Interview Judge — Development agent for Claude Code
Scores a finished simulated interview against the fixture answer key and the artifacts it produced.
How to install Interview Judge
Installs to ~/.claude/agents/mwellis81-spec-factory-interview-judge.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/mwellis81/spec-factory/HEAD/agents/interview-judge.md -o ~/.claude/agents/mwellis81-spec-factory-interview-judge.md Restart Claude Code, or start a new session, for it to be picked up.
What Interview Judge does
name: interview-judge description: Scores a finished simulated interview against the fixture answer key and the artifacts it produced. model: opus tools: Read
You grade an interview after a simulated run, so the factory can tell a real interrogation from a polite one. You judge the questions, never the product.
Read, in this order:
- The transcript you were given, under
docs/factory/interviews/. specfactory.config.yamlforfixture:, thenfixtures//answer-key.md. 3
Alternatives in Development
- Owner Judge — Reviews proposed changes to VoiceStudio against the owner's documented standards 41.3k ★
- Civitai Intent Review — Scores a feature segment in the main Civitai Next.js app (src/) against the intent doc for the work — did the 7.2k ★
- Skill Verify Auditor — Rubric compliance auditor for skill Self-Verify steps (dispatch marker skill-verify: ) 57 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Himcm Judge
Strict, independent HiMCM judge. Scores a finished solution paper section by section (1-10) against judging-gu
Learn Assessor
Blind grader for the learning system (teach / tutor / level-up). Grades ONE learner answer against a frozen, v
Output Auditor
The quality gate. Scores artifacts against a published rubric, verifies every citation against the ledger, and
Faktenpruefer
Independent fact checker with fresh context. Takes a finished answer, report, or text and checks each factual
Habit Judge
Read-only verifier that scores a session, a diff, or a transcript against a habit set and returns an evidence-
Plan Judge
Independent reviewer that scores an implementation plan against the fixed plan-quality rubric and returns spec
Related Skills
Evolve Skill
SPIKE — GEPA/DSPy-style offline A/B evolution of ONE prompt-only skill's SKILL.md body against a small fixture
Ralph Output Adversarial Review
Adversarially reviews the artifacts produced by a RALPH run (code/tests/UI/config) against repo policy (testin
Hackathon Judge
Evaluate a hackathon project against the official "Built with Opus 4.6" judging criteria. Scores demo, impact,