@monoes/monomindcli 2.15.3 → 2.15.4

package/org-skills/hypothesis-generation/references/concepts_and_workflow.md

@@ -0,0 +1,173 @@
+# Concepts and Candidate Lifecycle
+
+## Purpose
+
+This reference prevents common category errors in hypothesis work. It is a vocabulary and workflow guide, not a theory of confirmation and not an automatic ranking method.
+
+## Object model
+
+### Observation
+
+A bounded account of what was detected or reported:
+
+- source or measurement;
+- population/system, place, and time;
+- unit of observation;
+- preprocessing, exclusions, missingness, and uncertainty;
+- whether the observation was expected or selected after inspection.
+
+An observation can be mistaken, biased, or unrepresentative. It does not explain itself.
+
+### Research question
+
+An answerable question that fixes the scope of inquiry. It should identify the target population/system, variables or interventions, comparator where meaningful, outcome, timeframe, context, and claim type.
+
+PICO/PICOT is appropriate for many intervention-effect questions. It is not a universal ontology. Use a framework matched to the question and involve affected stakeholders where appropriate.
+
+### Hypothesis
+
+A candidate proposition that could explain or relate observations and yield testable implications. Keep its status as `candidate` until evidence changes the state. Avoid “validated hypothesis,” “proven mechanism,” and similar language unless the statement is being used only to quote a source accurately.
+
+### Mechanism
+
+A proposed process connecting antecedent conditions to an outcome. A mechanism should identify entities, activities, ordering, and boundary conditions where the domain permits. A plausible narrative without discriminating predictions remains a story.
+
+### Causal estimand
+
+A precise target causal contrast. At minimum, state:
+
+- target population/system;
+- intervention/exposure and comparator;
+- outcome and time horizon;
+- population-level summary;
+- treatment versions and intercurrent-event strategy where relevant;
+- identification assumptions.
+
+The estimand is the target, the estimator is the method, and the estimate is the numerical result.
+
+### Prediction
+
+An observable implication derived from a candidate before checking the target result. A useful prediction specifies conditions, measurement, expected pattern, uncertainty, and an incompatible result. It should distinguish at least one rival when possible.
+
+### Alternative explanation
+
+A rival account that could produce the same observation. Rivals include:
+
+- distinct mechanisms;
+- measurement or processing artifacts;
+- confounding/common causes;
+- selection or attrition;
+- collider conditioning;
+- reverse causation;
+- contextual or temporal heterogeneity;
+- stochastic variation.
+
+Rivals can coexist. Do not force mutual exclusivity when a mixed explanation is scientifically plausible.
+
+### Null hypothesis
+
+A defined no-effect/no-difference model used in an analysis. It is not “nothing happened,” and failure to reject it does not establish equivalence or absence. Define compatibility, equivalence, or non-inferiority rules separately when those are the scientific targets.
+
+### Negative control
+
+A control in which the target mechanism should not operate but relevant bias pathways should remain. Negative exposure and negative outcome controls can reveal confounding, selection, measurement, or analytic bias when their assumptions are credible. A negative control does not repair bias automatically.
+
+### Operationalization
+
+The mapping from a construct to a measurement, category, intervention, or variable. Record instrument/method, unit, timing, population/system, validity, reliability, calibration, missingness, transformations, cut points, and limitations.
+
+### Analysis plan
+
+The planned mapping from data to estimand, prediction, or descriptive target. It includes units, populations, transformations, models, contrasts, effect measures, uncertainty, missingness, multiplicity, diagnostics, sensitivity analyses, and decision rules.
+
+### Evidence
+
+Empirical observations or documented sources that bear on claims. Record whether a source supports, challenges, contextualizes, or supplies a method. Citation presence does not prove claim support; a human must inspect the source.
+
+## Candidate lifecycle
+
+Use explicit states:
+
+1. **Draft candidate** — generated but not yet searched or operationalized.
+2. **Evidence-bounded candidate** — linked to a dated search and source ledger.
+3. **Test-ready candidate** — has measurements, rivals, falsifiers, controls, and analysis links.
+4. **Preregistered candidate** — time-stamped before the relevant outcome was inspected.
