Przejdź do treści
Biblioteka skilli
Sprzedaż i obsługa klienta · Analiza

lead-qualification

/lead-qualification

Ocenia i kwalifikuje leady sprzedażowe według kryteriów i dopasowania, w tym z frameworkami BANT, MEDDIC i własnymi modelami punktacji.

Repozytorium
skills ↗
Licencja
Apache-2.0
Ostatnia zmiana repozytorium
25.10.2026

Ocena i bezpieczeństwo

100/ 100Klasa: dobry
Format25 / 25
Frontmatter z nazwą i opisem, poprawna nazwa, opis do 1024 znaków, nazwa zgodna z folderem.
Odkrywalność25 / 25
Opis mówi, kiedy użyć skilla, ma sensowną długość i jest w 3. osobie.
Treść35 / 35
Co najmniej 150 słów i do 500 linii, nagłówki, listy kroków, przykłady albo kod.
Higiena15 / 15
Bez zaślepek typu TODO, bez ścieżek Windows, z licencją.
Ryzykobrak sygnałów w skanie
Pliki w paczce
2
Skrypty
0
Komentarze HTML
0
Adresy URL w SKILL.md
0
Przestarzałość

Brak sygnałów. Repozytorium zmienione 25.10.2026, bez odwołań do wycofanych modeli i API.

Licencja

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

Co robi i kiedy

Ocenia i kwalifikuje leady sprzedażowe według kryteriów i dopasowania, w tym z frameworkami BANT, MEDDIC i własnymi modelami punktacji.

Oryginalny opis (EN)

Score and qualify sales leads based on criteria and fit. Use when a user asks to qualify leads, score prospects, prioritize sales leads, evaluate lead quality, rank leads by fit, assess sales pipeline, or determine which leads to pursue first. Supports BANT, MEDDIC, and custom scoring frameworks.

Jak działa

  1. Overview
  2. Instructions
  3. Examples
  4. Guidelines
Sekcje z nagłówków SKILL.md, w oryginale · 261 linii, 1 500 słów
Podgląd SKILL.md
---
name: lead-qualification
description: >-
  Score and qualify sales leads based on criteria and fit. Use when a user asks
  to qualify leads, score prospects, prioritize sales leads, evaluate lead
  quality, rank leads by fit, assess sales pipeline, or determine which leads to
  pursue first. Supports BANT, MEDDIC, and custom scoring frameworks.
license: Apache-2.0
compatibility: "Requires Python 3.11+ with pandas 3 (and openpyxl for .xlsx input)"
metadata:
  author: terminal-skills
  version: "1.1.0"
  category: business
  tags: "sales, leads, qualification, scoring, pipeline"
  use-cases: "Score and rank a list of inbound leads to prioritize sales outreach, Evaluate leads against ideal customer profile criteria, Analyze pipeline quality and identify the most promising opportunities"
  agents: "claude-code, openai-codex, gemini-cli, cursor"
---

# Lead Qualification

## Overview

Score and qualify sales leads to prioritize outreach and focus on the highest-value opportunities. This skill evaluates leads against configurable criteria such as BANT (Budget, Authority, Need, Timeline), company fit, engagement signals, and custom scoring rules. Produces ranked lead lists with scores, recommendations, and next-step suggestions.

## Instructions

When a user asks to qualify, score, or prioritize their leads, follow these steps:

### Step 1: Load the lead data

Accept leads from CSV, spreadsheet, or manual input:

```python
import pandas as pd

def load_leads(file_path):
    if file_path.endswith('.csv'):
        df = pd.read_csv(file_path)
    elif file_path.endswith('.xlsx'):
        df = pd.read_excel(file_path)
    else:
        raise ValueError("Supported formats: CSV, XLSX")
    df.columns = [col.strip().lower().replace(' ', '_') for col in df.columns]
    return df
```

Key fields to look for or request:
- Company name, industry, company size (employees or revenue)
- Contact name, title, role
- Lead source (inbound, referral, outbound, event)
- Budget information (if available)
- Current solution / competitor
- Engagement signals (website visits, content downloads, demo requests)
- Notes or qualification details

### Step 2: Select the scoring framework

**BANT Scoring** (default for most B2B):

| Criteria | Weight | Scoring |
|----------|--------|---------|
| Budget | 30% | Has budget (30), exploring (15), no budget (0) |
| Authority | 25% | Decision maker (25), influencer (15), researcher (5) |
| Need | 25% | Urgent need (25), acknowledged need (15), no clear need (5) |
| Timeline | 20% | Within 3 months (20), 3-6 months (10), 6+ months (5) |

**Company Fit Scoring** (for ICP matching):

| Criteria | Weight | Scoring |
|----------|--------|---------|
| Industry match | 25% | Target industry (25), adjacent (15), other (5) |
| Company size | 25% | Ideal range (25), close (15), outside (5) |
| Geography | 15% | Target region (15), serviceable (10), other (5) |
| Technology fit | 20% | Uses compatible stack (20), neutral (10), incompatible (0) |
| Revenue potential | 15% | High ACV (15), medium (10), low (5) |

### Step 3: Score each lead

Match keywords as whole words. Plain substring tests misfire: `'cto' in 'contractor'` is true, and `'3 month' in '13 months'` is true.

```python
import re

def has(text, words):
    return re.search(r"\b(?:" + "|".join(re.escape(w) for w in words) + r")\b", text, re.I) is not None

def score_lead_bant(lead):
    score, reasons = 0, []

    # Budget (30 points)
    budget = str(lead.get("budget", "")).lower()
    if budget in ["yes", "confirmed", "approved"]:
        score += 30; reasons.append("Budget confirmed")
    elif budget in ["exploring", "pending", "maybe"]:
        score += 15; reasons.append("Budget being explored")
    else:
        reasons.append("No budget information")

    # Authority (25 points)
    title = str(lead.get("title", ""))
    if has(title, ["ceo", "cto", "cfo", "coo", "founder", "owner", "vp", "svp", "evp", "vice president", "director", "head of"]):
        score += 25; reasons.append("Decision maker")
    elif has(title, ["manager", "lead", "senior", "principal"]):
        score += 15; reasons.append("Influencer role")
    else:
        score += 5; reasons.append("Researcher / early stage")

    # Need (25 points)
    need = str(lead.get("need", lead.get("pain_point", ""))).strip().lower()
    if has(need, ["urgent", "critical", "immediate", "asap"]):
        score += 25; reasons.append("Urgent need identified")
    elif need and need not in ["none", "no", "nan"]:
        score += 15; reasons.append("Need acknowledged")
    else:
        score += 5; reasons.append("Need unclear")

    # Timeline (20 points)
    timeline = str(lead.get("timeline", "")).lower()
    months = re.search(r"\b(\d+)\s*(?:-\s*\d+\s*)?months?\b", timeline)  # "3 months", "4-6 months"
    if has(timeline, ["now", "asap", "this month", "this quarter"]) or (months and int(months.group(1)) <= 3):
        score += 20; reasons.append("Near-term timeline")
    elif has(timeline, ["next quarter", "this year"]) or (months and int(months.group(1)) <= 6):
        score += 10; reasons.append("Medium-term timeline")
    else:
        score += 5; reasons.append("No clear timeline")

    return score, reasons
```

**MEDDIC** (for larger, multi-stakeholder deals) scores six questions instead: Metrics (the quantified business result), Economic buyer (who signs), Decision criteria, Decision process, Identify pain, Champion (an internal advocate). Many teams add a seventh C for Competition (MEDDICC). Give each a 0-2 rating (unknown, partial, confirmed) and rank by the total; unanswered questions are the next discovery-call agenda.

