agentleFS
carlosbuelvas1carlosbuelvas1/openclaw-skills/approved-backlog-watchdog/SKILL.md

approved-backlog-watchdog

Skill0 starsChanged 6 months agoMITView on GitHub

Detect approved content items that have been sitting unpublished for over 24 hours and emit escalation alerts. Use when checking whether the content pipeline has stalled — specifically when approved articles, content runs, or deliverables are not moving to shipped/distributed status within the expected window.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 8 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    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. Distinctive:

    When asked "is anything stuck in the pipeline?" or "what's been approved but not shipped?"

    line 13
  2. Distinctive:

    Before distribution planning sessions.

    line 14
  3. Distinctive:

    Does not publish, distribute, or modify any content.

    line 26
  4. Distinctive:

    Does not send messages to external channels (Telegram, email, etc.).

    line 27
  5. Distinctive:

    Does not install or fetch anything from the network.

    line 28
  6. Distinctive:

    Does not trigger other skills or agents.

    line 29
  7. Distinctive:

    If no items are stalled, output:

    line 47
  8. Distinctive:

    If data files are empty or missing, report pipeline clear — do not error.

    line 62
  9. Very specific:

    If updatedAt is missing, treat as unknown age and flag for manual review.

    line 63

≈ “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

Approved Backlog Watchdog

Scans the Mission Control data stores for approved items that have not progressed to shipped/distributed within 24 hours. Emits a structured alert per stalled item.

When to Use

  • Periodic pipeline health check (manual trigger or cron).
  • When asked "is anything stuck in the pipeline?" or "what's been approved but not shipped?"
  • Before distribution planning sessions.

What This Skill Does

  1. Reads data/approvals.json for items with status: 'approved'.
  2. Reads data/articles.json for articles with stage: 'approved' or review.verdict: 'approved'.
  3. Reads data/content-runs.json for runs with status: 'ready' or status: 'approved'.
  4. For each item, checks if updatedAt is more than 24 hours ago.
  5. Emits one alert per stalled item with: id, title, age, current status, recommended action.

What This Skill Does NOT Do

  • Does not publish, distribute, or modify any content.
  • Does not send messages to external channels (Telegram, email, etc.).
  • Does not install or fetch anything from the network.
  • Does not trigger other skills or agents.

Output Format

## Backlog Watchdog Alert — [date]

[X] items stalled beyond 24h:

### [item title]
- ID: [id]
- Type: [approval | article | content-run]
- Status: [current status]
- Age: [Xd Xh]
- Last updated: [timestamp]
- Recommended: [escalate | assign | deprioritize]

If no items are stalled, output:

✅ Pipeline clear — 0 items stalled beyond 24h.

Acceptance Test

  • Given data/articles.json contains one article with stage: 'approved' and updatedAt set to 30 hours ago.
  • When the skill is invoked.
  • Then output includes exactly one alert for that article with age > 24h and recommended action.
  • Pass: alert present, age correct, no false positives from non-approved items.

Edge Cases

  • If data files are empty or missing, report pipeline clear — do not error.
  • If updatedAt is missing, treat as unknown age and flag for manual review.
  • Ignore items with status: 'rejected' or stage: 'retired'.

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.