 xianren
|
937b642da8
|
refactor(zhiyi): v0.3 architecture rebuild — progressive disclosure + provenance + fidelity tests
Sample master (zhiyi) rebuilt to new architecture:
- SKILL.md slimmed from 225→94 lines with decision tree + Quick Ref
- Provenance frontmatter: CBETA IDs, FoJin text IDs, citation_format
- voice.md/teaching.md moved to references/ (loaded on demand)
- sources/ with canonical excerpts (offline-capable)
- tests/fidelity.jsonl: 5 Q&A pairs with expected citations/keywords
- scripts/validate.py: cross-master frontmatter linter
- scripts/test-fidelity.py: Claude API-based fidelity test runner
Follows Anthropic Agent Skills patterns:
- Progressive disclosure (metadata→body→references)
- Decision tree for branching workflows
- Task-gated reference loading
- Quick Reference table
- Scripts as black boxes (--help, never Read source)
|
2026-04-06 07:05:43 +08:00 |
|