### Step 4: Classify and rank leads

Assign qualification tiers based on score:

```python
def classify_lead(score):
    if score >= 80:
        return "Hot", "Immediate follow-up - schedule a call today"
    elif score >= 60:
        return "Warm", "Priority follow-up within 48 hours"
    elif score >= 40:
        return "Nurture", "Add to nurture campaign, follow up in 1-2 weeks"
    else:
        return "Cold", "Low priority - monitor for engagement changes"
```

### Step 5: Generate the qualification report

Output a ranked list with scores, tiers, reasons, and recommended actions:

```python
def qualify(df, output_path="qualified_leads.csv"):
    rows = []
    for lead in df.to_dict("records"):
        score, reasons = score_lead_bant(lead)
        tier, action = classify_lead(score)
        rows.append({**lead, "score": score, "tier": tier, "action": action, "reasons": "; ".join(reasons)})
    ranked = pd.DataFrame(rows).sort_values("score", ascending=False)
    ranked.to_csv(output_path, index=False)
    return ranked
```

## Examples

### Example 1: Qualify a list of inbound leads

**User request:** "Score these 25 leads from our webinar sign-ups. Here's the CSV file."

**Actions taken:**
1. Load leads.csv with 25 entries
2. Apply BANT scoring based on available fields
3. Rank and classify all leads

**Output:**
```
Lead Qualification Report
=========================
Total leads scored: 25

Tier Breakdown:
  Hot (80+):     4 leads (16%) - Immediate follow-up
  Warm (60-79):  7 leads (28%) - Priority follow-up
  Nurture (40-59): 9 leads (36%) - Nurture campaign
  Cold (<40):    5 leads (20%) - Monitor

Top 5 Leads:
  Rank | Company          | Contact       | Score | Tier | Action
  1    | TechGrowth Inc   | Sarah Chen, VP| 95    | Hot  | Call today - budget confirmed, urgent need
  2    | DataFirst LLC    | Mark Jones, Dir| 90   | Hot  | Call today - decision maker, Q1 timeline
  3    | ScaleUp Corp     | Amy Park, CTO | 85    | Hot  | Call today - strong tech fit, active eval
  4    | CloudNine SaaS   | Tom Lee, Head | 80    | Hot  | Demo this week - exploring budget
  5    | GreenField Co    | Lisa Wang, Mgr| 75    | Warm | Follow up in 48h - need confirmed

Full report saved: qualified_leads.csv
```

### Example 2: Evaluate leads against ideal customer profile

**User request:** "We sell to mid-market SaaS companies (100-1000 employees) in North America. Score these leads for fit."

**Actions taken:**
1. Define ICP criteria from user description
2. Score each lead on company fit dimensions
3. Highlight best-fit and poor-fit leads

**Output:**
```
ICP Fit Analysis
================
Target Profile: Mid-market SaaS, 100-1000 employees, North America

Fit Distribution:
  Strong fit (80+):    8 leads - Match ICP on 4+ criteria
  Moderate fit (60-79): 12 leads - Match on 2-3 criteria
  Weak fit (<60):      5 leads - Poor ICP match

Strong Fit Leads:
  1. StreamLine (SaaS, 450 emp, US) - Score: 92
  2. DataPipe (SaaS, 280 emp, Canada) - Score: 88
  3. FlowMetrics (SaaS, 620 emp, US) - Score: 85

Weak Fit (consider deprioritizing):
  - MegaCorp Industries (Manufacturing, 15,000 emp) - Score: 25
  - LocalShop (Retail, 12 emp, UK) - Score: 20
```

### Example 3: Pipeline quality analysis

**User request:** "Analyze our current pipeline of 50 opportunities and tell me which ones to focus on this quarter"

**Actions taken:**
1. Load pipeline data
2. Score on BANT plus deal velocity indicators
3. Identify stalled deals and top opportunities

