agentleFS
craigcossairtcraigcossairt/trellis/.claude/skills/daily-brief/SKILL.md

daily-brief

Skill5 starsChanged 12 days agoMITView on GitHub

Start-of-day ranked brief - open issues, recent commits, work in progress, and anything waiting on a human decision. Use when asked for a 'daily brief', 'morning brief', 'what should I work on today', 'start my day', 'catch me up'.

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 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

  • 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

  • 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

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

  • 0

    Common

    Most of the 24 edited versions we read keep these.

  • 3

    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:

    Optional signals: - IF other MCP servers are connected (email, analytics, error tracking), pull their top items.

    line 18
  2. Distinctive:

    Keep the whole brief under ~30 lines:

    line 34
  3. Distinctive:

    If the project has no tracker and no recent commits, say so and suggest the single most useful next step instead of inventing a board.

    line 57

“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

You are producing the day's brief: a ranked answer to "what should I work on today?" grounded in the project's actual state, not vibes.

Gather (use what exists, skip what doesn't - never fail on a missing source)

  1. Git state - commits since yesterday (git log --since=yesterday --oneline --all), current branch, uncommitted changes, unpushed commits, open PRs (gh pr list).
  2. Open issues - gh issue list (or the project's tracker via its MCP server if one is connected - check AGENTS.md for which tracker this project uses).
  3. Project docs - the 5 newest entries in docs/decision-log.md and any gotchas added in the last week, for context on where the project's head is.
  4. Optional signals - IF other MCP servers are connected (email, analytics, error tracking), pull their top items. Never error or nag about sources that aren't connected; a git-only brief is still a good brief.

Rank

Score candidate work by, in order:

  1. Unblocks something - work that other work (or a person) is waiting on
  2. Deadline proximity - anything dated
  3. Momentum - in-progress work close to done beats starting something new
  4. Quick wins - under-30-minute items worth batching

Flag separately anything that needs a HUMAN decision before an agent can act on it.

Output format

Keep the whole brief under ~30 lines:

# Daily Brief - {date}

## Recommended focus (top 3)
1. {item} - {one-line why it's ranked here}
2. ...
3. ...

## Needs your decision
- {item} - {what's blocked on the human}   (omit section if empty)

## Also on the board
- {compressed list of remaining open items}

## Since yesterday
- {commits/PRs merged, one line each}

Notes

  • Be opinionated in the ranking - a brief that lists everything equally decides nothing.
  • If the project has no tracker and no recent commits, say so and suggest the single most useful next step instead of inventing a board.
  • This skill can be scheduled (e.g. a daily task that runs it and saves the output) - see your harness's scheduling features. Start by running it manually; schedule it once you trust it.

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.