Repository navigation
Prepare the agent skills for the NVIDIA skills catalog (v2-candidate) - #110
kumo-isaac wants to merge 1 commit into
Conversation
The catalog copies each skill directory to one named for the skill and nothing around it, so each skill now lives in a directory named as its frontmatter names it (sdm-tabular, sdm-relational), links to its sibling by that name, and reaches the repository's docs by URL rather than by a relative path that leaves skills/. A test holds every skill to that. Each skill gains the catalog's governance card and evals for NVSkills CI. The evals follow these skills as they stand on v2-candidate: no extra for kumo-relational, no client-side size limits, unique-id keys for explanations, and one eval each for running the model in this process. The request workflow is the catalog's, pinned to a SHA, the same file as on main's PR, so the NVSkills CI gate runs on PRs into this branch. This is the v2-candidate port of #82. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Signed-off-by: igutierrez <igutierrez@nvidia.com>
Test results:
|
| Check | Result |
|---|---|
pytest tests/test_skills.py |
232 passed, 18 skipped |
test_a_skill_links_only_to_skills, test_a_skill_announces_itself |
10 passed |
ruff check . |
clean |
ruff format --check . |
clean (557 files) |
scripts/check_repo_hygiene.py all |
clean |
evals/evals.json (both skills) |
valid JSON |
The 18 skips are the live checks, which need SDM_RELATIONAL_URL, SDM_TABULAR_URL or SDM_IN_PROCESS=1. They weren't run.
NVSkills CI itself hasn't run. It needs #109 on main and the dispatch secret first.
|
Important Review skippedAuto reviews are disabled on base/target branches other than the default branch. Please check the settings in the CodeRabbit UI or the
|
This is #82 rebuilt on
v2-candidate, as asked in review there. It preparesskills/for NVSkills CI and the NVIDIA skills catalog.What changes
skills/tabular→skills/sdm-tabularandskills/relational→skills/sdm-relational, matching the frontmatter names these skills already use on this branch. The catalog copies each skill directory to one named for the skill, so sibling links (../sdm-tabular/...) only resolve when the two match.tests/test_skills.py,scripts/check_repo_hygiene.py,skills/README.mdanddocs/about/architecture.mdfollow the rename.docs/are now GitHub URLs (blob/main, the same form the repo's docs already use). The newtest_a_skill_links_only_to_skillsholds every skill to this.skill-card.mdis the catalog's governance card.evals/evals.jsonis what NVSkills CI's Tier 3 runs. The evals are written against these skills as they stand onv2-candidate, notmain:kumo-relationalneeds no extra.row_index.SDMClient.in_process().skill-card.mdandBENCHMARK.mdare excluded from the markdown checks. They follow the catalog's template, and NVSkills CI writesBENCHMARK.mditself..github/workflows/request-nvskills-ci.yml. The catalog's request workflow, pinned to a SHA, identical to Add the NVSkills CI request workflow #109. Therequire-nvskills-cigate runs from this copy on PRs into this branch./nvskills-cicomments only work once the same file is onmain(the default branch), which is what Add the NVSkills CI request workflow #109 is for.Before NVSkills CI can sign this
main.NVSKILLS_CI_DISPATCH_TOKENis set.NVIDIA/nvskills-cilists this repo withallowed_base_refs: ["main", "v2-candidate"]./nvskills-cihere.Until then the
require-nvskills-cicheck fails, as it does on #82.Open question for the skill authors
sdm-tabular/SKILL.mdsays aRequestholds the context to no size of its own (#93), whilesdm-tabular/references/in-process.mdsays "this client's own [limits] still are: a context above 10,000 rows is refused". I found no such check in the client, so the in-process sentence looks stale. I left both as written. Eval t03 doesn't depend on which one is right.Replaces #82.
🤖 Generated with Claude Code