Agent Skill

Candidate Qualification

Evaluate candidate profiles against a job description and hiring criteria with an evidence-based fit score.

Version 1.0 Updated June 2026 SKILL.md MIT 6 min read
View skill source Browse all skills

Overview

What this skill does

Screening candidates against a role is repetitive and easy to do inconsistently, especially across a large shortlist where requirements get weighed differently each time.

This skill applies the same job criteria to every candidate. It separates required from preferred skills, records which requirements are met with evidence, surfaces gaps and risks, and recommends whether to interview — without inferring anything sensitive about the person.

When to use it

Best used for

  • Screening a sourced shortlist against one role
  • Standardizing first-pass candidate review
  • Documenting why a candidate advances or not
  • Spotting must-have requirements that are missing

Know the limits

When not to use this skill

  • You have no structured job description or criteria
  • You need to assess protected characteristics (never do this)
  • The decision requires information not present in the profile

Inputs

Provide these when prompted. The skill asks for anything missing before it runs.

Required

  • A job description
  • Required skills
  • Candidate profiles

Optional

  • Preferred skills
  • Seniority expectations
  • Location or work-authorization requirements
  • Compensation band

Outputs

One record per candidate with a consistent, inspectable schema.

  • candidate_fit_score

    A 0–100 score against the role requirements.

  • required_criteria_matched

    Which mandatory requirements are evidenced.

  • missing_requirements

    Required items not found in the profile.

  • risk_factors

    Concerns to probe in screening (e.g. unexplained gaps).

  • interview_recommendation

    Advance, hold, or pass, with a reason.

Example

Example

A candidate scored against a backend role.

Input

Role: Senior Backend Engineer. Required: 5+ yrs, Go, distributed systems. Preferred: Kubernetes.

Candidate:
- 6 yrs backend, Go + Python
- Built event-driven services
- No Kubernetes mentioned

Output

candidate_fit_score: 82
required_criteria_matched: 5+ yrs (yes); Go (yes); distributed systems (yes)
missing_requirements: none required; Kubernetes (preferred) not evidenced
risk_factors: Kubernetes exposure unclear
interview_recommendation: Advance; confirm Kubernetes familiarity in screen

All required criteria are met, so the candidate advances. The only gap is a preferred skill, flagged as a screening question rather than a disqualifier.

Setup

How to use the skill

General steps first, then notes for specific clients where verified.

  1. 1Download the file using the button below, or copy the Markdown.
  2. 2Place it in a directory named after the skill (e.g. skill-name/).
  3. 3Make sure the filename stays exactly SKILL.md.
  4. 4Add any references or assets included with the package.
  5. 5Load the skill into a compatible agent and provide the required inputs.
Claude Code
  1. 1Create a folder for the skill and save SKILL.md inside it.
  2. 2Place the folder where your project's skills are discovered.
  3. 3Reference the skill when you want it applied to your data.
Other compatible clients
  1. 1Confirm the client supports the open Agent Skills format.
  2. 2Load the SKILL.md file as instructed by that client.
  3. 3If skills are not auto-loaded, paste the Markdown as instructions.

Source

Full SKILL.md source

Read the rendered skill or copy the complete Markdown. The download is generated from this exact source.

Version 1.0 SKILL.md ~2 KB MIT
View on GitHub

Candidate Qualification

Purpose

Evaluate candidate profiles against a job description and hiring criteria with an evidence-based fit score.

When to use this skill

  • Screening a sourced shortlist against one role
  • Standardizing first-pass candidate review
  • Documenting why a candidate advances or not
  • Spotting must-have requirements that are missing

When not to use this skill

  • You have no structured job description or criteria
  • You need to assess protected characteristics (never do this)
  • The decision requires information not present in the profile

Required inputs

  • A job description
  • Required skills
  • Candidate profiles

Optional inputs

  • Preferred skills
  • Seniority expectations
  • Location or work-authorization requirements
  • Compensation band

Rules

  1. Score only against the stated job requirements.
  2. Use evidence from the candidate profile; do not assume unstated experience.
  3. Do not infer health, religion, ethnicity, sexual orientation, political affiliation, or other sensitive personal attributes.
  4. Treat missing required items as gaps, not failures, unless the user marks them disqualifying.
  5. Apply the same criteria to every candidate.

Process

  1. Parse the job description into required and preferred criteria.
  2. Map each criterion to evidence in the candidate profile.
  3. Score required criteria first, then preferred.
  4. List matched requirements, gaps, and risks.
  5. Recommend advance, hold, or pass with a reason.

Output format

Return one record per candidate with the following fields:

  • candidatefitscore
  • requiredcriteriamatched
  • missing_requirements
  • risk_factors
  • interview_recommendation

Validation

  • Confirm each matched requirement cites profile evidence.
  • Confirm no sensitive attributes were inferred.
  • Confirm the recommendation follows from the criteria.

Limitations

  • A profile is not a full assessment; use the score as a screen, not a decision.
  • Self-reported experience may be inaccurate and should be verified.

Before you rely on it

Safety and limitations

  • A profile is not a full assessment; use the score as a screen, not a decision.
  • Self-reported experience may be inaccurate and should be verified.
  • Review the output before acting on it.
  • Do not upload confidential datasets to an external model without authorization.
  • Outputs depend on the model and the source data and are not guaranteed to be accurate.

History

Changelog

  1. v1.0June 2026
    • Initial release.

Questions

Agent Skill FAQ

What candidate information does it need?
A job description with clear required and preferred criteria, plus candidate profiles. The richer the profile, the more criteria it can evidence; thin profiles return more gaps rather than assumptions.
Does this skill make hiring decisions?
No. It produces an evidence-based screen to support a human decision. A recruiter should review every result.
Do I need ProfileSpider to use this skill?
No. The skill works on any compatible data. ProfileSpider is one convenient way to produce that structured input.
Does running this skill send data to ProfileSpider?
No. Downloading or copying the file does not send any data to ProfileSpider. What happens afterward depends on the AI service you load it into.
Are Agent Skills the same as prompts?
No. A skill is a structured, reusable package — task, inputs, rules, process, and output format — so the workflow runs consistently and can be shared, versioned, and edited.

Ready to Extract Structured Leads?

Start free and see how quickly you can build a clean lead list.

Install from Chrome Store

Get started for free