agentleFS
madeordinarymadeordinary/serel-memory/.claude/skills/weekly-update/SKILL.md

weekly-update

Skill1 starsChanged 18 days agoMITView on GitHub

Draft a stakeholder-ready weekly update from the memory bank and recent activity. Use when the user asks for a weekly update, status report, stakeholder summary, or progress email.

7 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

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Run git log --since="1 week ago" --oneline --all for recent activity.

    line 19
  2. Distinctive:

    Run git status to see current uncommitted work.

    line 20
  3. Distinctive:

    Keep each bullet to one line.

    line 59
  4. Distinctive:

    If a section has nothing to report, write "(none)" rather than omitting the section.

    line 63
  5. Distinctive:

    After generating the draft, ask the user:

    line 66

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

Weekly Update

Draft a weekly update suitable for stakeholders, pulling from the memory bank and recent git activity. The output should be skimmable in 30 seconds.

Scope: resolve which bank this targets per "Resolving scope" in docs/workflow-contract.md — an optional --scope <path> argument selects a project bank when the repo configures scopes; otherwise the root bank, as always.

Workflow

  1. Read:
    • memory-bank/projectbrief.md — what this project is
    • memory-bank/activeContext.md — current focus and open questions
    • memory-bank/progress.md — what works and what's in progress
    • memory-bank/decisionLog.md — decisions made or changed this week
  2. Run git log --since="1 week ago" --oneline --all for recent activity.
  3. Run git status to see current uncommitted work.

Output

Produce an update in this structure:

# [Project name] — Week of [Mon DD, YYYY]

## Headline
[One sentence — the most important thing a stakeholder should know about this week.]

## Shipped this week
- [completed item — what it does, why it matters]
- [completed item]

## In progress
- [active work — what's being built, expected completion if known]
- [active work]

## Up next
- [planned next — what we're picking up next, why]
- [planned next]

## Risks and open questions
- [risk or unresolved decision — impact, what's needed to resolve]
- [risk]

## Decisions
- [decision made or changed this week — why it matters]
- (or write "None this week")

## Asks
- [anything needed from stakeholders — decisions, resources, feedback]
- (or write "None this week")

Rules

  • Keep each bullet to one line. If something needs more, it belongs in a separate doc with a link from the update.
  • "Shipped" means done and verifiable. Don't conflate intent with completion.
  • "Risks" should be specific. "Things might be hard" is not a risk. "External API rate limits could block X by Y date unless we get a quota increase" is.
  • "Decisions" should be durable choices, not normal task progress.
  • If a section has nothing to report, write "(none)" rather than omitting the section. Empty sections are signal too — they tell the reader you considered it.
  • This is a stakeholder document, not an engineering log. Skip technical detail unless a stakeholder needs to know it. If a teammate would need more detail, mention there's a longer doc available.

After generating the draft, ask the user:

  • Is the headline the right one for this audience?
  • Tighter, longer, or about right?
  • Format for a specific channel (Slack, email, Confluence) or keep generic?

Revise based on their answer. Then stop.

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.