Is the Candidate Screening skill free?

Yes. The skill itself is free from dazuck/operator-skills. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Candidate Screening SkillProof Score?

9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.

How do I install Candidate Screening?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Candidate Screening with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Candidate Screening

Scores job applicants against 8 universal hire-bar traits, not just a resume checklist

by dazuck · dazuck/operator-skills

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.6/10
Tested: Jul 15, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 9d1fa4f

Ran both a generic resume review and the skill's 8-trait framework on two synthetic applications; the baseline called both candidates 'relevant, interview optional', while the skill's framework flagged the passive-language candidate ('was responsible for', 'worked closely with the team') as a hard Pass using the exact red-flag pattern the doc names, and gave the self-initiated, metric-backed candidate a Must Interview with cited evidence per trait.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 9/10
Docs & honesty 5/5

What Candidate Screening does

Screens Greenhouse (or manually-supplied) job applicants against 8 universal traits — high agency, grit, evidence of impact, technical depth, AI-nativeness, communication, world-class-at-something, and being an interesting person — plus role-specific criteria, producing a scored table and a Must Interview / Worth Exploring / Pass verdict. Triggers on 'screen candidates', 'review applicants', 'run candidate screening', 'check new applications', or 'evaluate candidates'.

How to install Candidate Screening

git clone https://github.com/dazuck/operator-skills
cd operator-skills
mkdir -p ~/.claude/skills
cp -r skills/candidate-screening ~/.claude/skills/candidate-screening

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Candidate Screening

/candidate-screening Scores job applicants against 8 universal hire-bar traits, not just a resume checklist

It also activates on plain-language prompts like these:

Screen these two Full-Stack Engineer applicants against our hire-bar traits
Review new Greenhouse applications and flag who's worth interviewing
Evaluate this candidate's resume for agency, grit, and evidence of impact

Frequently asked questions

Is the Candidate Screening skill free?: Yes. The skill itself is free from dazuck/operator-skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Candidate Screening work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Tested · Works. Ran both a generic resume review and the skill's 8-trait framework on two synthetic applications; the baseline called both candidates 'relevant, interview optional', while the skill's framework flagged the passive-language candidate ('was responsible for', 'worked closely with the team') as a hard Pass using the exact red-flag pattern the doc names, and gave the self-initiated, metric-backed candidate a Must Interview with cited evidence per trait.
What is the Candidate Screening SkillProof Score?: 9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
How do I install Candidate Screening?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Candidate Screening with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.