agentganggang-compare-workflowslisted

# AgentGangGang Compare Workflows Teach the agent how to install, connect, and use AgentGangGang as a compare-first browser workspace. ## Use this skill when - the user wants to compare the same prompt across multiple already-open AI chat tabs - the host can run a local MCP server - the user wants one inspectable compare artifact before broader automation ## What this package teaches - how to wire the local AgentGangGang MCP sidecar into a host - which MCP tools are safe and useful first - how to move from readiness checks to a real compare turn - how to keep the workflow grounded in a browser-native compare product ## Start here 1. Read [references/INSTALL.md](references/INSTALL.md) 2. Load the right host config from: - [references/OPENHANDS_MCP_CONFIG.json](references/OPENHANDS_MCP_CONFIG.json) - [references/OPENCLAW_MCP_CONFIG.json](references/OPENCLAW_MCP_CONFIG.json) 3. Skim the tool surface in [references/CAPABILITIES.md](references/CAPABILITIES.md) 4. Run the demo from [references/DEMO.md](references/DEMO.md) ## Recommended workflow 1. `agentganggang.bridge_status` 2. `agentganggang.check_readiness` 3. `agentganggang.compare` 4. `agentganggang.analyze_compare` 5. `agentganggang.run_workflow` ## Suggested first prompt Use AgentGangGang to compare the prompt below across the ready ChatGPT and Gemini tabs. Start with `agentganggang.bridge_status` and `agentganggang.check_readiness`. If fewer than two model tabs are ready, stop and tell me exactly which lo