+5. **Tested candidate** — results and deviations are available.
+6. **Retained, revised, challenged, or unresolved** — human interpretation with uncertainty.
+
+Never use `true`, `proven`, or `selected_winner` as a machine-generated state.
+
+## Multiple hypotheses and strong inference
+
+Platt’s 1964 strong-inference essay advocates:
+
+1. devising alternative hypotheses;
+2. devising a crucial experiment with alternative possible outcomes that exclude candidates;
+3. performing the experiment cleanly;
+4. recycling the process with subhypotheses.
+
+Use this as a discipline for contrast, not as a guarantee of truth. In practice:
+
+- alternatives may be incomplete;
+- candidates may not be mutually exclusive;
+- auxiliary assumptions can fail;
+- measurements may not distinguish the intended mechanisms;
+- a “crucial” result may be indeterminate;
+- exclusions remain provisional.
+
+Always include an “unknown or mixed explanation” path in interpretation.
+
+## Exploratory and confirmatory modes
+
+### Exploratory
+
+- Generates observations, candidates, variables, and models.
+- Can be data-dependent.
+- Must record that dependence.
+- Produces hypotheses for future tests rather than relabeling the same-data analysis as confirmation.
+
+### Confirmatory
+
+- Defines hypotheses, outcomes, exclusions, transformations, models, and decision rules before inspecting the target result.
+- Preserves the planned analysis.
+- Reports deviations and additional analyses transparently.
+
+Both modes are scientifically valuable. The integrity failure is not exploration; it is presenting exploration as if it were prespecified.
+
+## Uncertainty vocabulary
+
+Prefer:
+
+- “candidate explanation”;
+- “consistent with under the stated assumptions”;
+- “challenges this candidate if measurement and design assumptions hold”;
+- “not distinguished by this result”;
+- “not located within the documented search boundary”;
+- “requires replication or external validation.”
+
+Avoid:
+
+- “proved” or “disproved” for ordinary empirical results;
+- “novel” based only on no quick search hit;
+- “no effect” from a non-significant result;
+- “causes” from an unqualified association;
+- “the mechanism” when several remain plausible.
+
+## Minimum handoff
+
+A hypothesis package should contain:
+
+- frozen observation;
+- framed question and claim type;
+- dated search boundary and source ledger;
+- candidate hypotheses and mechanisms;
+- rivals and bias explanations;
+- causal estimand if applicable;
+- discriminating predictions and falsifiers;
+- operationalization and measurement-validity record;
+- nulls and controls;
+- design and analysis plan;
+- uncertainty and boundary conditions;
+- ethics/safety/regulatory gates;
+- preregistration/deviation plan;
+- accountable human review.

package/org-skills/hypothesis-generation/references/ethics_safety_and_ai.md

@@ -0,0 +1,216 @@
+# Ethics, Safety, Feasibility, and Responsible AI
+
+## This is a routing guide
+
+This reference helps identify gates. It is not legal, medical, regulatory, biosafety, biosecurity, export-control, ethics, or institutional advice. Requirements vary by jurisdiction, sponsor, institution, organism, material, and intended use.
+
+When applicability is uncertain, mark the gate `undetermined`, stop operational planning, and obtain a determination from the qualified local authority.
+
+## Universal intake
+
+Record:
+
+- accountable owner and institution;
+- intended purpose and foreseeable misuse;
+- affected people, animals, communities, ecosystems, infrastructure, or security interests;
+- data and material sensitivity;
+- funding, jurisdiction, and collaborating sites;
+- required expertise;
+- conflicts and incentives;
+- approvals, determinations, and unresolved blocks;
+- less risky ways to answer the question.
+
+Feasibility never overrides ethics or safety.
+
+## Human-participant gate
+
+Potential triggers include:
+
+- intervention or interaction with living people;
+- identifiable private information or biospecimens;
+- secondary use, linkage, re-identification, recruitment, or contact;
+- vulnerable populations or sensitive topics;
+- international or community-governed data.
+
+Required action:
+
+- obtain an IRB/REC or other authorized determination before research starts;
+- do not self-declare exemption;
+- address consent or authorized waiver, privacy, security, equitable selection, risk/benefit, compensation, return of results, and community governance as applicable;
+- use additional protections required by law or policy.
+
+In the United States, HHS 45 CFR 46 includes the Common Rule and additional subparts. Local and non-U.S. rules can differ. The 2024 revision of the World Medical Association Declaration of Helsinki is a relevant international ethical statement for medical research involving human participants.
+
+This skill does not provide clinical advice or authorize an intervention.
+
+## Animal-research gate
+
+Potential triggers include live vertebrate animals, field capture, breeding, procedures, tissues tied to ongoing animal activities, or covered training/testing.
+
+Required action:
+
+- obtain the applicable IACUC or equivalent approval before work;
+- establish institutional assurance and veterinary oversight where required;
+- apply replacement, reduction, and refinement;
+- justify species/model, numbers, endpoints, welfare monitoring, analgesia/anesthesia, and humane endpoints through the authorized process;
+- use current reporting guidance such as ARRIVE when applicable.
+
+The bundled tools do not calculate animal numbers or approve protocols.
+
+## Biosafety and biosecurity gate
+
+Potential triggers include:
+
+- recombinant or synthetic nucleic acids;
+- infectious agents, toxins, biological materials, gene transfer, or modified organisms;
+- environmental release;
+- select agents or regulated materials;
+- procedures that could alter hazard, host range, pathogenicity, transmissibility, resistance, or detection;
+- work beyond established institutional containment and training.
+
+Required action:
+
+- stop before operational detail;
+- route to the biosafety officer, Institutional Biosafety Committee, and other required authority;
+- use the current NIH Guidelines, CDC/NIH *Biosafety in Microbiological and Biomedical Laboratories*, local biosafety manual, and applicable regulations;
+- document containment and occupational-health decisions only after authorized review.
+
+Do not infer a containment level or operating procedure from this skill.
+
+## Dual-use and harmful-use gate
+
+Potential triggers include research, data, models, or protocols that could reasonably enable:
+
+- increased biological harm or spread;
+- evasion of detection, treatment, control, or safeguards;
+- scalable production or dissemination of harmful agents;
+- weaponization;
+- exploitation of critical vulnerabilities;
+- transfer of restricted technical information.
+
+Required action:
+
+1. Do not provide optimization, stepwise procedures, parameter choices, sequences, acquisition pathways, or troubleshooting that increase harmful capability.
+2. Preserve only a high-level scientific question, benefit rationale, and risk statement.
+3. Route to institutional dual-use/biosecurity review, funder, legal/export-control, and other required authorities.
+4. Follow current policy, award terms, and jurisdiction-specific controls.
+
+### U.S. policy status checked 2026-07-23
+
+- Executive Order 14292 of May 5, 2025 directed revision/replacement of the 2024 U.S. Government DURC/PEPP policy and paused federally funded research meeting its “dangerous gain-of-function” definition pending the replacement policy.
+- NIH Notice NOT-OD-25-112 stated that the Executive Order superseded NIH implementation of the 2024 DURC/PEPP policy and rescinded NOT-OD-25-061.
+- The HHS/ASPR policy page still stated at the verification date that federal departments and agencies would revise or replace the 2024 policy and that the page would be updated when the revised policy became available.
+
+Do not use the superseded 2024 implementation as current clearance. Recheck the official policy and award terms for every project because this status is time-sensitive.
+
+WHO’s *Global Guidance Framework for the Responsible Use of the Life Sciences* provides an international risk-governance framework; it does not replace national or local rules.
+
+## Data-governance gate
+
+Before using data:
+
+- confirm authority, consent, license, data-use agreement, and purpose limitation;
+- classify sensitivity and re-identification risk;
+- minimize fields and access;
+- use approved storage, retention, deletion, audit, and sharing controls;
+- address community and Indigenous governance;
+- separate public, controlled, confidential, proprietary, and export-controlled materials.
+
+Passing a local schema check is not de-identification, anonymization, HIPAA compliance, GDPR compliance, or authorization to share.
