qualify-lead
Skill0 starsChanged 7 months agoMITView on GitHub
Use when an inbound lead arrives or when prioritizing an outbound list. Produces a BANT or MEDDIC scorecard against the user's ICP, a verdict (qualified / nurture / disqualify), and a recommended next action. Asks for ICP definition if not provided.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- langchain-ai/lca-deepagentstheir own version, first seen Jun 18, 2026
- DanderlionJer/skillstheir own version, first seen May 6, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- langchain-ai/lca-deepagents★ 48same name
- DanderlionJer/skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository8 other files it gives its agents.
- code-reviewSkill
- cold-email-sequenceSkill
- content-calendarSkill
- funnel-analysisSkill
- market-researchSkill
- release-notesSkill
- seo-outlineSkill
- write-linkedin-postSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 43
Nurture (40-75%): Add to a sequence aimed at the missing dimension.
- Distinctive: line 44
Disqualify (< 40%): Do not pursue now. Note why.
- Very specific: line 70
Never invent budget, headcount, or stack info you don't have.
≈ “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.
Files
qualify-lead
Lead qualification is a forecasting exercise: given what we know about this account/person, what's the probability they close in the next 90 days, and what's the right next move?
Inputs to gather
- ICP definition — industry, company size, role, trigger event. If missing, ask first.
- The lead — company name, role, source, anything they said or filled in.
- Framework preference — BANT (default for SMB) or MEDDIC (default for mid-market+ deals).
BANT scorecard
| Dimension | Score 0-3 | Evidence |
| Budget | ||
| Authority | ||
| Need | ||
| Timeline |
Score 0 = no signal, 3 = strong explicit signal. Total / 12.
MEDDIC scorecard
| Dimension | Score 0-3 | Evidence |
| Metrics | what economic outcome are they targeting? | |
| Economic buyer | identified? engaged? | |
| Decision criteria | known? influenceable? | |
| Decision process | mapped? timeline? | |
| Identify pain | quantified? urgent? | |
| Champion | found? coachable? |
Score 0 = no signal, 3 = strong explicit signal. Total / 18.
Verdicts
- Qualified (≥ 75%): Hand to AE. Recommend specific next step (discovery call, proposal, pricing convo).
- Nurture (40-75%): Add to a sequence aimed at the missing dimension. Re-evaluate in 30/60/90 days.
- Disqualify (< 40%): Do not pursue now. Note why; revisit only on a trigger event.
Output format
## Verdict
<qualified | nurture | disqualify> — <one-line reason>
## Scorecard (<framework>)
<table>
## Score: X/Y (Z%)
## Gaps
- <missing dimension 1 and what would resolve it>
- <missing dimension 2 and what would resolve it>
## Recommended next action
<one specific action — meeting, sequence, intro request, etc.>
## CRM update
<paste-ready note for HubSpot/Salesforce>Hard rules
- Never invent budget, headcount, or stack info you don't have. Mark
[unknown]. - A high score on Need without a Decision Process is a trap — flag it.
- "They downloaded the whitepaper" is not Authority. Don't conflate engagement with intent.
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.

