agentleFS
DATA-AI-XYZDATA-AI-XYZ/Tandem/skills/weekly-monitor/SKILL.md

weekly-monitor

Skill0 starsChanged 6 months agoMITView on GitHub

Weekly MONITOR update (Friday cadence). Use when the user asks for a weekly review, end-of-week summary, monitor update, or weekly cadence. Computes the 7-day delta, updates MONITOR.md with revision history, flags stalled/blocked stories, runs backlog hygiene, regenerates the dashboard.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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:

    Run npm run pm:all (validator + dashboard together).

    line 49
  2. Distinctive:

    If validator fails, fix the violations BEFORE the dashboard run.

    line 51
  3. Very specific:

    If the Stop hook is active, the dashboard will also regen at session end — but running it explicitly here is cheap insurance.

    line 52

≈ “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

Tandem: weekly-monitor (PM hat)

Operate as PM hat. Friday 30-minute weekly review.

Load into context

  • _00-Project-Management/42-Monitor/MONITOR.md (current state)
  • _00-Project-Management/12-Active/ACTIVE.md
  • Last 7 days of activity — scan which files under 30-Epics/, 31-Features/, 32-Stories/, 34-Bugs/, 40-Decisions/ have completed_at or started_at within the last 7 days. For a multi-folder scan, delegate to an Explore agent (SOP §18) and ingest the summary, not the raw paths.
  • _00-Project-Management/14-Retros/ (most recent retro's "One change" — did it happen this week?)
  • _00-Project-Management/90-Standards/SOP.md

Task

1. Compute the weekly delta

  • Stories shipped (status → done in the last 7 days)
  • Stories started (status → in-progress in the last 7 days)
  • Stories currently blocked
  • BUGs filed
  • BUGs fixed
  • ADRs created

2. Update 42-Monitor/MONITOR.md

  • Per-epic and per-feature counts (shipped / total).
  • Progress bars (if used).
  • "Last updated" date.
  • Prepend a revision-history entry dated today, summarising the week in 3-5 lines.

3. Audit currents

  • Any story in-progress for > 5 days? Flag as stall risk.
  • Any story blocked for > 5 days? Escalate — Founder hat decision needed?
  • Any story in-review for > 3 days? Push to close-out (/tandem:close-out-story).

4. Backlog hygiene

  • Anything in not-started for > 90 days? Propose wontfix or archived (SOP §15 sunset rule).
  • Inbox count > 20? Propose a quick triage pass.

5. Dashboard regen

  • Run npm run pm:all (validator + dashboard together).
  • Confirm 42-Monitor/DASHBOARD.html reflects the week's changes.
  • If validator fails, fix the violations BEFORE the dashboard run.
  • If the Stop hook is active, the dashboard will also regen at session end — but running it explicitly here is cheap insurance.

Output rules

  • Single revision-history entry per week, prepended to MONITOR.
  • Format: **YYYY-MM-DD — week summary.** <3-5 lines>.
  • Be specific. Not "shipped some stories", but "shipped STORY-01.2.07 + STORY-01.3.01, closing FEAT-01.2 except for the sortable-headers AC".
  • Flag carry-forwards: "carrying STORY-02.1.04 into next week — blocked on ADR-0012."

Non-negotiable rules from CLAUDE.md

  • Frontmatter timestamps — do NOT modify any artefact's timestamps as part of this update. Only MONITOR's "Last updated" line changes.
  • Status enum — use canonical statuses in your summary, never synonyms.
  • Dashboard regen at end of update.

End-of-update summary (always emit)

  • Shipped this week: N
  • Stalled: <list of stories in-progress > 5 days>
  • Blocked: <list with reasons>
  • Carry-forward to next week: <list>
  • Suggestion for Founder hat: <if any strategic drift detected>

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.