Skill rating
6 skills. The A–F grade combines safety (60%) and quality (40%); tests add a bonus. The rating refreshes automatically from open catalogs.
ManufacturingLogistics and warehouseProcurementQuality controlContact centreField serviceFinanceCustomer supportindustry shortcuts
| # | Grade | Skill | Score ▾ | Safety | Quality | Process | Tests | Popularity | Updated |
|---|---|---|---|---|---|---|---|---|---|
| 1 | B | 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. | 100 | 84 | C | — | — | 10 h ago | |
| 2 | B | 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. | 100 | 75 | C | — | — | 10 h ago | |
| 3 | C | Scaffold a new Harbor benchmark adapter by running `harbor adapter init` and then guide implementation using the Adapters Agent Guide as the authoritative spec. | 100 | 72 | C | — | — | 10 h ago | |
| 4 | B | Write Harbor task verifiers using Reward Kit. Use when creating or editing a task's tests/ directory, adding grading criteria, setting up LLM/agent judges, or designing verifiers that produce a reward | 100 | 81 | D missing files | — | — | 10 h ago | |
| 5 | C | Generate a greeting message and write it to a file. | 100 | 47 | D | — | — | 10 h ago | |
| 6 | C | Create a new Harbor task for evaluating agents. Use when the user wants to scaffold, build, or design a new task, benchmark problem, or eval. Guides through instruction writing, environment setup, ver | 95 | 78 | D missing files | — | — | 10 h ago |