メニュー
Standing watcher. Reruns the trial, literature (PubMed + bioRxiv), and ClinVar-relookup specialists against the FIXED profile and diffs against the stored baseline. Empty diff -> one calm "no significant changes" timeline entry.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Open Targets gene-disease association lookup via the official MCP connector. One GraphQL round trip per gene. Emits Tier C informational evidence.
PubMed + bioRxiv search for recent literature on the patient's genes and diagnosis. bioRxiv preprints are first-class (earliest signal). Emits Tier C; the LLM only summarizes genuine free text, it never asserts facts.
ClinicalTrials.gov v2 search for trials relevant to the patient's diagnosis and genes. Eligibility is surfaced as "may be eligible — confirm with your care team", never confirmed. Emits Tier C.
Uncertainty-ranked gap report (spec §8b). For an unresolved (Tier B) variant, names that the analysis can't resolve it and attributes the gap to a missing input — a documented family history — that would let the analysis weight it. Never a test order.
Uncertainty-ranked gap report (spec §8b). Names a pharmacogenomic module the analysis could NOT complete and attributes the gap to a specific missing input (a genotype). Never tells the patient to get a test — it is a report on the tool's blind spots for the care team.
Deterministic CPIC pharmacogenomics lookup over the patient's current medications. Pure code, no LLM. Emits Tier A/B for CPIC Level A/B gene-drug pairs; flags a missing genotype instead of ever directing a dose change.
| name | world-evidence-watch |
| kind | standing |
| domain | literature |
| description | Standing watcher. Reruns the trial, literature (PubMed + bioRxiv), and ClinVar-relookup specialists against the FIXED profile and diffs against the stored baseline. Empty diff -> one calm "no significant changes" timeline entry. |
A standing specialist (spec §8a) — run by the recheck loop on a schedule, not in round one. It reruns the trial / literature / ClinVar-relookup specialists against the fixed profile, then diffs against the stored baseline:
new_trials = current_trial_ids - known_trial_ids
new_pmids = pubmed.search(genes, mindate=last_checked)
new_biorxiv = biorxiv.search(genes, since=last_checked)
reclassified = {v: now[v] for v in snapshot if now[v] != snapshot[v]}
bioRxiv is first-class (earliest signal). Every card passes the code gate.
STATUS: live — re-queries app.trials.search_trials + app.literature. search_literature(since=ctx.last_checked) and returns the current snapshot. The
diff/baseline logic lives in app/recheck.py (diff_new_records by source_id), which
turns genuinely-new items into hedged timeline cards and updates the baseline. Runs
only when BWCLS_LIVE_SOURCES=1; empty snapshot -> calm "no significant changes".