resume-ats-llm-reference

Document resume optimization, ATS scoring, and LLM guardrail logic for the Tayari pipeline.

Updated Jan 20, 2026
One-click install
npx skills add https://github.com/Harshodai/tayari-skill-boost --skill resume-ats-llm-reference
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: resume-ats-llm-reference
Source: https://github.com/Harshodai/tayari-skill-boost/tree/main/.claude/skills/resume-ats-llm-reference
Command: npx skills add https://github.com/Harshodai/tayari-skill-boost --skill resume-ats-llm-reference

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill provides the domain-specific knowledge required to understand how resume optimization engines function, bridging the gap between generic advice and the actual implementation of ATS scoring, semantic similarity, and guardrail logic.

Core Features & Use Cases

  • ATS Scoring Logic: Explains the difference between structural heuristic scoring and real-world ATS parsing.
  • Optimization Theory: Details the Reflexion method, STAR rubric application, and keyword-stuffing prevention.
  • Use Case: Use this reference when debugging why a resume is failing ATS checks or when you need to understand the specific formulas used for TF-IDF cosine similarity in the Tayari pipeline.

Quick Start

Load the resume-ats-llm-reference skill to explain the current heuristic scoring thresholds and the logic behind the truthfulness guardrail.

Frequently Asked Questions about resume-ats-llm-reference

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How does ATS scoring actually work for resume optimization?

Resume optimization engines use structural heuristic scoring and semantic similarity calculations to evaluate resumes, differing significantly from real-world ATS parsing logic. This reference details those specific formulas and thresholds.

How do I debug a resume failing ATS checks?

Debugging failed ATS checks requires verifying structural heuristics and TF-IDF cosine similarity calculations against established quality signal metrics. This reference provides the technical documentation needed to trace scoring failures.

What is the Reflexion method for resume optimization?

The Reflexion method is an optimization theory applied alongside the STAR rubric to enhance resume content while enforcing keyword-stuffing prevention. This skill documents how these guardrails function within the pipeline.

How do LLM guardrails detect resume fabrication?

LLM-based career pipeline guardrails detect fabrication by applying truthfulness logic and semantic similarity calculations to resume content. This skill provides the technical documentation to verify these accuracy heuristics.

Do I need backend service definitions to use this resume reference?

Yes, this reference requires deep integration with Tayari backend service definitions to verify structural heuristics and established quality signal metrics. It supports developers and analysts debugging the pipeline.