map-validity-envelope

Files (1)

• SKILL.md

SKILL.md (first lines)

# map-validity-envelope
## Purpose
Map where a claim, method, or design remains valid by defining axes, probing values, detecting breakpoints, and constructing a multidimensional validity envelope.
## Input contract
```yaml
mode_contracts:
  systematic-perturbation: &validity_input
    required: [claim_or_method, validity_target, analysis_dimensions]
    optional: [baseline_conditions, critical_case_rule, perturbation_budget]
    constraints: [axes_values_outcome_measure_and_breakpoint_rule_must_be_explicit]
  boundary-value-stress: *validity_input
  critical-case: *validity_input
```
## Execution protocol
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.

1. You MUST load skill `define-analysis-dimensions` to define the validity axes. You MUST load skill `enumerate-dimension-values` to enumerate representative and boundary values.
2. Apply the probes required by the selected mode and retain their evidence.
3. You MUST load skill `detect-breakpoint` to locate validity transitions. You MUST load skill `construct-validity-envelope` to construct the supported envelope.
4. You MUST load skill `analyze-scaling-regime` to analyze scale-dependent regime changes.
   If global effect decomposition is needed beyond the envelope, consider `sensitivity-analysis`. If the resulting boundary claim lacks a reachable falsifier, consider `falsifiability-audit`.
Deviation: use `critical-case` when a decisive case can replace broad probing; otherwise use `systematic-perturbation` or `boundary-value-stress` according to the declared mode and evidence.
## Output contract
```yaml
mode_contracts:
  systematic-perturbation:
    produces: [dimension_schema, perturbation_records, breakpoints, validity_envelope]
    delta_fields: [findings, evidence_updates, uncertainties, decisions, open_questions]
  boundary-value-stress:
    produces: [dimension_schema, perturbation_records, breakpoints, validity_envelope, critical_case_report]
    delta_fields: [findings, evidence_updates, uncertainties, decisions, open_questions]
  critical-case:
    produces: [breakpoints, validity_envelope, critical_case_report]
    delta_fields: [findings, evidence_updates, uncertainties, decisions, open_questions]
```
## Thresholds and quality gates
- Breakpoints require an explicit outcome criterion and before/after evidence.
- Envelope claims must state untested regions and uncertainty.
## Failure and counterexamples
Do not infer an envelope from a single favorable case. Mark extrapolation outside sampled axes as unsupported.
## Provenance map
- concept: validity-envelope-mapping [strategy]
- resolved: systematic-perturbation
- resolved: variation-axis-definition
- resolved: controlled-perturbation
- concept: validity-envelope-construction [sop]
- resolved: adversarial-stress-testing
- concept: validity-envelope-mapping [stress strategy]
- resolved: parameter-space-mapping
- resolved: extreme-value-generation
- resolved: breakpoint-detection
- intermediate: Pass5/validity-envelope-analysis
- intermediate: Pass5/boundary-stress-test
## Preserved source criteria ledger
| source | source line | kind | source criterion |
|---|---:|---|---|
| v4 architecture | modes/calls | structural | Actual modes are `systematic-perturbation`, `boundary-value-stress`, `critical-case`; alias labels are not used. |
## Context checkpoint / Delta notes
Append axes, values, perturbations, breakpoints, envelope, critical cases, scaling findings, and untested regions.

## Mode branches
- `systematic-perturbation`: broad controlled variation across declared axes. You MUST load skill `apply-perturbation` to vary the declared axes systematically.
- `boundary-value-stress`: emphasize boundary, pathological, and adversarial values. You MUST load skill `apply-perturbation` to probe boundary and pathological values.
- `critical-case`: select inference-maximizing cases and document selection logic. You MUST load skill `select-critical-case` to select and justify the decisive cases.

From yogsoth-ai/de-anthropocentric-research-engine, Apache-2.0.

More from yogsoth-ai/de-anthropocentric-research-engine