Skip to content

K-Dense-AI/scientific-agent-skills / skills/hypothesis-generation

hypothesis-generation

Verified

Formulates evidence-bounded scientific questions, candidate hypotheses, rival explanations, causal or associational claims, discriminating predictions, measurements, and preregistration-ready analysis plans. Used when turning observations or preliminary findings into transparent, testable research plans without treating hypotheses as facts.

assets/prediction_rival_matrix_template.csv

View on GitHub
prediction_id,hypothesis_id,rival_hypothesis_ids,conditions,observable,expected_if_focal,expected_if_rivals,falsifier,indeterminate_result,boundary_conditions,measurement_ids,negative_control_ids,analysis_ids,uncertainty
P1,H1,H2,"Random assignment, successful manipulation, calibrated measurements, and masked validation","Ordering of synthetic intermediate M and outcome Y","Intermediate M changes before outcome Y in condition X","H2 predicts no condition-specific intermediate change and a shift shared with the reference quantity","Outcome Y changes without the prespecified intermediate change after successful manipulation and valid measurement","Manipulation or measurement check fails, or uncertainty is too large to distinguish the patterns","Synthetic eligible units over one prespecified interval",M-INTERMEDIATE;M-OUTCOME,NC1,A1,"Magnitude is not assumed; the planned interval and measurement resolution determine whether patterns are distinguishable"
P2,H2,H1,"Matched synthetic acquisition and calibration workflow","Shift in the synthetic negative-control reference quantity","Reference quantity and outcome Y shift together by acquisition period","H1 predicts outcome Y changes without a corresponding reference shift","Reference quantity is stable across independently calibrated periods while outcome Y changes reproducibly by assignment","Reference measurement fails or acquisition periods do not overlap assigned conditions","Synthetic acquisition batches covered by the declared calibration process",M-NEGATIVE-CONTROL;M-OUTCOME,NC1,A2,"A control shift can have causes other than the stated measurement-drift rival"
add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks.Stars: 115kUpdated Claude CodeCodexVerifiedInstall