Skill rating
7 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 | A | Review CRAFT Search gold answer quality for a specific task. Use when the user asks to review, check, investigate, or look closely at a craft-* task ID. Evaluates gold files, functions, assertions, an | 100 | 91 | C | — | — | 5 d ago | |
| 2 | B | Build or publish nemo-switchyard Python distributions through the repository's GitHub Actions workflow. Use when asked to build a development wheel, cut a Python release, publish to PyPI, create a rel | 100 | 84 | D | — | — | 5 d ago | |
| 3 | B | Review Switchyard Rust changes for correctness and maintainability. Use for pull requests or diffs touching crates, PyO3 bindings, async runtime behavior, streaming, protocol types, translation, algor | 100 | 85 | D | — | — | 5 d ago | |
| 4 | B | switchyard-docsGeneratorGitHubSoftware developmentWriting and documentsNVIDIA-NeMo/SwitchyardAgent Skills Edit or debug the published Switchyard MkDocs site. Use for docs pages, mkdocs.yml navigation, mkdocs_hooks.py source links, strict build failures, local previews, or .github/workflows/docs.yml. | 100 | 84 | C | — | — | 5 d ago | |
| 5 | B | switchyard-testing-ciAnalyzerGitHubSoftware developmentData and analyticsNVIDIA-NeMo/SwitchyardAgent Skills Select or debug Switchyard validation and GitHub CI. Use when asked which tests to run, whether a change is ready, why a CI job failed, how to reproduce CI, or whether live provider tests are appropri | 100 | 81 | F | — | — | 5 d ago | |
| 6 | B | switchyard-community-gardeningProcedureGitHubData and analyticsSoftware developmentNVIDIA-NeMo/SwitchyardAgent Skills Triage or resume Switchyard's repository-wide community-maintenance queue, prepare a gardening handoff, or report a gardener's activity and impact. Do not use for one isolated issue or pull request, i | 100 | 85 | D missing files | — | — | 5 d ago | |
| 7 | B | Deep dive on Harbor trial results for tasks that use SWE-Bench-style F2P (FAIL_TO_PASS) and P2P (PASS_TO_PASS) reference tests. Diagnoses why an agent failed and audits whether a failing task is genui | 100 | 74 | C missing files | — | — | 5 d ago |