Candidate Scorecard

SKILL.md

---
name: candidate-scorecard
description: "Turn interview notes into a structured candidate scorecard and hire recommendation. Use when asked to write an interview scorecard, a candidate evaluation, an interview debrief, or to summarize feedback into a hire/no-hire call. Produces a per-competency assessment with evidence and ratings, an overall recommendation with confidence, and the open questions for the next round — evidence-based, bias-aware, and decision-ready."
homepage: https://mohitagw15856.github.io/pm-claude-skills/skill/candidate-scorecard.html
metadata:
  {
    "openclaw": { "emoji": "🧲" }
  }
---

# Candidate Scorecard Skill

A scorecard converts a fuzzy "I liked them" into an evidence-based, comparable evaluation. It rates the
candidate against the **same competencies** the role defined, ties each rating to **specific evidence** from the
interview, and lands a clear recommendation — so debriefs are about evidence, not who argues hardest. (For the
role's question set and competencies, pair with [`interview-question-bank`](../interview-question-bank/SKILL.md).)

## Working from a brief

Given rough interview notes, **produce the full scorecard anyway** — organize the evidence under the relevant
competencies and give a rating + recommendation, marking where evidence is thin *(low confidence / probe next
round)*. Never invent things the candidate said; if a competency wasn't assessed, say so rather than guessing.

## Required Inputs

Ask for these only if they aren't already provided (else mark as not assessed):

- **The role & competencies** — what's being assessed (or use the role's interview kit).
- **Interview notes** — what the candidate said/did, ideally with examples.
- **The interview scope** — which round/competencies this interviewer covered.
- **Scale** — the rating scale to use (e.g. 1–4: strong no / no / yes / strong yes).

## Output Format

### Candidate Scorecard: [name] — [role]

- **Summary** — one-line read: overall rating and the headline reason.
- **Per-competency assessment** — for each competency assessed:

| Competency | Rating | Evidence (what they said/did) | Concern / gap |
|---|---|---|---|

  Mark any competency you couldn't assess as **Not assessed**.
- **Strengths** — the 2–3 clearest, evidence-backed.
- **Risks / gaps** — the real concerns, with the evidence (not vibes).
- **Open questions for next round** — what to probe to resolve uncertainty.
- **Recommendation** — Hire / No hire / Lean yes / Lean no, with a **confidence level** and the one-sentence rationale.

## Quality Checks

- [ ] Every rating is tied to specific evidence from the interview, not impressions
- [ ] Competencies not actually assessed are marked "Not assessed", not guessed
- [ ] Strengths and risks are concrete and balanced — not a one-sided narrative
- [ ] The recommendation states a confidence level and what would change it
- [ ] Open questions hand the next interviewer something specific to probe
- [ ] No invented quotes/claims; bias-prone "culture fit" is replaced with job-related evidence

## Anti-Patterns

- [ ] Do not rate on overall vibe — anchor each score to what the candidate actually demonstrated
- [ ] Do not invent or embellish what they said to justify a rating
- [ ] Do not score competencies you didn't test — flag them for the next round
- [ ] Do not hide low confidence behind a confident-sounding verdict — say how sure you are
- [ ] Do not lean on "culture fit" as a reason — name the specific, job-related concern

## Based On

Structured-hiring practice — competency ratings anchored to evidence, calibrated recommendations with confidence, and bias-aware, decision-ready debriefs.