# Spec Driven Eval

Scores how completely an implementation fulfills a PRD/spec, case by case, and produces...

- Repository: https://github.com/tech-leads-club/agent-skills (7121 stars)
- Category: Testing
- License: CC-BY-4.0
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add tech-leads-club/agent-skills --skill spec-driven-eval -g -a claude-code -y`
Codex: `npx skills add tech-leads-club/agent-skills --skill spec-driven-eval -g -a codex -y`
Cursor: `npx skills add tech-leads-club/agent-skills --skill spec-driven-eval -g -a cursor -y`
Gemini CLI: `npx skills add tech-leads-club/agent-skills --skill spec-driven-eval -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add tech-leads-club/agent-skills`

## Description

Scores how completely an implementation fulfills a PRD/spec, case by case, and produces a single comparable final grade. Invoke only when explicitly named (e.g. run spec-driven-eval); do not auto-trigger. Use when benchmarking spec-driven implementations, grading acceptance criteria, evaluating whether a feature was 100% implemented, comparing multiple implementations of the same PRD, or auditing implementation and test coverage (unit and e2e) against product requirements. Do NOT use for planning or building features (use tlc-spec-driven), writing PRDs, or general code review unrelated to a spec.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Spec-Driven Implementation Evaluation

Evaluate a spec-driven-development (SDD) effort against a PRD **case by case** (acceptance criterion by acceptance criterion), scoring **implementation** and **tests** separately, and roll up to a single comparable final grade. Designed for benchmarking: the same PRD evaluated across different SDD frameworks, and the same effort evaluated twice, must yield comparable, reproducible numbers.

### Two subjects, two questions

This eval answers two independent questions, and keeps their verdicts separate because they fail independently:

1. **How good is the framework at respecting and extracting requirements?**, Did it honor the PRD and stay in bounds (*respect*: `Final` implementation side + Scope `S`), and did it surface the implicit requirements the PRD only implied, without noise (*extract*: Elicitation `E`)?
2. **How good is the harness at ensuring they are all implemented?**, Does the test suite prove every sanctioned requirement is actually built (`T` + Engineering Gates `G`)?

> **The linkage that makes "all implemented" well-defined:** the harness is held accountable for the **full sanctioned requirement set = `PRD acceptance criteria ∪ valid E-additions`**. A valid requirement the framework extracted but the harness never tests is a *harness* miss (`T`), not a framework miss (`E` keeps the extraction credit). Extraction defines the verification target.

Scoring is **checklist-based**: every criterion is decomposed into atomic binary (MET / UNMET) checks, each backed by `file:line` evidence. Binary decomposition is the design choice that makes the grade reproducible, graded/Likert scales (`is this a 3 or a 4?`) are the dominant source of evaluator-to-evaluator disagreement; binary checks raise inter-evaluator agreement to roughly human level. Partial credit is **derived** from the fraction of checks met, never judged on a sliding scale.

## When to use

The rest: https://github.com/tech-leads-club/agent-skills/blob/HEAD/packages/skills-catalog/skills/(development)/spec-driven-eval/SKILL.md