agentleFS
cacardinalcacardinal/laila/.claude/skills/domain-hygiene/SKILL.md

domain-hygiene

Skill1 starsChanged 4 months agoMITView on GitHub

Scan all domain status files for stale content (stale "Last updated" headers, past-due checkboxes, past-due status-table rows). Surfaces a consolidated list so Alex can give one-line facts and Laila batch-updates the files.

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Run the scan and show the report: markdown grouped by domain, ordered by staleness.

    line 25
  2. Very specific:

    Ask one-line questions per domain: "For career — conference follow-up (Apr 15), portfolio refresh (Apr 16), Q1 networking goal (Mar 31): …

    line 31
  3. Distinctive:

    Default 30 days. The Friday daily-brief uses 30 days.

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Domain Hygiene Skill

Domain tracking/status.md files drift because nothing prompts a review. This skill scans them weekly (via the daily-brief on Fridays) or on-demand and surfaces stale items for batch cleanup.

Scanner

Walk every domains/*/tracking/status.md (plus any Next_Actions.md a domain keeps) and flag:

  1. Stale header — Last updated: date older than the threshold (default 30 days)
  2. Past-due checkbox — unchecked [ ] with an explicit deadline marker (by, due, deadline, target) pointing to a past date
  3. Past-due status row — table row with a status cell of Not Started / Pending / In Progress / Planned and a past date in the row

Status-keyword matching is exact-cell (not substring) to avoid false positives. The scan can be done directly with Read/Grep over the four domains, or via a helper script if you add one (e.g. scripts/domain-status-hygiene.py emitting the same findings as JSON for other skills to consume).

Usage

/domain-hygiene or /domain-hygiene scan

Run the scan and show the report: markdown grouped by domain, ordered by staleness.

/domain-hygiene cleanup

  1. Run the scan
  2. Present the flagged list to Alex in a compact form
  3. Ask one-line questions per domain: "For career — conference follow-up (Apr 15), portfolio refresh (Apr 16), Q1 networking goal (Mar 31): which are done / moved / killed?"
  4. Batch-apply updates to the status files (mark [x], change status columns to Complete / Killed / bump the date, etc.)
  5. Bump Last updated: headers on touched files

The pattern is reply-driven cleanup: Alex gives facts, Laila edits.

Threshold

Default 30 days. The Friday daily-brief uses 30 days; ad-hoc invocations can use a tighter threshold (e.g. 14 days) when asked.

When to invoke proactively

  • Fridays during the daily brief — auto-include findings in the Infrastructure section (see the daily-brief skill, step 11b)
  • After a quarter boundary — quarter ends often leave lots of "Not Started" quarterly goals that should be killed or rolled forward
  • Alex says "are my status files stale?" or "scan my domains"

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.