agentleFS
vitaedotaivitaedotai/agent/skills/candidate-screening/SKILL.md

candidate-screening

Skill0 starsChanged 36 days agoMITView on GitHub

Compare candidate evidence with an agreed role scorecard, identify missing information, and prepare a recruiter review without making automatic hiring decisions.

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the selected job brief, the agreed scorecard, and candidate-provided or authorized records.

    line 13

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Candidate screening

Inputs

Use the selected job brief, the agreed scorecard, and candidate-provided or authorized records. Record the source and date for each profile. If the scorecard is missing, establish criteria before evaluating people.

Procedure

  1. Resolve identity and duplicate records. Do not join two people just because their names match.
  2. Extract job-related evidence for each criterion. Preserve short source references so the recruiter can verify the claim. Distinguish “led,” “contributed,” and “observed” where the source supports that distinction.
  3. Apply the agreed anchors only where evidence exists. Mark missing evidence as “not assessed.” A CV omission is not a negative finding.
  4. Identify contradictions and write neutral clarification questions. Avoid speculative explanations for employment gaps or career changes.
  5. Summarize strengths, unresolved requirements, and the next evidence needed. If a stored match score exists, label its source and keep it separate from the evidence assessment.
  6. Return an assessment for human review. Do not automatically reject, advance, or rank candidates based on protected characteristics, health, family circumstances, ethnicity, religion, age, or inferred personality.

Output

For each candidate: record identifier; criterion-by-criterion evidence table; supported rating or not assessed; source; strengths; uncertainties; and targeted follow-up questions. Include a concise recruiter-review summary, not a final employment decision.

Example

Requirement: ownership of production reliability. CV evidence: “Built dashboards for three services.” Assessment: observability contribution evidenced; incident leadership not assessed. Follow-up: “Tell us about an incident you personally investigated, the action you took, and what changed afterward.” Do not rewrite the CV as “owned reliability across three services.”

Quality check

Could another reviewer trace every conclusion to a source? Did missing information stay unknown? Were the same criteria used across candidates? Are any stored or model-generated scores being mistaken for facts?

With Vitae

Use live search_ats_candidates, get_candidate, and get_candidate_resume after selecting the correct record. Read the job through get_job. A recruiter-approved stage change is a separate action with a verified application identifier and the server's approval boundary. Do not move stages as a side effect of writing this report.

Completion and handoff

Give the recruiter the evidence and questions. Continue to candidate-outreach or interview-kit only according to the recruiter's decision and the candidate's current stage.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.