+
+## Regulatory gate
+
+Potential triggers include:
+
+- human interventions or clinical investigations;
+- drugs, biologics, devices, diagnostics, or software intended for clinical use;
+- environmental release;
+- genetically modified organisms;
+- regulated laboratory, animal, agricultural, or chemical activities;
+- claims intended for product labeling, approval, or public-health action.
+
+Record:
+
+- intended use;
+- jurisdiction;
+- product/activity classification;
+- sponsor and responsible regulatory owner;
+- applicable quality system or submission route;
+- current determination and source/date.
+
+Do not infer regulatory status from a research label, reporting checklist, or generated artifact.
+
+## Feasibility gate
+
+Assess:
+
+- scientific and technical capability;
+- validated measurement;
+- statistical information/precision;
+- qualified personnel and facilities;
+- time and resources;
+- access to population/system;
+- approvals and material/data access;
+- foreseeable failure and stopping criteria.
+
+If infeasible, revise the question or conduct a bounded feasibility study. Do not weaken protections or invent optimistic assumptions.
+
+## Responsible AI policy
+
+### Local-first rule
+
+Default to local processing. Do not send sensitive, unpublished, confidential, personal, proprietary, controlled, or security-relevant information to an external AI system without:
+
+- explicit authorization;
+- a named approved service and account;
+- a defined minimum data scope;
+- contract, retention, training-use, location, and access review;
+- applicable publisher, funder, institutional, and participant permission.
+
+The bundled scripts make no network, model, image, or external-service calls and read no environment credentials.
+
+### Human accountability
+
+An accountable human must:
+
+- own the question, candidate set, and final scientific decisions;
+- verify every citation, identifier, quotation, and source-to-claim link;
+- verify calculations and scientific plausibility;
+- inspect omitted rivals and boundary conditions;
+- review ethics, safety, privacy, dual-use, and regulatory implications;
+- disclose AI assistance where policy requires;
+- retain or delete records under the controlling policy.
+
+AI output is not evidence and cannot grant approval.
+
+### Known AI risks
+
+NIST AI 600-1 identifies generative-AI risks including confabulation, data privacy, harmful bias/homogenization, information integrity, human–AI configuration, and dangerous recommendations. Mitigate by:
+
+- independent human ideation before AI expansion;
+- generating rivals from different disciplinary perspectives;
+- separating source retrieval from claim synthesis;
+- checking primary sources directly;
+- recording prompts/tool versions when authorized and scientifically relevant;
+- challenging convergent, polished, or overly confident output;
+- using multiple human reviewers for high-consequence work.
+
+Doshi and Hauser’s 2024 experiment found AI-assisted stories were more similar to one another even while some individual creativity measures improved. Do not generalize that one study to all scientific ideation; treat homogenization as a plausible risk and preserve independent candidate generation.
+
+UNESCO’s AI ethics recommendation emphasizes human rights, privacy/data protection, responsibility/accountability, transparency, and human oversight. Ultimate responsibility remains human.
+
+## Stop conditions
+
+Stop and escalate when:
+
+- authorization is absent or ambiguous;
+- a required review is missing;
+- data or material classification is unknown;
+- harmful-use potential cannot be bounded;
+- a request seeks operational harmful detail;
+- patient-specific advice is requested;
+- a regulatory or legal determination is needed;
+- the proposed measurement cannot validly bear on the construct;
+- qualified expertise is unavailable.
+
+Record the block without copying sensitive details into a general-purpose artifact.

package/org-skills/hypothesis-generation/references/experimental_design_patterns.md

@@ -0,0 +1,301 @@
+# Design Patterns for Discriminating Tests
+
+## Design starts from the prediction
+
+For each test, link:
+
+`candidate → mechanism → prediction → observable → operationalization → design → analysis → interpretation`
+
+Choose the design that can distinguish candidates under realistic uncertainty. Do not select a design merely because it is familiar or available.
+
+## NIH-aligned rigor questions
+
+Where applicable, address:
+
+- rigor of the prior research forming the scientific premise;
+- unbiased and well-controlled design;
+- relevant biological variables such as sex, age, weight, or health condition;
+- authentication and validity of key biological/chemical resources;
+- transparent methods, analysis, interpretation, and reporting.
+
+Apply only the elements relevant to the science and explain omissions.
