---
name: GSD Eval Review
slug: gsd-eval-review
category: Quality
description: "GSD Eval Review audits a completed AI phase's evaluation coverage against the plan in AI-SPEC.md and produces an EVAL-REVIEW.md remediation plan. Use it after executing an AI phase to verify whether the evaluation strategy was implemented."
github: "https://github.com/open-gsd/gsd-core/tree/next/skills/gsd-eval-review"
language: JavaScript
stars: 8257
forks: 573
install: "npx degit https://github.com/open-gsd/gsd-core/tree/next/skills/gsd-eval-review ~/.claude/skills/gsd-eval-review"
installs_to: ~/.claude/skills/gsd-eval-review
source_path: skills/gsd-eval-review/SKILL.md
collection_size: 25
category_size: 1354
collection_url: "https://dirskills.com/collections/open-gsd/gsd-core"
added: 2026-08-15T06:51:02.013Z
last_synced: 2026-08-15T06:51:02.013Z
canonical_url: "https://dirskills.com/skills/gsd-eval-review"
---

# GSD Eval Review

GSD Eval Review audits a completed AI phase's evaluation coverage against the plan in AI-SPEC.md and produces an EVAL-REVIEW.md remediation plan. Use it after executing an AI phase to verify whether the evaluation strategy was implemented.

**Install:**

```bash
npx degit https://github.com/open-gsd/gsd-core/tree/next/skills/gsd-eval-review ~/.claude/skills/gsd-eval-review
```

## README

<objective>
Conduct a retroactive evaluation coverage audit of a completed AI phase.
Checks whether the evaluation strategy from AI-SPEC.md was implemented.
Produces EVAL-REVIEW.md with score, verdict, gaps, and remediation plan.
</objective>

<execution_context>
@~/.claude/gsd-core/workflows/eval-review.md
@~/.claude/gsd-core/references/ai-evals.md
</execution_context>

<context>
Phase: $ARGUMENTS — optional, defaults to last completed phase.
</context>

<process>
Execute end-to-end.
Preserve all workflow gates.
</process>