Stats
Actions
Tags
From ask-llm
This skill should be used when the user asks to "review my code with multiple providers", "get reviews from Gemini and Codex", "multi-provider review", "review changes", or wants independent code reviews from both Gemini and Codex in parallel.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ask-llm:multi-reviewThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Run independent code reviews from Gemini and Codex in parallel, then present combined validated findings with consensus highlighting.
Run independent code reviews from Gemini and Codex in parallel, then present combined validated findings with consensus highlighting.
Gather the diff to review:
git diff to get unstaged changesgit diff --cached to get staged changesIf the diff is empty, inform the user there are no changes to review.
Launch both agents in parallel using the Agent tool in a single message:
gemini-reviewer agent with the diff contentcodex-reviewer agent with the diff contentOnce both agents complete, present a combined summary:
Consensus (flagged by BOTH providers):
Gemini only:
Codex only:
Contradictions:
Validation stats:
npx claudepluginhub lykhoyda/ask-llm --plugin ask-llmRuns parallel code reviews with Codex, Gemini, and Claude on git diffs or files, generating an integrated report for multi-AI perspectives.
Runs code reviews via external LLMs (OpenAI Codex CLI, Google Gemini CLI) on uncommitted changes, branch diffs, or commits using git and bash.
Orchestrates multi-agent code review with Codex CLI, Gemini CLI, and five Claude specialist subagents (security, performance, logic, regression, robustness) then synthesizes findings into verified fixes. Use for deep reviews, second opinions, or council reviews on PRs, commits, or branches.