+
+## Core design record
+
+Every design should state:
+
+- study system and target population;
+- experimental/observational unit and analysis unit;
+- sampling frame and recruitment/selection;
+- interventions/exposures and comparator versions;
+- allocation, randomization, concealment, and masking;
+- outcomes, timing, measurement IDs, and quality control;
+- positive, negative, vehicle/sham, procedural, or reference controls as applicable;
+- inclusion, exclusion, attrition, and stopping;
+- sample-size, precision, or information rationale;
+- analysis IDs and estimands;
+- safety, ethics, feasibility, data, and regulatory gates;
+- replication, transport, and external-validation plan.
+
+## Experimental designs
+
+### Randomized intervention
+
+Useful for causal contrasts when intervention, allocation, and ethics permit.
+
+Check:
+
+- allocation sequence and concealment;
+- intervention versions, adherence, contamination, and co-interventions;
+- masking of participants, providers, outcome assessors, and analysts where feasible;
+- primary estimand and intercurrent events;
+- intention-to-treat or other analysis population aligned to the estimand;
+- harms, stopping, missing outcomes, and protocol deviations.
+
+Randomization does not solve measurement bias, nonadherence, post-randomization selection, interference, or poor external validity.
+
+### Factorial design
+
+Useful for multiple interventions and interactions.
+
+Check:
+
+- scientific meaning and scale of interaction;
+- power/precision for interactions, not only main effects;
+- compatibility and safety of combined conditions;
+- multiplicity and hierarchy;
+- whether sparse combinations undermine interpretation.
+
+### Within-unit or crossover design
+
+Useful when effects are reversible and carryover can be controlled.
+
+Check:
+
+- period and sequence effects;
+- washout rationale;
+- time trends and learning;
+- missing periods;
+- whether the condition is stable and intervention reversible.
+
+### Perturbation and rescue
+
+Useful for mechanistic candidates when ethically and technically appropriate.
+
+Check:
+
+- perturbation specificity and off-target effects;
+- manipulation check;
+- rescue interpretation and overexpression artifacts;
+- temporal order;
+- orthogonal perturbations and measurements;
+- relevant negative and positive controls.
+
+A rescue can still be explained by compensatory or non-specific effects.
+
+### Time-course
+
+Useful when candidates predict different ordering or dynamics.
+
+Check:
+
+- sampling times justified by expected process;
+- independent versus repeated units;
+- baseline and pre-trend;
+- measurement stability across time;
+- multiple looks and timepoint multiplicity;
+- lag, feedback, and reverse causation.
+
+## Observational designs
+
+### Cross-sectional
+
+Can estimate prevalence and associations at a defined time. It usually cannot establish temporal direction. Explicitly consider selection, reverse causation, survival/prevalence bias, and common-method measurement.
+
+### Cohort/longitudinal
+
+Can establish measured temporal ordering and incidence. It does not eliminate confounding.
+
+Check:
+
+- time zero and eligibility;
+- exposure updates and time-varying confounding;
+- loss to follow-up and informative censoring;
+- competing events;
+- immortal-time and delayed-entry risks;
+- outcome ascertainment changes.
+
+### Case-control
+
+Efficient for some rare outcomes.
+
+Check:
+
+- source population and control sampling;
+- matching implications;
+- exposure measurement and recall;
+- selection mechanisms;
+- correct effect measure and sampling analysis.
+
+### Natural/quasi-experimental
+
+Can strengthen causal identification when an assignment mechanism or discontinuity is credible.
+
+Check:
+
+- assignment mechanism and manipulation;
+- continuity, parallel trends, exclusion, or instrument assumptions as applicable;
+- anticipation and spillovers;
+- bandwidth/window choices;
+- placebo/negative-control tests;
+- sensitivity to specification and clustering.
+
+The design label alone does not establish identification.
+
+## Computational and theoretical designs
+
+### Simulation
+
+Use to test implications of assumptions, estimator behavior, or model dynamics.
+
+Record:
+
+- data-generating process and parameter ranges;
+- rationale for scenarios;
+- seeds and software versions;
+- performance targets and uncertainty;
+- failure cases and sensitivity;
+- separation between simulated truth and empirical validity.
