ask-llm

Review the current code changes specifically with OpenAI GPT-5.6 Sol. Use when the user asks for a Sol review, says "review with Sol", wants a model-pinned Codex review, or invokes /sol-review.

Generate an image via OpenAI's gpt-image-2 model through the Codex CLI. Use when user asks to "generate an image", "create an image", "make a picture of", "render a graphic", "draw something", or wants visual content via Codex. Requires codex-cli >= 0.125.0 with the `image_generation` feature flag enabled (stable + on-by-default since 0.125).

This skill should be used when the user asks to "compare LLMs", "see how each provider answers", "side-by-side response", "what do Gemini, Codex, Ollama, and Antigravity think", or wants raw responses from multiple providers without synthesis. Unlike /brainstorm (which synthesizes findings) or /multi-review (which validates code reviews), /compare just shows each provider's answer side-by-side.

Get a second opinion from Google Antigravity (agy) on your current code changes. Analyzes staged/unstaged diffs and returns prioritized findings. Use when the user asks to "review with Antigravity", "Antigravity code review", or "ask agy to check my code".

Show codex-pair status and set up the per-edit Codex review hook for this project. Detects whether codex-pair is active, paused, or not yet configured. On first run (no marker), offers interactive setup with auto-detected project context. On subsequent runs, shows current state, recent review activity, and toggle instructions. The per-edit hook itself runs automatically; this command is the human-facing dashboard for it.

Request a review of the current code changes from the Fable model. Use when the user asks for a Fable review, says "review with Fable", wants Fable's independent perspective on a diff, or invokes /fable-review.

Get a second opinion from OpenAI Codex on your current code changes. Analyzes staged/unstaged diffs and returns prioritized findings. Use when user asks to "review with Codex", "Codex code review", or "ask Codex to check my code".

Resume the codex-pair PostToolUse hook for this project after a previous /codex-pair-pause. Removes the .codex-pair/state/paused sentinel. The hook starts reviewing edits again on the next Edit/Write/MultiEdit. No-op if no pause sentinel exists.

Pause the codex-pair PostToolUse hook for this project without removing the .codex-pair/context.md marker. Writes a .codex-pair/state/paused sentinel that the hook checks on every Edit/Write/MultiEdit. Use when you want to temporarily silence reviews — running a noisy refactor, dogfooding the hook itself, working on docs-only changes, etc. — and resume later with /codex-pair-resume.

Use when the user wants to defer a codex-pair HIGH finding so the Stop-gate stops blocking turn-end. Records an acknowledgement in .codex-pair/state/acks.json keyed by the 16-char hash printed in the gate's block message. Usage /codex-pair-ack <hash> "<reason>".

Send a topic to multiple LLM providers in parallel while Claude Opus performs its own independent research in parallel, then synthesize all findings. Usage /brainstorm [providers] <topic>. External providers default to antigravity,codex. Example /brainstorm antigravity,codex,ollama "review this architecture"

Send a topic to ALL LLM providers (Gemini, Codex, Ollama, Antigravity) in parallel while Claude Opus performs its own independent research in parallel. Synthesizes findings from up to five participants. Shortcut for /brainstorm gemini,codex,ollama,antigravity <topic>. Requires Ollama running locally and agy installed for the Antigravity participant.

This skill should be used when the user asks to "review my code with multiple providers", "get reviews from Antigravity and Codex", "multi-provider review", "review changes", or wants independent code reviews from both Antigravity and Codex in parallel.

Verifies what the assistant claims to have done — proves the work against actual state using OpenAI Codex with a read-only tool surface. Use when the user asks to "verify with Codex", "check the assistant's claims", "did Codex actually do what it said", "verify this turn", "prove the work", or wants a trust check distinct from issue review. Different from `/codex-review`, which finds new issues.

Get a second opinion from Gemini on your current code changes. Analyzes staged/unstaged diffs and returns prioritized findings. Use when user asks to "review with Gemini", "Gemini code review", or "ask Gemini to check my code".

Get a second opinion from a local Ollama LLM on your current code changes. Analyzes staged/unstaged diffs and returns prioritized findings. No API keys needed. Use when user asks to "review with Ollama", "local code review", or "review offline".