Skip to content

feat(domain-probes): add 9 panel review probes from review-harvest backfill#186

Merged
Yoojin-nam merged 2 commits into
mainfrom
feat/domain-probe-additions
Jun 23, 2026
Merged

feat(domain-probes): add 9 panel review probes from review-harvest backfill#186
Yoojin-nam merged 2 commits into
mainfrom
feat/domain-probe-additions

Conversation

@Yoojin-nam

Copy link
Copy Markdown
Contributor

What

Nine reviewer-side panel probes promoted from the local review-harvest inbox — each a recurrent class a multi-agent panel under-rated or missed (confirmed/likely reusable). Probes are markdown only (no executable code), edited in the canonical peer-review modules and vendored byte-identical into self-review via check_domain_probe_sync.py --sync.

Module New Probe
sr_ma.md (→ P0–P17) P14 small-k DTA/proportion-MA enrollment overlap → recompute effective independent k
P15 mixed analysis-unit denominator (per-patient/session/lesion) pooled into one proportion
P16 "prospectively registered" vs registration-after-search chronology
P17 boundary-degenerate proportion (≥k−1 at 0%/100%) pooled with spurious precision
observational_confounding.md (→ O1–O16) O15 selection on optional modality/procedure availability (spectrum bias, not a generalizability caveat)
O16 serial-imaging size/growth endpoint: which-lesion-tracked + multiplicity
diagnostic_accuracy.md (→ D1–D8) D8 exclusion flow-diagram ↔ Methods-prose consistency + modality-safety (MR/contrast/device/artifact) enumeration
ai_overclaiming.md (→ AO0–AO6) AO6 arm-defining task vs deployment workflow (handicapped arm / AI-success-conditioned selection) — design-level, escalate past Major
survival_prognostic.md S7 sharpened with an apparent-vs-optimism deterministic tell (calibration slope == 1.00 / discrimination with no optimism/bootstrap/external token)

Housekeeping

Also corrects pre-existing stale probe-range labels in both SKILL.md files for the touched modules (some had drifted since prior probe additions — e.g. sr_ma was still labelled P1–P10, diagnostic D1–D6 despite D7). Counts now match the modules.

CI

validate_skills.sh (PII + structure + domain-probe vendoring byte-identical), check_domain_probe_sync.py --strict, check_locale_inventory.py all pass. No code, no detector/skill count change → catalogs untouched, no release.

🤖 Generated with Claude Code

Yoojin-nam and others added 2 commits June 24, 2026 08:06
Nine reviewer-side probes promoted from the review-harvest inbox (each a
recurrent, confirmed/likely-reusable class a panel under-rated or missed).
Edited in the canonical peer-review modules and vendored byte-identical to
self-review via check_domain_probe_sync.py --sync.

sr_ma.md (P0–P11 -> P0–P17):
- P14 small-k DTA/proportion-MA enrollment overlap -> recompute effective k
- P15 mixed analysis-unit denominator pooled into one proportion
- P16 "prospectively registered" vs registration-after-search chronology
- P17 boundary-degenerate proportion pooled with spurious precision

observational_confounding.md (O1–O14 -> O1–O16):
- O15 selection on optional modality/procedure availability (spectrum bias,
  distinct from a generalizability caveat)
- O16 serial-imaging size/growth endpoint: which-lesion-tracked + multiplicity

diagnostic_accuracy.md (D1–D7 -> D1–D8):
- D8 exclusion flow-diagram <-> Methods-prose consistency + modality-safety
  (MR/contrast contraindication, device/artifact) exclusion enumeration

ai_overclaiming.md (AO0–AO5 -> AO0–AO6):
- AO6 arm-defining task vs deployment workflow (handicapped arm /
  AI-success-conditioned selection) — design-level, escalate past Major

survival_prognostic.md:
- S7 sharpened with an apparent-vs-optimism deterministic tell (calibration
  slope == 1.00 / discrimination with no optimism/bootstrap/external token)

Also corrects pre-existing stale probe-range labels in both SKILL.md files for
the touched modules (sr_ma, observational, diagnostic, ai_overclaiming) so the
prose counts match the modules. No code, no detector/skill count change ->
catalogs untouched, no release.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
@Yoojin-nam Yoojin-nam force-pushed the feat/domain-probe-additions branch from 77103db to eb5fd96 Compare June 23, 2026 23:16
@Yoojin-nam Yoojin-nam merged commit 065b1fd into main Jun 23, 2026
3 checks passed
@Yoojin-nam Yoojin-nam deleted the feat/domain-probe-additions branch June 23, 2026 23:49
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant