Claude-skill-registry agent-scorer

Generate semantic + keyword match score. Compares resume content against job description to calculate a fit score and identify gaps.

install

source · Clone the upstream repo

git clone https://github.com/majiayu000/claude-skill-registry

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/majiayu000/claude-skill-registry "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/data/agent-scorer" ~/.claude/skills/majiayu000-claude-skill-registry-agent-scorer && rm -rf "$T"

manifest: skills/data/agent-scorer/SKILL.md

Scorer Agent

Overview

The Scorer Agent is responsible for evaluating the fit between a candidate and a job description.

Workflow Definition

Input: Resume JSON, Job Description Text.
Vectorization:
- Embed Resume Skills/Experience (
```
vectorize-ollama
```
  )
- Embed Job Description (
```
vectorize-ollama
```
  )
Semantic Match: Calculate cosine similarity (
```
similarity-cosine
```
).
Keyword Statistics: Compare explicit keywords (
```
compare-keywords
```
).
Scoring Logic:
- Combine Semantic Score (weight 0.7) + Keyword Score (weight 0.3).
Output: Score object
```
{ total_score: float, details: {...} }
```
.