Menu

Individual skill

governed-crm-cleanup

0upvotes

Use this skill when CRM data is unreliable, a cleanup is overdue, or a team is considering a bulk correction. Produces an evidence-backed audit, a reviewable change plan, approved corrections, and controls that prevent the same defects from returning.

skills/ryan-iyengar/governed-crm-cleanup/SKILL.md

Read pinned source

Source commit 5d786aad0c7b2ca59b1abf1f601f9407ca261996

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Instructions only
Last checked
Nov 11, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
237
Repository last updated
Oct 20, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

Use this when CRM defects affect routing, reporting, pipeline reviews, or execution. Produce a baseline, an operation-level correction plan, a verified result, and a prevention backlog.

## Establish the baseline

1. Snapshot the affected objects, field definitions, owners, pipeline stages, and automation rules before proposing changes. Record the extraction time and record counts.
2. Define each audit check as an explicit rule with a target population, condition, severity, and evidence. Cover duplicates, ownership gaps, stale pipeline, critical-field completeness, stage conformance, and integration drift.
3. Count findings by object, rule, owner, source, and age. Separate isolated bad records from systematic failures created by imports, forms, integrations, or team behavior.
4. Preserve ambiguous findings. An audit should expose uncertainty rather than convert it into a confident correction.

Use [references/audit-rubric.md](references/audit-rubric.md) to score severity and choose the first batch.

## Build the change plan

Represent every proposed change as one reviewable operation containing:
Back to top