UTM/.claude/commands/utm-review.md at main

mirror of https://github.com/utmapp/UTM.git synced 2026-10-11 21:59:56 +00:00

Files

T

osy fb61bfe86a docs: add /utm-review and /utm-submit agent contribution workflows

Add agent-neutral workflows that walk an AI coding tool through reviewing a
change against the contribution guidelines and then opening or updating a pull
request to utmapp/UTM with the required AI attribution and human-testing
attestation.

The canonical instructions live in .agents/skills/ (auto-discovered by Codex,
Cursor, Amp, Zed, Copilot, Windsurf, OpenCode, Antigravity, and others), with
thin slash-command shims for Claude Code (.claude/commands/) and OpenCode
(.opencode/command/). AGENTS.md is trimmed to the essentials and points at the
workflows, and CONTRIBUTING.md now directs contributors to use them.

Assisted-by: Claude:claude-opus-4-8

2026-06-09 00:07:02 +08:00

580 B

Raw Permalink Blame History

description, argument-hint, allowed-tools

description

argument-hint

allowed-tools

Review pending UTM changes (standard code review + CONTRIBUTING.md/AGENTS.md audit) before submitting. Run before /utm-submit.

low|medium|high|max

Bash, Read, Grep, Glob, Skill, Task

Read and follow the canonical, agent-neutral workflow in .agents/skills/utm-review/SKILL.md, executing its steps end to end.

Claude Code specifics:

For the Step 3 standard code review, invoke the code-review skill at the effort level passed here (default high).
Argument passed to this command (review effort, if any): $ARGUMENTS

580 B Raw Permalink Blame History

580 B

Raw Permalink Blame History