Agent skill · lobehub
testing-heterogeneous-agents
Manually runs the live LobeHub official-provider compatibility matrix across Claude Code, Codex, Grok Build, Kimi Code, Pi, and TRAE when explicitly invoked by the user.
What it needs
About 4k tokens when loaded.
What this skill does
Testing Heterogeneous Agents This project skill extends acceptance with one scenario: proving that every server-advertised official model completes through each supported external CLI agent and LobeHub's server-default provider binding. It does not replace Acceptance. Use Acceptance for the plan, approval gate, evidence contract, immutable rounds, publishing, and teardown. Use .agents/acceptance/PROJECT.md for LobeHub's Electron launch, auth, CDP, and multi-instance commands. This skill owns only the compatibility-matrix semantics and its executable harness. Manual Invocation Only The user invokes this skill with /testing-heterogeneous-agents in Claude Code or $testing-heterogeneous-agents in Codex. Do not automatically load or execute it as part of development, debugging, acceptance, or release tasks, and do not schedule it. A reference from another skill is not permission to invoke it. Manual invocation still requires scope and cost approval before live requests. Scope The matrix covers: Claude Code, Codex, Grok Build, Kimi Code, Pi, and TRAE; models returned by the live getServerDefaultHeterogeneousCapability response; the real Desktop renderer → IPC → CLI → official relay path; the ingress selected by each agent (anthropic-messages or openai-responses); a unique marker round trip plus authoritative relay, provider, and model observations. It does not cover user-defined providers, user-managed API keys, general model quality, tool-use quality, or ordinary chat-agent execution. Add a separate scenario instead of silently widening this matrix. Harness Filters, topic id, and non-default CDP port are optional when the attached Electron window already supplies the intended scope. Exit codes: Code Meaning ---- --------------------------------------------------------------- 0 Every selected cell passed 1 At least one selected cell failed 2 No failures, but at least one cell was blocked 3 Electron, authentication, topic, or capability preflight failed Run Workflow 1. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills lobehub/testing-heterogeneous-agents