lead-qualification

A workflow that scores and categorizes contacts as potential sales leads using details such as job title, company fit, email type, LinkedIn presence, and relationships.

In plain words
What is it for?
Use it to score new contacts, refresh scores, assign lifecycle stages and tags, and record why each contact received its score.
Why use it?
It gives a consistent way to distinguish promising contacts from people who need nurturing or are currently low priority.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/nimblebraininc/upjack/lead-qualification
Any agent
npx skills add NimbleBrainInc/upjack --skill lead-qualification
Clone the repo
git clone --depth 1 https://github.com/NimbleBrainInc/upjack

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 400 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00400
Opus 5 $0.00000 $0.00200
Sonnet 5 $0.00000 $0.00080
Haiku 4.5 $0.00000 $0.00040

Measured 2d ago against content hash 1d6bfb360fea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lead-qualification scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

examples/crm/skills/lead-qualification/SKILL.md · 52 lines

What it actually says

Lead Qualification

Score and qualify new contacts based on their profile and engagement signals.

When to Use

  • A new contact is created (triggered automatically via hook)
  • Nightly lead scoring refresh (triggered via schedule)
  • User asks to evaluate or score a contact

Process

  1. Gather signals from the contact record:

    • Job title and seniority (C-suite, VP, Director = high signal)
    • Company size and industry fit
    • Email domain (corporate vs. personal)
    • LinkedIn presence
    • Existing relationships to other entities
  2. Score the contact (0-100):

    • 80-100: Hot lead — immediate follow-up needed
    • 60-79: Warm lead — nurture with targeted content
    • 40-59: Neutral — monitor for engagement
    • 0-39: Cold — low priority
  3. Update the contact with:

    • lead_score: Numeric score
    • lifecycle_stage: Based on score (lead, mql, sql)
    • tags: Add relevant tags (e.g., "hot-lead", "decision-maker")
  4. Log an activity explaining the scoring rationale

Scoring Rubric

Signal Points
C-suite title +25
VP/Director title +15
Manager title +10
Company size > 200 +15
Company size 50-200 +10
Corporate email domain +10
LinkedIn profile present +5
Multiple relationships +10
Recent activity (7 days) +10

Rules

  • Never decrease a lead score by more than 20 points in a single update
  • Always explain score changes in an activity note
  • If enrichment bundle is available, use enrich_person before scoring
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 52 lines · 0 tokens per session scan A 1d6bfb360fea

Subscribe to this mod's changes

lead-qualification is a skill published in the GitHub repository NimbleBrainInc/upjack (9 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 400 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories