# ats-screener

The ats-screener Claude Code subagent scores a resume against a job posting. Run it after revising the resume and before applying: it checks file parsing, then grades each qualification.

- subagent · `type=agent` · Claude Code, Codex, Cursor · ★ 73 repo stars
- Author: Jerome Hardaway, Vets Who Code
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Vets-Who-Code/ai-era-job-kit/tree/HEAD/agents/ats-screener.md
- Updated: 2026-11-11
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/agents/ats-screener

## What it does

ats-screener screens one resume against one job posting. It starts with knockout questions, then checks whether the resume can be parsed. A failed parse stops the grading process.

For each qualification, the subagent looks for direct evidence in the resume and records an exact quote with its section. A related skill does not count, and work experience counts only when tied to dated roles. The subagent saves its own A-to-D grade, then compares it with another grader’s result. The report gives the grade, counts, and up to five possible fixes. It reflects documented screening practices, not a prediction of a hiring decision.

The kit needs the `resume-scorer` skill, `scripts/screen_grade.py`, and `references/ats-research.md`. The script splits the posting and compares the graders’ results; its temporary files go outside any Git repository.

## Install

### Claude Code (native platform)

1. **Plugin marketplace**
In the agent chat (not a shell):
```text
/plugin marketplace add Vets-Who-Code/ai-era-job-kit
```
In the agent chat (not a shell):
```text
/plugin install ai-era-job-kit@ai-era-job-kit
```

2. **Manually: put the files in place**
- File: `.claude/agents/ats-screener.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/ats-screener.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/ats-screener.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/Vets-Who-Code/ai-era-job-kit/tree/HEAD/agents/ats-screener.md

## When to use it
- score a resume against a specific job posting
- spot qualifications without direct resume evidence
- check whether a screening system can parse a resume file
- compare two independent resume grades

## Example prompts
- Score my resume against this job posting and grade each qualification.
- Find posting requirements that my resume does not directly support.
- Compare your grade with the other reviewer's and report where they agree.

## Similar
- [ats](https://affpapa.org/en/nevibecode/mcp/ats.md) — MCP server · ★ 7 repo stars
- [resume-ats-optimizer](https://affpapa.org/en/nevibecode/skills/resume-ats-optimizer.md) — skill · 75 installs
- [agency-ats-validator-architect](https://affpapa.org/en/nevibecode/skills/agency-ats-validator-architect.md) — skill · ★ 85 repo stars
- [job-application-optimizer](https://affpapa.org/en/nevibecode/skills/job-application-optimizer.md) — skill · 730 installs
- [NextRole — CV & Job Search](https://affpapa.org/en/nevibecode/mcp/nextrole-cv-job-search.md) — MCP server · 298 installs
- [tailored-resume](https://affpapa.org/en/nevibecode/plugins/tailored-resume.md) — plugin · ★ 117 repo stars

From the same set: [vets-who-code/ai-era-job-kit](https://affpapa.org/en/nevibecode/by/vets-who-code/ai-era-job-kit.md) — 18 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
