# Pprose Eval

> Score one practical document with metrics and rubric grading; read-only on source. Use when asked to score, evaluate, grade, rubric-check, or measure quality.

- Skill: `jlevy/pprose-eval` (Agent Skill)
- Install (CLI): `npx skillmds@latest add jlevy/pprose-eval`
- Raw SKILL.md: https://api.skillmd.com/api/skills/jlevy/pprose-eval/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: jlevy (https://skillmd.com/u/jlevy)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/jlevy/pprose-eval

---

<!-- DO NOT EDIT: generated by `pprose install` (format=f02) -->

> Run pprose as `pprose <command>` if on PATH, else `uvx pprose@0.4.0 <command>`
> (zero-install via uv).
> Run `pprose --help` for every command, `pprose skill` for the other Practical Prose
> skills, and `pprose list` for all on-demand playbooks, style guides, and procedures
> (`pprose shortcut`, `pprose guidelines`, `pprose runbook` each print one by name).

# Evaluate One Practical Prose Document

This is read-only on the source document.
It writes eval report files.

Use it when the user wants a formal Practical Prose evaluation of one document.

## Inputs

- Path to one Markdown artifact.
- Artifact label.
- Scope class: `status`, `memo`, `brief`, `deep_research`, or `design_doc`.
- `ANTHROPIC_API_KEY` for model scoring, unless the user asks for dry-run or manual
  scoring only.

## Steps

1. Run `pprose runbook practical-prose-eval-single` for the full procedure.

2. If the artifact is a comprehensive practical guide (a reference work helping readers
   navigate a complex topic), read `pprose guidelines writing-practical-guides` for
   genre context before scoring; the rubric’s anchors scale with purpose, audience,
   genre, and risk level.

3. Generate the eval stub:

   ```bash
   pprose report from-metrics path/to/artifact.md --label NAME --scope-class brief --out artifact.eval.md
   ```

4. Inspect deterministic metrics:

   ```bash
   pprose metrics path/to/artifact.md --format yaml
   ```

5. Score the qualitative dimensions (`--model` is required; run
   `pprose score --list-models` for choices, or pass `--dry-run` to skip the API call):

   ```bash
   pprose score artifact.eval.md --model opus
   ```

6. Validate the result:

   ```bash
   pprose report validate artifact.eval.md --complete
   ```

## Output

Return the eval report path, validation result, and any scoring or alignment issues that
need human review.