Publisher · agent skills
Agent skills by harbor-framework
harbor-framework publishes 8 audited skills on 1 repository: 7 SAFE, 1 CAUTION, 0 BLOCK.
Cite
Cite this page
ModelsAtlas. “Agent skills by harbor-framework”. Retrieved 28 Oct 2026. https://modelsatlas.com/skills/harbor-framework
Verdicts across 8 skills
Repositories
- harbor-framework/harbor ↗8 skills · ★ 5,916
Bundled Keep
harbor-framework/harbor
Existing task skill that should remain after job-level skill injection.
Create Adapter
harbor-framework/harbor
Scaffold a new Harbor benchmark adapter by running `harbor adapter init` and then guide implementation using the Adapters Agent Guide as the authoritative spec.
Create Task
harbor-framework/harbor
Create a new Harbor task for evaluating agents. Use when the user wants to
Generate Greeting
harbor-framework/harbor
Generate a greeting message and write it to a file.
Publish
harbor-framework/harbor
Publish a Harbor task or dataset to the registry. Use when the user wants to upload, publish, or share tasks or datasets/benchmarks on the Harbor registry.
Rewardkit
harbor-framework/harbor
Write Harbor task verifiers using Reward Kit. Use when creating or editing a
Runtime Proof
harbor-framework/harbor
Write the proof file for the Harbor runtime skill injection example.
Upload Parity Experiments
harbor-framework/harbor
Create or reuse Hugging Face dataset PRs for `harborframework/parity-experiments` and upload Harbor parity/oracle result folders efficiently with sparse checkout, raw git pushes, and Git LFS.
Questions about harbor-framework's skills
Are harbor-framework's skills safe?
Where do harbor-framework's skills come from?
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- Are harbor-framework's skills safe?
- Where do harbor-framework's skills come from?