**Output:**
```
Pipeline Quality Analysis: Q4 2026
====================================
Total opportunities: 50
Total pipeline value: $2.4M

Quality Distribution:
  High quality (likely to close):  12 deals ($820K)
  Medium quality (needs work):     18 deals ($740K)
  Low quality (at risk):           14 deals ($580K)
  Stalled (no activity 30+ days):   6 deals ($260K)

Recommended Focus (Top 10):
  1. Northwind Logistics - $120K - score 92 - sign-off meeting with CFO booked for Nov 4
  2. Brightline Health - $85K - score 88 - security review pending, send SOC 2 report
  (8 more, each with score and next step)

Stalled Deals Requiring Attention:
  - Harbor Freight Systems ($60K): no contact in 45 days, re-engage or close out
  - Lumen Analytics ($45K): champion left the company, identify a new sponsor

Quarterly Forecast:
  Best case:   $820K (high quality deals)
  Likely case: $620K (weighted by probability)
  Worst case:  $380K (only committed deals)
```

## Guidelines

- Default to BANT scoring for B2B leads unless the user specifies a different framework.
- Always sort output by score descending so the best leads appear first.
- Include a specific recommended action for each lead tier, not just the score.
- When lead data is incomplete, score based on available fields and note what information is missing.
- Flag leads where the contact title suggests they are not a decision maker but the deal is otherwise strong.
- For pipeline analysis, flag stalled deals (no activity in 30+ days) as a separate category.
- Scoring weights should be configurable. Use the defaults but adjust if the user specifies different priorities.
- Never present raw scores without context. Always include the tier classification and a recommended action.
- Install in a virtual environment: `python -m venv .venv && .venv/bin/pip install pandas openpyxl` (pandas 3 needs Python 3.11+).
- Lead data is personal data (names, work emails): keep exports out of shared folders and version control, and do not send it to third-party enrichment tools without the user's approval.
- Scores rank leads; they do not predict closing. Revisit the weights after comparing scores with real won/lost outcomes.
Pliki w paczce (2)
  • SKILL.md 11 KB
  • _scores.json 1 KB

Wersje

RepozytoriumWynikLicencja
Ta strona · TerminalSkills/skills100Apache-2.0
Navinspire-ia/navin100AGPL-3.0
naveedharri/benai-skills100MIT
criptogus/agent-evolve-network86Apache-2.0

Migawka bazy z 13.11.2026 · wersja paczki de1975e908d9 (skrót SHA-256 całej paczki)

Pobrania w ostatnich 30 dniach: 0 · ranking

Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.

Podobne skille

  • 85sales
    Pomaga w strategii sprzedaży, pipeline'ie i kwalifikacji szans według BANT lub MEDDIC oraz w pracy z CRM.
  • 100deal-qualification
    Kwalifikuje szansę sprzedażową metodą MEDDIC i ocenia, czy warto ją ciągnąć dalej oraz na jakim etapie lejka się znajduje.
  • 100lead-researcher
    Kwalifikuje i priorytetyzuje leady względem ICP, ocenia listy punktowo i pisze spersonalizowane haczyki otwierające wiadomość.
  • 100lead-scoring
    Ocenia i priorytetyzuje leady według dopasowania firmograficznego i sygnałów zaangażowania, tworząc uporządkowane kategorie dla zespołu sprzedaży.
  • 100bant
    Audytuje transkrypt rozmowy sprzedażowej B2B według BANT (budżet, decydent, potrzeba, termin) albo przeszukuje eksport CRM pod kątem szans bez pól BANT.
  • 100lead-triage
    Ocenia i kieruje przychodzące leady albo ustawia w kolejności zaległe, względem ICP i frameworku kwalifikacji, a potem rekomenduje priorytet i następny krok.

Uwagi i zgłoszenia

Wiadomość trafi do Bartosza Sokolińskiego. Adres e-mail jest potrzebny tylko do odpowiedzi. Szczegóły w polityce prywatności.