Menu
Run a multi-angle code review using three specialist agents in parallel. Use when the user types /review or when finishing a code task.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Write or rewrite copy that sounds human. Kills generic AI filler, asks for specifics before writing, and pushes back on vague prompts. Use when writing marketing copy, landing pages, blog posts, event descriptions, or any user-facing text.
enforce the iron laws on all written output. activate when writing, editing, or reviewing any text including copy, emails, taglines, descriptions, blog posts, social media, proposals, bios, documentation, README files, commit messages, code comments, UI strings, error messages, PR descriptions, changelogs, or any content task. also activate when the user asks for feedback on existing writing.
enforce the iron laws on all written output. activate when writing, editing, or reviewing any text including copy, emails, taglines, descriptions, blog posts, social media, proposals, bios, documentation, or any content task. also activate when the user asks for feedback on existing writing. these rules override default chatgpt writing style.
Ten rules that stop AI from writing like AI. Activate on any writing, editing, or copy review task. Overrides default writing style with specific, human-sounding output.
Structured 4-phase workflow for non-trivial tasks. Enforces Understand, Plan, Execute, Verify phases with quality gates.
| name | review |
| description | Run a multi-angle code review using three specialist agents in parallel. Use when the user types /review or when finishing a code task. |
| argument-hint | ["file or area"] |
Run a multi-angle code review on the current branch using three specialist agents in parallel.
Type /review to review all changes on the current branch against main. Or /review <specific file or area> to narrow the scope.
Launches three agents simultaneously, each reviewing the same diff from a different angle:
Each agent runs on Sonnet for speed. Results are consolidated into a single report.
Determine the review target:
$ARGUMENTS is empty, review the full diff of the current branch against main$ARGUMENTS names a file or directory, scope the review to that areamain with uncommitted changes, review the working tree diffgit diff main...HEAD --stat
git diff main...HEAD
If $ARGUMENTS specifies a scope, filter to those paths.
Launch all three agents in parallel using the Agent tool with run_in_background: true:
Agent 1: Code Review
Agent 2: Security Audit
Agent 3: Architecture Review
Once all three agents complete, present a single report:
## Review Results
### Critical (fix before merge)
- [list any critical findings from all three agents]
### Important (should fix)
- [list important findings]
### Suggestions (nice to have)
- [list suggestions]
### Clean
- [note any areas all three reviewers found no issues with]
If all three agents find nothing, say so: "All three reviewers passed. No issues found."
After presenting results, ask: