Add persona-seed skill for pluggable corpus → persona packs - #5
Merged
Conversation
Introduce a provider-agnostic seed pipeline (MatrAIx fixture first): search, SeedProfile mapping, generate-gate e2e, and pack-local provenance — so population corpora can feed OpenPersona without one-off per-source create paths. Co-authored-by: Cursor <cursoragent@cursor.com>
Provide decode_parquet.py / decode-matraix.sh to turn HF packed shards into fixture-shaped JSON for MATRAIX_CORPUS_PATH, and accept .jsonl corpora in the provider for larger offline indexes. Co-authored-by: Cursor <cursoragent@cursor.com>
Resolve providers via providers/registry.json (id or hfRepo) so /datasets listings stay discovery-only until explicitly registered, and future corpora share family adapters instead of hard-coded maps. Co-authored-by: Cursor <cursoragent@cursor.com>
Intent locales like zh/en now resolve against primary_language names (Chinese/English), matching toSeed's localeFromLanguage mapping. Co-authored-by: Cursor <cursoragent@cursor.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
skills/persona-seed: provider-agnostic seed pipeline (MatrAIx fixture first) from intent search → SeedProfile →persona.json→ generate →soul/seed-provenance.jsoncorpusMode, slug/extra safety, corpus validate helper, and e2e/generate-gate testsskills/open-personatopersona-seed(vsanyone-skilldistillation)Test plan
node --test skills/persona-seed/tests/persona-seed.test.js(14 tests)node scripts/validate-skills.mjs skills/persona-seednode skills/persona-seed/scripts/run-pipeline.js --intent '{"domain":["software"],"traits":["precise"]}' --name Nova --slug nova-seed --out /tmp/nova-seedMade with Cursor