lead-qualification
Skill1 starsChanged 56 days agoMITView on GitHub
Use when stage 18 of the prospecting system has positive replies and each one needs a go / nurture / no-go decision before a meeting is booked — checking the person, the account, the timing, and the reply itself against the ICP. Also use when the ask is \"is this lead worth a call?\".
8 other projects use a version of this.
Adopted by
Most recently taken up by
- athina-ai/goose-skillstheir own version, first seen Nov 9, 2026
- cwhited26/pocket-agent-starter-skillstheir own version, first seen Nov 1, 2026
- gooseworks-ai/goose-skillstheir own version, first seen Nov 1, 2026
- vijaysuperpositionist/skillstheir own version, first seen Nov 1, 2026
- Nomanriaz786/claude-consulting-teamtheir own version, first seen Nov 1, 2026
- astDeniss/business-skillstheir own version, first seen Nov 1, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- athina-ai/goose-skills★ 1.3ksame name
- gooseworks-ai/goose-skills★ 1.3ksame name
- cognyai/claude-code-marketing-skills★ 106same name
- astDeniss/business-skills★ 8same name
- open-gitagent/enterprise-skills★ 4same name
- Nomanriaz786/claude-consulting-team★ 1same name
- cwhited26/pocket-agent-starter-skills★ 0same name
- vijaysuperpositionist/skills★ 0same 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 repository21 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- account-notesSkill
- audience-discoverySkill
- audience-filterSkill
- buying-signalsSkill
- cold-emailSkill
- contact-enrichmentSkill
- customer-patternsSkill
- follower-scrapeSkill
- follow-upsSkill
- icp-definitionSkill
- lead-prioritizationSkill
- lead-scoringSkill
- linkedin-outreachSkill
- lookalike-researchSkill
- personalizationSkill
- pipeline-reviewSkill
- prospecting-systemSkill
- reply-classificationSkill
- segmentationSkill
- targeted-searchSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
1
Distinctive
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 44
Every no-go and nurture reason is data.
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Lead Qualification
A positive reply is not a qualified lead. This stage spends a few minutes per replier so the calendar fills with the right meetings, and so the wrong ones get a useful answer instead of a call.
Pipeline contract
Stage 18 of 20. Reads 17-replies.csv (rows with is_positive=true), 10-scored.csv, 09-signals.csv, 02-client-profile.yaml. Writes 18-qualified.csv (adds decision, decision_reason, open_questions, suggested_reply).
Files live in runs/<run>/. Column definitions: /prospecting-system.
Four checks
| Check | Question | Evidence |
| Person | Can they buy, champion, or introduce? | title vs the profile's job_titles; what they said about their role |
| Account | Does the company still pass the hard filters? | screen and fit_components from stage 10 — re-verify anything that was blank |
| Timing | Is there a reason to act now? | dated signals from stage 9; timing words in the reply ("next quarter", "evaluating now") |
| Reply | What did they actually ask for? | the reply text and its stage 17 label |
Record what is known and what is not. An unknown is an open question for the call, not a fail.
Decision
- go — person and account pass, nothing in the reply contradicts fit. Book it. Hand to
/account-notes. - nurture — fit is real but timing is not ("reach out in Q3"). Log the re-engage date and the trigger that would bring it forward. Re-engagement rules: the Re-Qualification table in
/lead-scoring. - refer —
positive_referral: the named person becomes a new lead. Add them to08-leads.csvwithsource_typeunchanged andsource_detail=referral from <lead_id>, and contact them the same day. - no-go — a hard filter fails. Reply politely and close it. Do not book a meeting to find out.
decision_reason is one sentence naming the check that decided it. suggested_reply is a draft for the human; nothing is sent.
Rules
- The hard filters are the human's. If a no-go feels wrong, say so in
decision_reasonand propose a filter change for stage 20 — do not quietly pass the lead. - For Tier 1 accounts, build the full account brief (Level 3 in
/lead-scoring) before the call, via/account-notes. - Every no-go and nurture reason is data. Stage 20 reads this file to see which segments and sources produce replies that do not qualify.
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.