← ClaudeAtlas

comparelisted

Multi-model code review. Fan out a bug or task to multiple LLMs, diff their findings, optionally debate, then dispatch subagents to fix in parallel. Use when the user types /compare or asks to compare models on a code issue.
Cristophereasygoing927/compare-mcp · ★ 2 · AI & Automation · score 75
Install: claude install-skill Cristophereasygoing927/compare-mcp
# /compare skill ## Trigger User types: `/compare <issue description> [--debate] [--providers claude,openai]` Or naturally: "compare models on this bug", "get a second opinion from multiple models" ## Workflow ### Step 1 — discover Call `compare_models` to show the user which providers are enabled. If fewer than 2 are enabled, stop and tell the user: > Enable at least 2 providers in `~/.compare/config.json`. Run `compare_models` to check. ### Step 2 — read code Use the Read tool to load the relevant file(s). If the user didn't specify a file, use Glob + Grep to find the most relevant file for the issue description. Respect `max_file_lines` from config (default 1000). If the file is larger, ask the user to specify a line range or pass the most relevant section. ### Step 3 — dispatch Call `compare_run` with the file contents and issue description. If `--providers` was specified, pass the provider list. While waiting, tell the user: "Querying [provider1], [provider2]... (parallel)" ### Step 4 — diff Call `compare_diff` with the responses. Display a findings table: ``` Finding | Providers | Severity --------------------------|------------------|---------- Memory leak in tile loop | claude, openai | high Dead code: prevVisible | openai | medium ``` Show: "Models agreed on X% of findings." ### Step 5 — debate (if `--debate` flag or user asks) Call `compare_debate` with the responses. Display: "Debate complete. [N] findings dispute