agentleFS
Sign inStart free
prosyo-aiprosyo-ai/gtm-skill/skills/crm-hygiene-audit/SKILL.md

crm-hygiene-audit

Skill13 starsChanged 24 days agoMITView on GitHub

Use this skill when CRM data is messy and reports cannot be trusted: \"audit our CRM\", \"clean up our CRM data\", \"duplicates and missing fields\", \"why is our pipeline report wrong\". Checks duplicates, missing required fields, stale and past-due opportunities, ownership gaps, lifecycle stage errors, bad picklist values and unlinked records, quantifies each issue, ranks them by impact on reporting and selling, and produces a cleanup plan plus the rules that stop the mess coming back. Proposes changes for approval, never bulk-edits on its own.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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 when the pipeline report and reality disagree.

    line 16
  2. Distinctive:

    Every issue has a count and an impact, not just "data is messy".

    line 59
  3. Distinctive:

    MUST export a backup before any bulk change.

    line 66
  4. Distinctive:

    MUST get approval with a sample before merges, deletions or bulk updates.

    line 67
  5. Distinctive:

    MUST fix opted-out contacts in active sequences immediately.

    line 68
  6. Distinctive:

    NEVER permanently delete records without explicit approval.

    line 69

≈ “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

Use this when the pipeline report and reality disagree. It produces a ranked list of data problems, a cleanup plan and the rules that keep data clean afterwards.

Inputs

  • Exports of accounts, contacts and opportunities (or read access).
  • The fields and stages the business relies on.
  • The reports leadership uses, so impact can be judged.

The play

1. Inventory issues

AreaCheck
DuplicatesAccounts by domain; contacts by email; similar names
CompletenessRequired fields empty: industry, size, owner, lifecycle stage, source
OpportunitiesPast close dates, no next step, no activity in 30 days, amount empty or zero, stage without required fields
OwnershipRecords owned by former employees or unassigned
LifecycleCustomers without closed-won deals; leads with won deals
PicklistsFree-text values where picklists should be; outdated values
RelationshipsContacts not linked to accounts; deals without contacts
ComplianceOpted-out contacts still in active sequences

2. Quantify and rank

Count each issue and score impact: does it break forecasting, routing, outreach or compliance? Compliance and forecast issues come first.

3. Plan the cleanup

For each issue: the fix, who decides (some merges need a human), whether it can be done in bulk safely, and the order. Merges and deletions are proposed with a sample for approval, then run in batches with a backup export first.

4. Prevent recurrence

Required fields at stage changes, validation rules, duplicate checks on create, ownership reassignment when people leave, a monthly hygiene report.

Output format

Health score: X/100
Issues (ranked): <issue - count - % of records - impact - fix - bulk-safe? - owner>
Cleanup plan: <week by week, with approval points>
Prevention: <rules to add>
Monthly report: <metrics to track>

What good looks like

  • Every issue has a count and an impact, not just "data is messy".
  • Opt-out compliance issues are fixed first.
  • The prevention rules are light enough that reps follow them.
  • The common mistake is a one-time cleanup sprint with no rules, so the data is dirty again in a quarter.

Rules

  • MUST export a backup before any bulk change.
  • MUST get approval with a sample before merges, deletions or bulk updates.
  • MUST fix opted-out contacts in active sequences immediately.
  • NEVER permanently delete records without explicit approval.

Example prompts

  • "Audit these CRM exports and tell me what's wrong, ranked by impact."
  • "Our forecast is off every month. Check our opportunity data."
  • "Write the hygiene rules and monthly report for our CRM."

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.

Check your setup, free