agentleFS
scribemailscribemail/claude-plugin/skills/workspace-audit/SKILL.md

workspace-audit

Skill0 starsChanged 32 days agoMITView on GitHub

Sweep a Scribe workspace for problems in one pass (teammates with no signature, failed installations, erroring integrations, unpublished drafts, expired campaigns) and report what to fix first. Use for "audit our signatures", "who's missing a signature", or a health check before a rollout.

3 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

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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. Very specific:

    Keep it short enough to act on.

    line 45

≈ “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

Auditing a Scribe workspace

A read-only sweep. Run the checks, then report findings ranked by how many people they affect, each with the one action that fixes it. Do not make changes as part of an audit — propose them.

The sweep

  1. Workspace and plan — get_workspace: plan (tier, status, billing interval), seat_count (what is invoiced), and event_tracking. A past-due plan or a plan without installation explains failures that look technical.
  2. Integration health — list_integrations: any status: "error" row, with error_message and error_since. This is the highest-leverage finding — a broken integration silently blocks every install behind it.
  3. Coverage — list_emails (with auto_paginate) against list_signature_recipients for each signature from list_signatures. Addresses in the first set and none of the second have no signature at all. Report them grouped by teammate, not as a flat list of aliases.
  4. Installation failures — list_signature_installations with status: "failed". Group by error_code: a wall of user_not_found is one directory problem, not fifty tickets.
  5. Unpublished work — signatures whose last_published_at is null or older than their last edit have drafts nobody can see. Flag them; publishing is the user's call.
  6. Campaigns — list_marketing_campaigns: drafts that were never scheduled, and active campaigns whose end_time has passed.
  7. Field hygiene (optional, when the ask is broader) — list_smart_fields plus list_teammates to spot fields that are empty for most of the team, which render as blank lines in every signature.

Reporting

Lead with the count and the fix, not the method:

3 integrations erroring — Microsoft 365 has been failing since 12 Aug (invalid_grant); 41 of 48 failed installs trace to it. Reconnect it first.

7 teammates with no signature — Ana, Ben, … Assign them the "Company Default" template, or set assign_to_all_future_emails on it so new joiners are covered.

2 unpublished drafts — "Sales EMEA" was edited 3 days ago and never published.

Keep it short enough to act on. Offer to fix the top item, and get explicit confirmation before any write. For product questions raised by the findings, use search_docs / read_docs_page rather than answering from memory.

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.