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

..

references

refactor(zhiyi): v0.3 architecture rebuild — progressive disclosure + provenance + fidelity tests

2026-04-06 07:05:43 +08:00

sources

refactor(zhiyi): v0.3 architecture rebuild — progressive disclosure + provenance + fidelity tests

2026-04-06 07:05:43 +08:00

tests

refactor(zhiyi): v0.3 architecture rebuild — progressive disclosure + provenance + fidelity tests

2026-04-06 07:05:43 +08:00

meta.json

feat: smart master selection + expanded keywords (6→24 per master)

2026-04-05 09:07:24 +08:00

SKILL.md

refactor(zhiyi): v0.3 architecture rebuild — progressive disclosure + provenance + fidelity tests

2026-04-06 07:05:43 +08:00