agentleFS
MicrosoftKnown publishermicrosoft/aibast-agents-library/solutions/building-permit-processing/manual/skills/aibast_permit-backlog_bp01/SKILL.md

permit-backlog-and-complaint-risk

Skill8 starsChanged 3 months agoMITView on GitHub

Use for department-wide delay, statutory-clock, backlog, and likely-status-call questions; ranks every open synthetic permit and identifies the first intervention.

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill for questions such as "what has been sitting too long," "what is overdue," "who will complain or call first," or "where …

    line 8
  2. Distinctive:

    Use a compact table if reporting the full backlog.

    line 39
  3. Distinctive:

    Never recalculate ages from today's date and never change a permit state.

    line 41

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
<!-- bic:source=blank -->

Permit backlog and complaint risk

Use this skill for questions such as "what has been sitting too long," "what is overdue," "who will complain or call first," or "where should the director intervene." No permit ID is required.

Fixed snapshot result

Work from the 2026-08-07 synthetic snapshot. Exclude approved BP-2025-0102. There are 5 open applications and 3 are overdue. Rank them:

  1. BP-2025-0104 — Metro School District — 63 days old against 45 days, 18 days overdue, correction cycle 3, complaint risk 100/100.
  2. BP-2025-0101 — Greenfield Development LLC — 48 days old against 30 days, 18 days overdue, cycle 2, complaint risk 66/100.
  3. BP-2025-0103 — Sunrise Solar Inc. — 26 days old against 21 days, 5 days overdue, cycle 1, complaint risk 25/100.
  4. BP-2025-0105 — Greenfield Development LLC — 3 days old, on track, complaint risk 0/100.
  5. BP-2025-0106 — Ridgeline Restaurants Inc. — 1 day old, on track, complaint risk 0/100.

Procedure

  1. Lead with BP-2025-0104 and Metro School District as the hottest issue and the applicant most likely to call first.
  2. Explain that it is 18 days overdue, is in correction cycle 3, and is with Tom Delgado.
  3. Recommend that an authorized reviewer draft the cycle-3 correction list and choose a specific re-review date. Do not claim the update was sent or direct staff to communicate, issue, escalate, or change anything.
  4. Name BP-2025-0101 as the second intervention and BP-2025-0103 as the remaining overdue application.
  5. Use a compact table if reporting the full backlog.

Never recalculate ages from today's date and never change a permit state.

For the locked Preview prompt, search for BPP-01 Locked Response in the synthetic permit records and reproduce it verbatim. Do not rewrite, expand, summarize, or supplement it.

End with: > Synthetic pilot data as of 2026-08-07; no live municipal system was accessed or changed.

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.