agentleFS
Sign inStart free
anmoba99anmoba99/pipedrive-claude-skills/skills/pd-ask/SKILL.md

pd-ask

Skill0 starsChanged 29 days agoMITView on GitHub

Answer any plain-English question about the user's Pipedrive data (deals, contacts, organizations, activities, notes, leads, products) with the cheapest possible queries. Use for ad-hoc questions not covered by a more specific pd-* skill.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 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.

  • 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. Distinctive:

    Check for a better skill: daily to-do -> pd-morning-brief.

    line 20
  3. Distinctive:

    If the plan needs more than about 15 calls or would pull 500+ records, say so and offer a narrower version first.

    line 22
  4. Very specific:

    Run. Aggregate with pd-core/scripts/pd_digest.py when counting or summing over more than about 20 records.

    line 23
  5. Very specific:

    If the data is ambiguous (two "Acme" orgs, missing field), say so in one line and ask.

    line 34
  6. Very specific:

    Never guess custom field meanings: map names via .pipedrive/field-map.json or .pipedrive/account_context.json.

    line 35

≈ “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

pd-ask

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

Requires: Pipedrive Fallback: question needs data Pipedrive does not hold -> say which data is missing.

Steps

  1. Restate the question as a query in one line: object, filters, time window, fields, aggregation. Example: "Clients in Porto not contacted in 60 days" -> orgs with city=Porto (custom/address field), deals or activities with no update since today-60d.
  2. Check for a better skill: daily to-do -> pd-morning-brief; team or forecast -> pd-pipeline-review; deals at risk -> pd-premortem; why we win or lose -> pd-win-loss; best customer segments -> pd-icp-discovery. If one fits, use it.
  3. Plan calls with pd-core/references/query-playbook.md. Prefer: known ID > saved filter (filter_id) > filtered list > search.
  4. If the plan needs more than about 15 calls or would pull 500+ records, say so and offer a narrower version first.
  5. Run. Aggregate with pd-core/scripts/pd_digest.py when counting or summing over more than about 20 records.
  6. Answer.

Output

<Direct answer in 1-2 lines>
<up to 20 compact rows: id | name | key fields>
Query: <one line: what was fetched and filters used>

If the data is ambiguous (two "Acme" orgs, missing field), say so in one line and ask. Never guess custom field meanings: map names via .pipedrive/field-map.json or .pipedrive/account_context.json.

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