agentleFS
The-AI-ThinkerThe-AI-Thinker/claude-code-pm-starter/.claude/skills/status-update/SKILL.md

status-update

Skill13 starsChanged 3 months agoMITView on GitHub

Draft the user's status update from the active project's tasks.md and recent notes in operations/. Use when the user needs to report progress to their team, their manager, or stakeholders.

11 other projects use a version of this.

Adopted by

Most recently taken up by

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 11 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:

    Find the state: Read the active project's tasks.md (Status notes first, then Now / Next / Blocked) and any operations/ notes dated since …

    line 12
  2. Distinctive:

    Every claim of progress points at something real: a merged change, a decision made, a number moved, a meeting outcome.

    line 23
  3. Very specific:

    After the user approves the draft, update tasks.md's Status notes so the next update starts from today's truth.

    line 25

“Common” is measured: kept by at least 6 in 10 of the 11 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

Status update

Draft the update the user owes someone, from files, not from their memory.

Steps

  1. Find the state. Read the active project's tasks.md (Status notes first, then Now / Next / Blocked) and any operations/ notes dated since the last update. If several projects are active, ask which ones the update covers.
  2. Ask two things only: who the update is for, and where it will be posted (email, Slack, a doc). Skip the questions if the conversation already says.
  3. Draft it in the user's voice per context/preferences.md. Default shape, unless preferences say otherwise:
    • One line on the headline: the single most important thing that moved or didn't.
    • What shipped or progressed, with the concrete result.
    • What's blocked, with the specific ask that would unblock it. An update without an ask is a diary entry.
    • What's next.
  4. Match the channel. Slack gets short lines and no headings; email gets a subject line; a doc gets the full shape.

Rules

  • Every claim of progress points at something real: a merged change, a decision made, a number moved, a meeting outcome. No "good progress on X".
  • Blockers name the blocker, not just the feeling. "Waiting on legal's read of the data clause since the 12th" beats "legal is slow".
  • After the user approves the draft, update tasks.md's Status notes so the next update starts from today's truth.

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.