Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Phase 2 of disease-market-sizing-orchestration. Discovers disease-specific stratification dimensions by citing guideline sections from sources/guidelines/. ALWAYS uses cite-based discovery — NEVER built-in stratification templates. Output: .cache/<slug>/staging.json. Use AFTER contract-elicitor and AFTER A1' guidelines fetch.
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | -58% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -57% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -66% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -41% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -62% | 0% |
KNOWN_STAGING_TEMPLATES dictif disease == "X": stratify_by("Y") 类硬编码CI watchdog (scripts/p0_watchdog.py) scans this skill's source for disease names + staging templates and blocks merge on hit.
stratify(slug_dir, ask_llm) -> staging.json pathschemas/staging.schema.json — every dimension MUST have name + citation_anchor + sub_cohorts (≥1).
Other measured skills in the registry, with their headline benchmark lift.