Run pprose as
pprose <command>if on PATH, elseuvx pprose@0.1.0 <command>(zero-install via uv). Runpprose --helpfor every command,pprose skill --listfor the other Practical Prose skills, andpprose shortcut --list/pprose guidelines --list/pprose runbook --listfor on-demand playbooks, style guides, and procedures.
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.
For the repo’s baseline batch evals, run pprose runbook practical-prose-baseline-evals
and default to running all third-party and self-eval artifacts unless the user asks for
a subset.
Inputs
- Path to one Markdown artifact.
- Artifact label.
- Scope class:
status,memo,brief,deep_research, ordesign_doc. ANTHROPIC_API_KEYfor model scoring, unless the user asks for dry-run or manual scoring only.
Steps
Run
pprose runbook practical-prose-eval-singlefor the full procedure.Generate the eval stub:
pprose report from-metrics path/to/artifact.md --label NAME --scope-class brief --out artifact.eval.mdInspect deterministic metrics:
pprose metrics path/to/artifact.md --format yamlScore the qualitative dimensions (
--modelis required; runpprose score --list-modelsfor choices, or pass--dry-runto skip the API call):pprose score artifact.eval.md --model opusValidate the result:
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.