agentleFS
jelbirtjelbirt/LLM-Skill-Build/digest/SKILL.md

digest

Skill1 starsChanged 3 months agoApache-2.0View on GitHub

Produce a cross-project status digest - a short, decisions-first brief synthesized from each repo's worktrees, branches, open PRs, CI state, and todo/state docs, ordered by what needs the reader's attention. Use whenever the user wants a status digest, weekly brief, Monday brief, standup summary, or cross-project status, says "digest", "weekly digest", "status brief", "what moved last week", or "where does everything stand", or when a scheduled digest run fires. Read-only - it never commits, writes files, or mutates any repo.

33 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use aeon-update, auto-workflow and 10 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.
  • aaronjmarsSkill

    aeon-update

    Pull framework updates from the upstream Aeon repo into this instance - 3-way merges canon's new commits into a PR, never clobbering operator config.

    Also in 4 projects that use this

  • aaronjmarsSkill

    auto-workflow

    Two-mode aeon.yml workflow builder - analyze inspects URLs and emits a tiered, signal-verified skill-enablement plan plus an aeon.yml diff; enable flips slugs to enabled:true and opens a PR.

    Also in 4 projects that use this

  • +10 more from aaronjmars

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 29 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    If $ARGUMENTS names a repo, a parent directory, or a focus area, use it.

    line 16
  2. Very specific:

    If the user has a multi-repo status helper on PATH, prefer it.

    line 26
  3. Distinctive:

    Do not write files and do not commit anything.

    line 56

“Common” is measured: kept by at least 6 in 10 of the 29 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

digest

One tight brief answering three questions: what moved recently, what is waiting on the reader, and what is at risk of being forgotten. Lead with what needs their attention, not with inventory.

1. Pick the scope

  • If $ARGUMENTS names a repo, a parent directory, or a focus area, use it.
  • Else if the working directory is inside a git repo, digest that repo.
  • Else find candidate repos one or two levels below the working directory (directories containing .git), and list what you found before digesting more than a handful.

2. Collect — read-only, never mutate anything during a digest

  1. Per repo: git worktree list plus git -C {dir} status --porcelain and ahead/behind counts for each worktree — branch, clean or DIRTY, drift. If the user has a multi-repo status helper on PATH, prefer it.
  2. Per repo with a GitHub remote: gh pr list --state open (age, CI state, review state) and gh pr list --state merged --limit 10 filtered to the digest window (default: last 7 days). Note anything red or stuck.
  3. Per repo: the todo or state doc its CLAUDE.md points at (e.g. tasks/todo.md) — open gates, in-progress items, "awaiting owner" markers. Plus git log --oneline --since='7 days ago' on the default branch for what actually landed.
  4. Skip repos with no activity in the window rather than reporting silence.

3. Compose — decisions-first, one screen

Order by what the reader should act on, not by repo:

  1. Waiting on you — open gates, PRs awaiting review, unanswered questions. Each with a one-line "what happens once you decide."
  2. Moved recently — merged PRs, closed gates, landed milestones; one line each naming the decision it embodied, not the file list.
  3. In flight — active workstreams and where each stands; flag worktrees that look abandoned (dirty with no commits in the window).
  4. Risks / drift — stale branches, red or stuck CI, worktrees ahead of origin but unpushed, anything promised in a todo doc but untouched.

Omit empty categories rather than padding them. Keep the whole digest under ~40 lines. No disclaimers or footers.

4. Deliver

Print the digest directly in chat. If the invocation came from a scheduled run whose instructions name another delivery channel, use that channel too. Do not write files and do not commit anything.

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.

Reviews can't be read right now.

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.