agentleFS
Sign inStart free
shipkitlabsshipkitlabs/client-delivery-kit/skills/client-update/SKILL.md

client-update

Skill0 starsChanged 2 months agoMITView on GitHub

Write a client-facing progress update from git history for a date range or since the last update. Translates commits into outcomes a non-technical client understands, lists what's next, and surfaces anything blocked on them. Use weekly, at milestones, or whenever a client asks "how's it going?".

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. ARCASSystems/FounderOS★ 7same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    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:

    Group commits into outcomes: Follow references/translation.md.

    line 23
  2. Very specific:

    Map to the scope: If SCOPE.md exists, tag each outcome with the deliverable it advances and estimate percent complete per deliverable.

    line 24
  3. Very specific:

    Find what's blocked: Look for TODO comments added in the range mentioning "client", "waiting", "need", "pending".

    line 25
  4. Distinctive:

    Never paste commit messages.

    line 32
  5. Distinctive:

    Never include file names, function names, branch names, or technical nouns the client didn't use themselves.

    line 33
  6. Distinctive:

    If nothing shipped in the period, say so and say why.

    line 36

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

/client-update — git history to client progress update

Output: UPDATE-{YYYY-MM-DD}.md in an updates/ folder (create it), plus the same text printed so it can be pasted into email or Slack.

Input

$ARGUMENTS may include:

  • A range: since=2026-09-01, since="last monday", since=v1.2.0, since=last (meaning: since the newest file in updates/). Default: since the newest file in updates/, or the last 7 days if none.
  • to= an end date (default now).
  • --format email|slack|doc (default email).
  • --milestone "Name" to frame the update around a milestone from the scope.
  • --blockers "text" anything you know is blocked that git won't show.
  • --next "text" to override the next-steps section.

Process

  1. Pull the history. git log --since=… --until=… --no-merges --format="%h%x09%ad%x09%s%x09%b" --date=short, plus git diff --stat across the range for a sense of where the work landed. If the repo has multiple authors, include all of them; this is a team update, not a personal one.
  2. Group commits into outcomes. Follow references/translation.md. The client doesn't want 23 commits; they want 3–6 things that are now true that weren't before. Merge related commits. Drop pure refactors, formatting, CI fiddling, and dependency bumps unless they matter to the client (security fix, performance).
  3. Map to the scope. If SCOPE.md exists, tag each outcome with the deliverable it advances and estimate percent complete per deliverable. Be conservative. "Done" means demonstrable and QA'd, not "code is written".
  4. Find what's blocked. Look for TODO comments added in the range mentioning "client", "waiting", "need", "pending". Combine with --blockers. Each blocker names who owns the next action.
  5. Write next steps. 2–4 items, concrete, for the coming period. Pull from the scope's next milestone unless --next is given.
  6. Write the update from references/update-template.md in the requested format, following references/tone.md.
  7. Print it. Then a one-line note to the user about anything you weren't sure how to phrase.

Rules

  • Never paste commit messages. Translate every one.
  • Never include file names, function names, branch names, or technical nouns the client didn't use themselves. "The database" is fine. "The Prisma migration" is not.
  • Percent-complete is per deliverable, never for the whole project (whole-project percentages create false precision and get quoted back at you).
  • Bad news goes in the update, near the top, with what you're doing about it. Surprises at delivery cost more than honesty now.
  • If nothing shipped in the period, say so and say why. An honest "we were blocked on X" is a normal update.
  • Under 250 words for email and Slack. Under 500 for doc format.

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