+
+Simulation can show consequences within a model, not that the model describes nature.
+
+### Predictive model evaluation
+
+Separate prediction from causation.
+
+Check:
+
+- target population, outcome, time origin, and horizon;
+- leakage and preprocessing;
+- train/tune/test independence;
+- calibration and discrimination;
+- uncertainty and subgroup performance;
+- temporal/geographic/external validation;
+- dataset shift and update policy.
+
+### Secondary-data analysis
+
+Record provenance, data-generating process, inclusion, missingness, transformations, version, and prior analysis exposure. Avoid using the same data to generate and confirm a hypothesis without transparent separation or independent validation.
+
+## Controls
+
+### Positive control
+
+A condition expected to produce a known response. It checks whether the system and measurement can detect a relevant effect.
+
+### Procedural control
+
+Matches handling, timing, delivery, or processing without the target active component.
+
+### Negative control
+
+Should not operate through the target mechanism but should share relevant bias pathways. State assumptions and failure interpretation.
+
+### Null comparator
+
+A comparator representing no intervention or no difference may be useful, but it is not equivalent to a negative control and may not isolate placebo, handling, expectancy, or background trends.
+
+## Measurement validity
+
+Before collecting target outcomes:
+
+- define constructs and proxies;
+- verify instrument validity in the target context;
+- assess reliability/repeatability;
+- calibrate and authenticate resources;
+- prespecify detection limits and quality failures;
+- plan masking and standardized acquisition;
+- define missing/invalid values;
+- test cross-site, cross-device, cross-group, or longitudinal comparability where relevant.
+
+A precise measure can be precisely wrong. Technical replicates do not replace independent biological, participant, site, or experimental units.
+
+## Sample size and precision
+
+Do not use universal minima.
+
+Base planning on:
+
+- primary estimand and effect/precision target;
+- expected variability and dependence;
+- allocation ratio;
+- attrition/missingness;
+- multiplicity or sequential design;
+- model complexity;
+- feasibility and ethical burden;
+- uncertainty in planning values.
+
+Report assumptions and sensitivity to them. Pilot data may be too unstable for definitive effect-size planning; use external evidence, conservative ranges, or precision-based goals where appropriate.
+
+## Multiplicity
+
+Inventory:
+
+- candidate hypotheses;
+- outcomes and timepoints;
+- subgroups and interactions;
+- model specifications and transformations;
+- interim looks and stopping;
+- repeated datasets or cohorts.
+
+Prespecify a strategy appropriate to the inferential goal, such as:
+
+- family-wise error control;
+- false-discovery-rate control;
+- hierarchical/gatekeeping testing;
+- multilevel estimation;
+- clearly labeled exploratory analysis without confirmatory claims.
+
+Do not report only favorable analyses. Threshold crossing is not a quality score or probability that a candidate is true.
+
+## Missing data and deviations
+
+Define:
+
+- missingness by variable, time, and group;
+- reasons and data-collection process;
+- primary handling;
+- assumptions;
+- sensitivity analyses;
+- protocol and analysis deviations.
+
+Complete-case analysis is not automatically unbiased. Record deviations without overwriting the original plan.
+
+## Replication and open materials
+
+Following the National Academies terminology:
+
+- reproducibility uses the same data/code/conditions;
+- replicability collects new data to address the same question.
+
+Plan:
+
+- code, environment, seeds, and workflow capture;
+- provenance and versioning;
+- shareable materials and justified restrictions;
+- independent replication;
+- boundary-condition and transport tests;
+- reporting of null and contrary results.
+
+Open sharing remains subject to consent, privacy, community governance, intellectual property, biosecurity, and other controls.
+
+## Intervention reporting
+
+For randomized intervention work:
+
+- use SPIRIT 2025 and its explanation/elaboration for protocol completeness;
+- use CONSORT 2025 and its explanation/elaboration for result reporting;
+- include trial registration, protocol and statistical-analysis-plan access, outcomes, harms, intervention/comparator details, analysis populations, missing data, and important changes;
+- use applicable extensions.
+
+These are reporting guidelines. They do not replace ethics review, trial registration rules, statistical expertise, or regulatory requirements.