agentleFS
anmoba99anmoba99/pipedrive-claude-skills/skills/pd-account-health/SKILL.md

pd-account-health

Skill0 starsChanged 32 days agoMITView on GitHub

Account management on Pipedrive organizations: book of business per account manager, health scores, renewals, accounts with only one contact, products similar customers buy, account review (QBR) briefs and sales to customer success handoff. Optional health score saved to an organization field. Use for account health, churn risk, renewals, upsell, QBR or handoff requests.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Follow pd-core rules (load pd-core if not loaded).

    line 11
  2. Very specific:

    Read accounts in .pipedrive/config.json (set by pd-setup, keys in references/setup.md).

    line 19
  3. Very specific:

    Only when accounts.health_field is set.

    line 41
  4. Very specific:

    Run the script with --writeback-out.

    line 42

≈ “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

pd-account-health

Follow pd-core rules (load pd-core if not loaded).

Requires: Pipedrive Optional: Google Docs (review, handoff) Fallback: chat, optional pinned [Claude] note on the org (after confirm)

Account model

Read accounts in .pipedrive/config.json (set by pd-setup, keys in references/setup.md). Missing: run the pd-setup accounts step, or continue with defaults and say so: accounts = orgs with a won deal, account manager = org owner, revenue = won value of the last 12 months, renewal = first won deal anniversary.

Pick a mode

User saysModeLoad
"my book", "portfolio", "accounts at risk", "how are my accounts"portfolioreferences/modes/portfolio.md
"health of <org>", "score my accounts"healthreferences/modes/health.md
"renewals this quarter", "what renews next"renewalsreferences/modes/renewals.md
"single-threaded", "who do we know at", "contacts coverage"coveragereferences/modes/coverage.md
"upsell", "cross-sell", "what else could <org> buy"whitespacereferences/modes/whitespace.md
"QBR for <org>", "account review", "prep the business review"reviewreferences/modes/review.md
"handoff for <deal>", "brief CS on <deal>"handoffreferences/modes/handoff.md

More than about 30 accounts in scope: use the portfolio flow (script) even for health, renewals, coverage or whitespace questions, then answer from its output.

Scoring (same in every mode)

scripts/account_rollup.py scores 0-100 from facts: last touch 30%, activity trend 20%, next step planned 20%, people covered 20%, product breadth vs peers 10%. Green 70+, amber 40-69, red under 40. A driver with no data is left out and the others reweighted. Weights can be changed in accounts.weights. Always state the weights once. Notes are read by Claude only for the accounts the user asks about, capped at 10 per run, and quoted with dates.

Write-back (opt-in)

Only when accounts.health_field is set. Always ask before writing.

  1. Run the script with --writeback-out. It lists only accounts whose bucket changed or score moved 10+ points, max 200.
  2. Show: count, 5 sample rows (org, old, new), the field names. Ask "Update these <n> organizations?"
  3. On yes: updateOrganization with the custom_fields of each row. Log to pipedrive-out/pd-account-health/<date>-writeback.log. Stop on the first error and report.
  4. Then say once: a Pipedrive filter on Health score plus an automation can create the follow-up activity for red accounts. Do not build that workflow in Claude.

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.