— Talent & Leadership

Candidate Comparison

Compares candidates against a shared, role-specific rubric, producing an evidence-backed assessment of their relative fit, key differentiators and trade-offs.

  • Talent & Leadership
  • Traceable reasoning
  • Runs anywhere
Preview methodology

1–2 weeks → ~15 minutes

For a typical multi-document review workflow

No coding required

Input
CVs or dossiers for two or more candidates
Output
Shared assessment rubric with quotations from the role brief supporting each criterion
Runs in
Skillsize · ChatGPT · Claude · Copilot
Export
SKILL.md · MCP
Time saved
~1–2 weeks per run

— USE CASES

What people use Candidate Comparison for

Shortlist decisions

Provides a ranked comparison of candidates against the same role requirements, with evidence supporting each score. Makes the reasons for relative fit explicit.

Closely matched candidates

Highlights the differentiators and trade-offs between candidates with similar profiles, giving decision-makers a clearer view of where their documented strengths diverge.

Client hiring recommendations

Provides a findings report and comparison matrix that consultants can use to support a hiring recommendation, with assessments traceable to the role brief and candidate materials.

Hiring panel discussions

Gives assessors a shared, evidence-backed reference for discussing candidate fit, keeping the comparison anchored in the stated role requirements.

What it works from

  • CVs or dossiers for two or more candidates
  • Job description or role brief
  • Documented candidate experience and qualifications

What you get back

  • Shared assessment rubric with quotations from the role brief supporting each criterion
  • Candidate scores by criterion with verbatim supporting evidence
  • Candidate ranking with key differentiators and trade-offs
  • Comparison matrix available in CSV format

— HOW IT BEHAVES

How Candidate Comparison produces its result

The mechanics behind this specific template — what it reads, what it calculates, and where a human stays in the loop.

Whole sets of CVs, applications and interview notes at once

All of your CVs, applications and interview notes is processed as one set, so patterns across documents surface instead of being read one file at a time.

Composed as work product

Findings on the candidate pool are written up as a document that reads like professional output, with each claim tied back to a candidate.

Delivered as a working table

The candidates land as a clean table you can sort, filter or drop straight into the deliverable.

Why this is expensive by hand

Candidate comparisons become difficult when CVs emphasise different strengths and assessors apply different standards. In practice it shows up as shortlist decisions: provides a ranked comparison of candidates against the same role requirements, with evidence supporting each score. Makes the reasons for relative fit explicit. It is the kind of work that decides whether a recommendation survives scrutiny — and the kind that quietly eats 1–2 weeks of senior time whenever it comes round.

How this Skill produces it

As a Skill, the work is already sequenced. You bring the evidence, and the run produces shared assessment rubric with quotations from the role brief supporting each criterion plus candidate scores by criterion with verbatim supporting evidence. The judgement is built in — how items are broken up, what standard they are held to, and where the run stops for a human review. Net effect: 1–2 weeks down to ~15 minutes, no drift between runs, and every conclusion traceable back to the evidence behind it.

Who it's for

  • CHROs and talent management leads
  • Succession and leadership development teams
  • Executive assessors and coaches
  • Consultants running talent reviews

Run it in Skillsize — or export it anywhere

Candidate Comparison exports as a structured SKILL.md file and is MCP-ready, so the same method runs in ChatGPT, Claude, Copilot or your own AI products. Adapt it to your methodology, and the intelligence stays yours — not locked to one vendor.

ChatGPTClaudeCopilotAI Products (MCP)