qualify-lead — Claude Code command: what it does, how to install
qualify-lead scores buyer fit and intent signals to determine whether sales teams should route, nurture, or recycle an account.
Apache-2.0 ★ 450 updated 2026-04-03
.claude/commands/qualify-lead.mdWhat qualify-lead does
The /sales-prospecting:qualify-lead command evaluates prospect records against ICP criteria, intent signals, and purchase triggers. It reviews company attributes, tech stack compatibility, and activity telemetry to decide if an account belongs with an AE, goes into nurturing, or returns to the pool.
Its five-step workflow normalizes incoming data, calculates fit and intent scores, assesses timing factors like fresh funding or key hires, and generates action steps. The output returns structured JSON containing fit, intent, and composite scores alongside urgency tags and recommended next moves.
Input JSON or CSV files for firmographics, technographics, and intent data are necessary for accurate evaluation. Leads pass to sales only when their composite score meets the minimum threshold, which is set to 70 by default.
What it helps with
- score prospects against ICP attributes and intent data
- route qualified leads to sales reps based on composite scores
- decide whether to recycle or nurture early-stage accounts
- map technographic stack alignment before scheduling outreach
Example prompts for the agent
- /sales-prospecting:qualify-lead --company "Acme" --persona "VP Revenue" --signals intent.json
- /sales-prospecting:qualify-lead --company "Stark Tech" --persona "CTO" --firmographics firmo.json --technographics tech.json --signals intent.json --threshold 75
- /sales-prospecting:qualify-lead --company "Cyberdyne" --persona "VP Sales" --stage PQL --signals intent.json
How to install qualify-lead
Manually: put the files in place
.claude/commands/qualify-lead.mdCall it with /qualify-lead. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/qualify-lead.mdCall it with /prompts:qualify-lead. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/qualify-lead.prompt.mdManually: put the files in place
.gemini/commands/qualify-lead.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about qualify-lead
How to install qualify-lead in Claude Code?
Add the command file to your project repository at .claude/commands/qualify-lead.md.
What does qualify-lead do?
It assesses company firmographics, tech stack, and intent events to generate routing recommendations with a composite score in JSON format.
What is the default qualification threshold?
The default minimum composite score required to hand a lead off to sales is 70, adjustable via --threshold.
Source text
qualify-lead.md · Apache-2.0
---
name: qualify-lead
description: Evaluate prospect fit and intent to determine next-best action for sales teams.
usage: /sales-prospecting:qualify-lead --company "Acme" --persona "VP Revenue" --signals intent.json
---
# Qualify Lead Command
Score leads against ICP, intent signals, and buying triggers to decide whether to route, recycle, or nurture.
## Command Syntax
```bash
/sales-prospecting:qualify-lead \
--company "<name>" \
--persona "<title>" \
--firmographics firmo.json \
--technographics tech.json \
--signals intent.json \
--threshold 75
```
### Parameters
- `--company`: Account name or domain.
- `--persona`: Primary buyer role under evaluation.
- `--firmographics`: JSON/CSV input of company attributes.
- `--technographics`: Technology stack details.
- `--signals`: Intent data (product usage, web visits, 3rd-party intent).
- `--threshold`: Minimum composite score to pass to sales (default 70).
- `--stage`: Lead stage (MQL, PQL, recycled) to influence scoring weights.
## Workflow
1. **Data Normalization** – clean and map firmographic, technographic, and behavior fields.
2. **Fit Scoring** – apply weighted ICP model (industry, size, geography, use case, tech stack compatibility).
3. **Intent Scoring** – incorporate behavioral data (content engagement, trials, intent providers, product telemetry).
4. **Timing Assessment** – evaluate trigger events (funding, hires, tech churn) plus buying cycle alignment.
5. **Recommendation Engine** – produce route/recycle/nurture guidance with rationale, next steps, and owner.
## Output Schema
```json
{
"company": "Acme Corp",
"fit_score": 82,
"intent_score": 76,
"composite_score": 79,
"decision": "route-to-ae",
"urgency": "high",
"rationale": [
"ICP match: SaaS, 200 employees, US",
"High technographic overlap",
"Recent product trial and pricing page visits"
],
"next_steps": [
"Assign to AE Sarah Lee",
"Send enterprise case study",
"Schedule discovery call within 48h"
]
}
```
## Best Practices
- Keep scoring models transparent so SDRs/RevOps can adjust weights.
- Blend qualitative notes (call transcripts) with quantitative data.
- Auto-sync outcomes to CRM and track model drift monthly.
- Use different thresholds for inbound vs outbound vs product-led leads.
---
© gtmagents · Apache-2.0 · gtmagents/gtm-agents