msd-core/commands/gsd/eval-review.md at a24de43f8bf4d42affc8ca2e788086aa8a2f9e0c

Files

Tom Boucher e81592878e feat(#2789 ): trim skill description anti-patterns; enforce 100-char budget (#2823 )

* feat(#2789): trim skill description anti-patterns; enforce 100-char budget

- Trim descriptions in all commands/gsd/*.md files over 100 chars
- Remove flag documentation from descriptions (belongs in argument-hint)
- Remove Triggers: keyword stuffing
- Add scripts/lint-descriptions.cjs — fails on descriptions > 100 chars
- Add npm script: lint:descriptions
- Add tests/enh-2789-description-budget.test.cjs

Closes #2789

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* docs(#2789): add CHANGELOG entry for description budget lint

* docs(#2789): update COMMANDS.md descriptions; add skill description standards note

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-04-29 08:14:11 -04:00

854 B

Raw Blame History

name, description, argument-hint, allowed-tools

name

description

argument-hint

allowed-tools

gsd:eval-review

Audit an executed AI phase's evaluation coverage and produce an EVAL-REVIEW.md remediation plan.

[phase number]

Read

Write

Bash

Glob

Grep

Task

AskUserQuestion

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.

<execution_context> @~~/.claude/get-shit-done/workflows/eval-review.md @~~/.claude/get-shit-done/references/ai-evals.md </execution_context>

Phase: $ARGUMENTS — optional, defaults to last completed phase. Execute @~/.claude/get-shit-done/workflows/eval-review.md end-to-end. Preserve all workflow gates.

854 B Raw Blame History

854 B

Raw Blame History