Agent skill · lobehub
run-eval-harbor
Run and diagnose existing Harbor or FrontierHarness evaluations against local production LobeHub or LobeHub Cloud, on a local Docker host, SSH worker, or Runta. Use for eval infrastructure, target preflight, lh CLI injection, Harbor smoke or job runs, resume, and failure triage. Excludes authoring Harbor tasks and product acceptance.
What it needs
About 4k tokens when loaded.
What this skill does
Run Eval Harbor Run existing Harbor evaluations against either this checkout's isolated local production harness or a remote LobeHub target. Use create-task to author or grade tasks and acceptance for product acceptance. Ask First Before preparing or running anything, obtain these independent choices. Do not use runta as a LobeHub server target or checkout as an execution environment: 1. LobeHub server: local production server from this checkout, or cloud/remote. 2. Execution environment: this local host, an SSH Docker worker, or Runta runtimes. The maintained Runta workflow currently targets a cloud/remote LobeHub server. 3. CLI source: checkout build from apps/cli, or published npm release. 4. Agent selection: cloud requires an exact LHAGENTID; local uses the seeded user's builtin inbox agent unless the user explicitly selects a different agent. 5. Eval repository path and whether the user wants a new job or a resume. 6. Credentials: for cloud, require its CLI API key in the eval repository's ignored .env. Local bootstrap seeds its CLI key. Reuse a provider credential already configured in LobeHub or the ignored local env; if the smoke reports InvalidProviderAPIKey, report the resolved agent's provider/model and ask only for that provider's real credential. 7. For a local LobeHub server, obtain explicit confirmation that port 3210 and every configured eval infrastructure port are unreachable from the public internet and other untrusted networks. Do not bootstrap the local stack without confirmation. For the Runta execution environment, also collect the harness repository and pinned commit, provider/key choice required by FrontierHarness, and the Terminal-Bench versus DeepSWE task subset. The Lh Cloud agent's model remains selected by LHAGENTID; do not replace it with FrontierHarness's --model unless the run is explicitly non-comparable. Do not infer these choices. DeepSeek is only one provider example, not a required credential or model. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills lobehub/run-eval-harbor