Evaluate entities against qualification criteria and output labels or scores.
npx skills add https://github.com/nurturev/gtm-engine --skill qualification
Please help me install this Agent Skill. Skill: qualification Source: https://github.com/nurturev/gtm-engine/tree/main/.claude/skills/qualification Command: npx skills add https://github.com/nurturev/gtm-engine --skill qualification
This Skill automates the evaluation of entities against predefined qualification criteria to decide if they are worth pursuing, reducing manual triage and speeding up lead targeting.
Provide a list of entities and the skill will return per-entity qualification results and scores.
High-intent search queries and answers about installing and using this skill.
Automated lead scoring evaluates entities against predefined qualification criteria to determine fit or disqualification. It supports per-entity evaluation or group-level scoring across aggregated signals, returning structured labels, scores, and rationale for deterministic filtering and downstream automation.
Group-level scoring qualifies leads by aggregating signals across multiple entities to produce an overall score and section-wise scoring with rationale. This approach assesses collective fit rather than individual entities, enabling broader research workflow automation and deterministic filtering.
Yes, entity qualification outputs are designed for downstream workflow automation. The skill returns structured per-entity labels or scores with rationale, which can be captured as workflow variables to drive deterministic filtering and automate subsequent research steps.
Per-entity evaluation classifies each lead as qualified or unqualified by assessing it against your predefined qualification criteria. You provide a list of entities, and the skill returns individual qualification results, optional scores, and rationale for each entity.
Group-level scoring is needed when you want to aggregate signals across multiple entities to produce an overall score and section-wise scoring with rationale. Per-entity evaluation is better suited for classifying individual leads as qualified or unqualified independently.
Yes, lead qualification supports deterministic filtering by outputting structured per-entity labels or scores with rationale. These outputs are suitable for deterministic filtering and can be integrated into research workflows via workflow variables for automated downstream processing.
surus-latGenerate synthetic benchmark datasets as JSONL input-output pairs from task specifications.
bhushanofficial69-specIdentify target accounts and leads matching a defined ICP for B2B sales.
nurturevResearch entities in batch or on-demand modes to produce standardized enrichment signals.
aiyinluyaAnalyze multi-sheet Excel or CSV files and export an Excel report with a pie chart.
