Skill

multi-review

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.

npx claudepluginhub lykhoyda/ask-llm --plugin ask-llm

Tool Access

This skill uses the workspace's default tool permissions.

Preview

Run independent code reviews from Gemini and Codex in parallel, then present combined validated findings with consensus highlighting.

SKILL.md

Similar Skills

multi-ai-review

Runs parallel code reviews with Codex, Gemini, and Claude on git diffs or files, generating an integrated report for multi-AI perspectives.

5 files

multi-ai-review

second-opinion

5.1k

Runs code reviews via external LLMs (OpenAI Codex CLI, Google Gemini CLI) on uncommitted changes, branch diffs, or commits using git and bash.

3 files5 tools

second-opinion

second-opinions

113

Gets second opinions from OpenAI Codex and Google Gemini on code reviews, plans, docs, codebase analysis, or tasks. Uses git diffs, file access, and custom tools.

2 files13 tools

hal-skills

Stats

Parent Repo Stars9

Parent Repo Forks3

Last CommitApr 2, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Multi-Provider Code Review

Run independent code reviews from Gemini and Codex in parallel, then present combined validated findings with consensus highlighting.

Instructions

Gather the diff to review:

Run git diff to get unstaged changes
Run git diff --cached to get staged changes
Combine both into a single diff

If 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 content
codex-reviewer agent with the diff content
Each agent performs its own 4-phase pipeline: Context → Prompt → Synthesis → Validation

Once both agents complete, present a combined summary:

Consensus (flagged by BOTH providers):

These have the highest confidence — two independent models agree
List each with both confidence scores

Gemini only:

Issues only Gemini flagged (with confidence score)

Codex only:

Issues only Codex flagged (with confidence score)

Contradictions:

Any cases where providers disagree about the same code

Validation stats:

How many issues each provider flagged vs how many survived validation

Multi-Provider Code Review

Run independent code reviews from Gemini and Codex in parallel, then present combined validated findings with consensus highlighting.

Instructions

Gather the diff to review:
- Run git diff to get unstaged changes
- Run git diff --cached to get staged changes
- Combine both into a single diff
If 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 content
- codex-reviewer agent with the diff content
- Each agent performs its own 4-phase pipeline: Context → Prompt → Synthesis → Validation
Once both agents complete, present a combined summary:

Consensus (flagged by BOTH providers):
- These have the highest confidence — two independent models agree
- List each with both confidence scores
Gemini only:
- Issues only Gemini flagged (with confidence score)
Codex only:
- Issues only Codex flagged (with confidence score)
Contradictions:
- Any cases where providers disagree about the same code
Validation stats:
- How many issues each provider flagged vs how many survived validation