consult-llm
Cross-check code decisions with independent second-opinion models
All Skills in This Repository (11)
Pure Emerald Level Indicators
raineworkshop
Orchestrate structured design workshops with multiple LLMs and human critique.
rainedebate-vs
Orchestrate a structured debate between an agent and an opponent LLM to synthesize an implementation plan.
rainepanel
Analyze tasks with asymmetric expert roles to synthesize trade-offs and recommendations.
rainereview-panel
Coordinate parallel multi-model reviews to identify and prioritize code defects.
rainedebate
Coordinate multi-LLM debates with a moderator to synthesize final solutions.
rainephased-implement
Orchestrate phased implementations across Git worktrees with serialized merges.
rainecollab
Orchestrate round-based ideation among multiple LLMs and synthesize a unified plan.
rainereview
Aggregate critical feedback from multiple LLM reviewers into a findings report.
raineimplement
Execute autonomous task workflows with external model review and auditable ledger.
rainecollab-vs
Coordinate alternating-turn brainstorming between two LLMs to synthesize a collaborative plan.
raineconsult
Query external LLMs for second opinions on files with model flags.
Frequently Asked Questions
FAQPage SchemaHow to install consult-llm?▼
Run `npx skills add raine/consult-llm --all -g -y` in your terminal to install all skills in this suite globally.
Why get a second opinion from another model?▼
A model reviewing its own work shares the same training and blind spots, so it is not an independent check. A differently trained model makes different mistakes and is more likely to challenge weak reasoning or catch what the first model missed.
What can I do with consult-llm?▼
You can consult another model on tricky bugs, run multi-model debates on implementation approaches, convene expert panels for design trade-offs, and get independent multi-model code reviews of your diffs.
Which models and backends does consult-llm support?▼
It supports GPT, Gemini, Claude, DeepSeek, MiniMax, Grok, GLM, and any OpenRouter model via API keys. You can also use existing subscriptions through CLI backends like Gemini CLI, Codex CLI, and Claude CLI without API keys.
Does consult-llm work with Claude Code and other coding agents?▼
Yes. The skills install into Claude Code, Codex, OpenCode, and Pi, and are triggered with simple slash commands like /consult, /debate, and /collab.
Related Repositories in Software Engineering
View All in Software Engineering→
openclawopenclaw
Run a personal AI assistant across your devices and chat apps
obrasuperpowers
Gives coding agents a disciplined workflow from idea to merged code
facebookreact
AI agent skills for building, testing, and porting React core