review-spec

# Review Spec Run two AI spec reviews in parallel and return combined findings. ## Step 1: Identify the Spec Determine the spec to review using these rules in order: 1. **Spec text in conversation** — If full spec text is already in context, use it 2. **Explicit path** — If a file path was provided, read it 3. **Explicit slug** — If a slug was provided, resolve to `.turbo/specs/<slug>.md` 4. **Single file** — Glob `.turbo/specs/*.md`. If exactly one file exists, read it 5. **Most recent** — If multiple files exist, read the most recently modified 6. **Legacy fallback** — If `.turbo/specs/` does not exist but `.turbo/spec.md` exists, use it 7. **Nothing found** — If no spec exists, say so and stop If multiple files exist and the most-recent choice is non-obvious, use `AskUserQuestion` to let the user pick from the candidates. ## Step 2: Run Two Reviews in Parallel Launch two Agent tool calls in a single message so they run concurrently (`model: "opus"`, do not set `run_in_background`): ### Internal Spec Review Spawn a subagent with the full spec text and instruct it to: 1. Read project context (CLAUDE.md and any existing codebase) to understand constraints 2. Apply the spec determination criteria below 3. Return findings in the output format below ### Run `/peer-review` Skill Spawn a subagent whose prompt includes the full spec text and the following review prompt, and instructs it to invoke `/peer-review` via the Skill tool: ``` <task> Review the following specif...