review
Installation
SKILL.md
Contains Shell Commands
This skill contains shell command directives (!`command`) that may execute system commands. Review carefully before installing.
Collect critical, honest feedback from all LLMs on an artifact. Push back on weak arguments. Report both consensus findings and unresolved disagreements.
Phase 0: Load consult-llm skill
Load the consult-llm skill before proceeding — it defines the invocation contract (stdin heredoc, flags, output format, multi-turn). Do not call the CLI without loading it first.
Arguments: $ARGUMENTS
Check the arguments for flags:
Mode flags:
--rounds N→ number of critique rounds (default: 2, max: 3)--dry-run→ skip the final synthesis, just show raw reviews--models <list>→ comma-separated selectors/model IDs to use as reviewers (default:gemini,openai,anthropic,deepseek)
Strip all flags from arguments to get the review target — a file path, directory, or topic description.