Repository navigation
Conversation
Contributor
|
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds
skills/oae-metadata: a skill that has an AI assistant draft a metadata JSON plus a report of gaps and uncertain values from a researcher's documents and data files, for import into the Metadata Builder.SKILL.mdand four hand-written references (class choice, Builder import rules, report template, OAPMetadata XML mapping).scripts/validate.py: standard-library validator that reports structural errors separately from gaps and prints each bounding box in words.just gen-alland covered by the CI drift check./llms.txt, and the skill at/skill/. New docs page: Drafting Metadata with an AI Assistant.skills/README.mdreplaces the architecture proposal from docs: add architecture proposal for skills & plugin development #42.Evals use third-party documents and stay outside the repo. On Claude Sonnet, across five cases, drafts made with only the JSON Schema validated but filled required fields with invented values in every run; drafts made with the skill had no structural errors and no invented values.