SkillAgentSearch skills...

candidate-scorecard

Turn interview notes into a structured candidate scorecard and hire recommendation

Install / Use

npx skills add mohitagw15856/pm-claude-skills --skill candidate-scorecard

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

79/100

Supported Platforms

Universal

Tags

Our assessment of candidate-scorecard

candidate-scorecard scores 79/100 on our quality scale, 2663rd of 4,140 Development & Engineering skills we index.

Its SKILL.md is 3.5 KB long, well organised into 8 sections and no code examples: a solid amount of guidance for an agent.

With 1,396 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
26/30
Structure
13/20
Description
12/15
Adoption
13/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated 6 days ago, so candidate-scorecard is actively maintained.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

candidate-scorecard compared with similar skills

All 4 of these similar skills score higher than candidate-scorecard; compare them before choosing.

SkillScoreStarsUpdatedFormat
candidate-scorecard (this skill)by mohitagw15856791.4k6d agoSKILL.md
ai-job-searchby MadsLorentzen10044.6k1d agoCLAUDE.md
claude-howtoby luongnv8910041.7ktodayCLAUDE.md
algorithmic-artby anthropics100177.9k8d agoSKILL.md
pptxby anthropics100177.9k8d agoSKILL.md

Frequently asked questions

How do I install candidate-scorecard?
Run npx skills add mohitagw15856/pm-claude-skills --skill candidate-scorecard. The install tabs above show the steps for each supported agent.
Which AI agents does candidate-scorecard work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is candidate-scorecard safe to use?
It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is candidate-scorecard still maintained?
The repository was last updated 6 days ago, so candidate-scorecard is actively maintained.

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."

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.)

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.

Related Skills

View on GitHub
GitHub Stars1.4k
CategoryDevelopment
Updated6d ago
Forks249

Languages

HTML

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions