pd-lead-qualifier
Skill0 starsChanged 30 days agoMITView on GitHub
Score Pipedrive leads or early-stage deals against BANT, MEDDICC, CHAMP or a custom checklist, list missing info and the next question to ask, and optionally write the score or convert leads to deals after confirmation. Use when the user asks which leads are serious, to qualify or score leads, or to clean the lead inbox.
In this repository19 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- pd-accessSkill
- pd-account-healthSkill
- pd-advisorSkill
- pd-askSkill
- pd-coreSkill
- pd-crm-architectSkill
- pd-data-hygieneSkill
- pd-follow-upSkill
- pd-icp-discoverySkill
- pd-industrySkill
- pd-morning-briefSkill
- pd-pipeline-reviewSkill
- pd-playbook-minerSkill
- pd-premortemSkill
- pd-setupSkill
- pd-thread-mapSkill
- pd-win-backSkill
- pd-win-lossSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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
- Distinctive: line 11
Follow pd-core rules (load pd-core if not loaded).
- Distinctive: line 36
Never mark a criterion confirmed without a quote or field value backing it.
≈ “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.
Files
pd-lead-qualifier
Follow pd-core rules (load pd-core if not loaded).
Requires: Pipedrive
Fallback: no score field in Pipedrive -> score goes in a [Claude] note (after confirm) or chat only
Steps
- Framework: from
config.jsonqualification_framework, the user's request, or the industry pack. Loadreferences/frameworks.mdfor criteria. - Scope:
getLeads limit=50(newest first), or early-stage dealsgetDeals stage_id=<first stages> status=open limit=50. Single lead named: search it. - Evidence per lead: lead/deal fields plus
getNotes lead_id|deal_id limit=5. Do not fetch notes for more than 25 records per run; say how many remain. - Score each criterion 0 (unknown), 1 (weak), 2 (confirmed), only from evidence. Total as a percentage. Grade: A >= 75%, B 50-74%, C 25-49%, D < 25%.
- For each lead: biggest gap and the single next question that closes it.
- Offer writes (safe-write): for deals, score to a custom field if one exists (field map: "Lead score", "Qualification"), else a note; for leads, a note (the connector cannot set lead custom fields);
convertLeadToDealfor A leads only if the user asks.
Output
Framework: BANT | scored 18 leads | 7 have no notes (scored on fields only)
A (3):
- <lead> | <org> | 88% | gap: timeline | ask: "When do you need this live?"
B (6): ...
C/D (9): <names only, one line>
Offer: write scores to field "Lead score"? convert A leads to deals?Never mark a criterion confirmed without a quote or field value backing it.
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
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.