run-eval-harbor
A maintainer skill in the LobeHub repository for running and troubleshooting existing Harbor or FrontierHarness evaluations against a LobeHub server, either a local production build from the checkout or a remote one.
What the skill teaches
A maintainer skill in the LobeHub repository for running and troubleshooting existing Harbor or FrontierHarness evaluations against a LobeHub server, either a local production build from the checkout or a remote one. Before acting it asks for every choice: server, where jobs run (local Docker, an SSH worker or Runta), which build of the lh command-line tool to use, the agent, the evaluation repository, new job or resume, and credentials. It enforces guardrails such as a fixed local port, a smoke test before every real job and never printing secrets, runs the bundled smoke script and then the job, exports trajectories, and traces failures to the evaluation services, LobeHub, the gateway, Docker networking or the task verifier.
Capabilities
Not stated in its documentation
About
- Publisher
- LobeHub
- Tool
- Testing
Install
The project doesn't document install steps that we could confirm. See the project's own instructions
What's inside
- agents/openai.yaml
- references/cloud.md
- references/local.md
- references/runta.md
- scripts/.gitignore
- scripts/bootstrap.sh
- scripts/frontierharness-chart-icon.mjs
- scripts/frontierharness-local.py
- scripts/frontierharness-runta.py
- scripts/lh/adapter.py
- scripts/lh/agent.py
- scripts/lh/pier_agent.py
- scripts/lh/template/check-lh.sh.j2
- scripts/lh/template/connect-lh.sh.j2
- scripts/lh/template/install-lh.sh.j2
- scripts/lh/template/run-agent.js
- scripts/lh/template/supervisord.conf.j2
- scripts/preflight.sh
- scripts/run-smoke.sh
- scripts/server.sh
- scripts/smoke/environment/Dockerfile
- scripts/smoke/instruction.md
- scripts/smoke/task.toml
MCP servers and skills can run code on your computer and act on your data. Review the source before installing.
This skill includes scripts that your agent may run.
Details
| Fact | Value | Source |
|---|---|---|
| Type | Skill | |
| Tool | Testing | |
| Publisher | LobeHub | source |
| Official status | Not stated in its documentation | |
| Needs an API key or sign-in | Not stated in its documentation | |
| Includes scripts | Yes | source |
| Platforms | Not stated in its documentation | |
| AI clients | Not stated in its documentation | |
| Licence | NOASSERTION | source |
| Pricing | Not stated in its documentation | |
| Activity | Last commit Nov 11, 202684,974 GitHub starsDownload data not available (not on npm or PyPI) | source |
| Links | Repository Website |
More from LobeHub
33 skills
- pr (Skill)
- acceptance (Skill)
- add-model-provider (Skill)
- add-setting-env (Skill)
- agent-signal (Skill)
- agent-testing-bot (Skill)
Also listed under: Testing
Sources
- GitHub repositorygithub.com/lobehub/lobehub · Backs: Publisher, ActivityNov 11, 2026
- Skill file (SKILL.md)github.com/lobehub/lobehub · Backs: Includes scriptsNov 15, 2026
- Skill file (SKILL.md)github.com/lobehub/lobehub · Backs: LicenceNov 10, 2026
- Folder in the repository (run-eval-harbor)github.com/lobehub/lobehub · Backs: Includes scriptsNov 10, 2026