feat(domain-probes): add 9 panel review probes from review-harvest backfill#186
Merged
Conversation
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>
77103db to
eb5fd96
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
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-reviewmodules and vendored byte-identical intoself-reviewviacheck_domain_probe_sync.py --sync.sr_ma.md(→ P0–P17)observational_confounding.md(→ O1–O16)diagnostic_accuracy.md(→ D1–D8)ai_overclaiming.md(→ AO0–AO6)survival_prognostic.mdHousekeeping
Also corrects pre-existing stale probe-range labels in both
SKILL.mdfiles for the touched modules (some had drifted since prior probe additions — e.g.sr_mawas still labelled P1–P10,diagnosticD1–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.pyall pass. No code, no detector/skill count change → catalogs untouched, no release.🤖 Generated with Claude Code