.
   Never hardcode numbers here — the files are the source of truth.]
  Gap: [what's blocking it / what closes it fastest]

4. Confirm

"Does this look right, or do you want to shift focus?" If the operator overrides the priority, support it — but note what's being deferred so nothing falls through.


Session End

On "wrap up", "done", "end of day":

1. Generate the session summary

Use _templates/session-summary.md as the structure. Cover:

  • Completed — what actually shipped (verified, not just attempted)
  • In Progress — what's left to finish
  • Decisions Made — each one appended to decisions/log.md
  • Blockers — what's stuck, and on whom
  • Next Session Priority — top 1-2 tasks to open with
  • Learned Rules Added — any new rules, or "None"

2. Update files

  • Append decisions to decisions/log.md: [YYYY-MM-DD] DECISION: ... | REASONING: ... | CONTEXT: ...
  • Route corrections per the routing doctrine (hook / script / skill edit / short rule — never blind-append)
  • Update context/current-priorities.md if priorities shifted

3. Save the summary

mkdir -p archives/sessions

Save to archives/sessions/[YYYY-MM-DD]-session.md.


Weekly Review (Fridays or on request)

1. Read the week's session summaries

ls archives/sessions/

Read each file from this week.

2. Generate the review

# Weekly Review — Week of [Date]

## Revenue
- Deals closed / payments collected / proposals sent / calls held / new leads
  (pull real numbers from records — never estimate)

## Client Work
- [What was delivered this week]

## Build Progress
- [Skills or systems built or refined]

## What Worked
- [Keep doing]

## What Didn't
- [Stop or change]

## Next Week Focus
1. [Priority 1]
2. [Priority 2]
3. [Priority 3]

Also run the productization hook: "What did you build this week that isn't in the product journal?" — log candidates via the productization-journal skill.

3. Save

mkdir -p archives/reviews

Save to archives/reviews/[YYYY]-W[XX]-review.md.


Priority Logic

Rank brief items with this hierarchy — context/current-priorities.md always wins on conflict:

  1. Flagship client deliverables — the signed top-tier account beats everything
  2. Billing / AR — invoices due, payments to collect, billing risk
  3. Pipeline — hot replies, proposals outstanding, follow-ups due
  4. Outreach — only if the lane is active in current-priorities.md
  5. Build skills/systems — important, never at the expense of revenue
  6. Admin/setup — lowest, unless it blocks something above

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.