Menu

Individual skill

judge

Obtain an independent review of the approach and trade-offs in completed work.

skills/judge/SKILL.md

Read pinned source

Source commit 1ca181388ad315d332cf0de07ea5fd1b3ccb8372

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
Yes
Skill scan complete
Yes
Observed behavior
Network or broad shell
Last checked
Nov 6, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
11
Repository last updated
Nov 3, 2026
License
CC0-1.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

Review `$ARGUMENTS`, or the latest substantive work when omitted. Infer scope from the conversation and relevant files; ask only if ambiguity would materially change the review.

Delegate to one independent, read-only reviewer with a clean context: the requested outcome, constraints, subject, relevant files, stack, and project conventions. Do not provide your verdict or preferred critique. Add reviewers only for materially distinct expertise. If delegation is unavailable, disclose that limitation; do not call self-review independent.

Ask the reviewer to assess domain fitness, architectural choices, proportionality, and fundamentally different ways to achieve the outcome. Distinguish justified deviations from missed constraints; compare simplicity against real requirements and account for the adoption costs of alternatives. Feature necessity is a separate lens available through `/audit necessity`, not an automatic additional pass.

Retain findings supported by specific evidence, an actionable alternative, and its costs. Distinguish defects, valid trade-offs, and preferences. Remove claims that misread constraints or lack evidence; preserve meaningful disagreements if multiple reviewers were used.

Report a clear recommendation and its rationale, validated strengths, findings by importance, and the single most valuable change, if any. Identify missing evidence and reviewer limitations. Stop after the report; implement only when asked.