abstract-structure
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Map where a claim, method, or design remains valid by defining variation axes, probing systematic or adversarial/boundary values, detecting breakpoints, and constructing a multidimensional validity envelope. Critical-case selection is an optional inference-maximizing mode.
Claude Code
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill map-validity-envelope --agent claude-code
Codex
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill map-validity-envelope -a codex -y
Cursor
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill map-validity-envelope -a cursor -y
Gemini CLI
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill map-validity-envelope -a gemini-cli -y
GitHub Copilot
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill map-validity-envelope -a github-copilot -y
OpenCode
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill map-validity-envelope -a opencode -y
Windsurf
$ npx skills add yogsoth-ai/de-anthropocentric-research-engine --skill map-validity-envelope -a windsurf -y
name: map-validity-envelope description: "Map where a claim, method, or design remains valid by defining variation axes, probing systematic or adversarial/boundary values, detecting breakpoints, and constructing a multidimensional validity envelope. Critical-case selection is an optional inference-maximizing mode."
Map where a claim, method, or design remains valid by defining axes, probing values, detecting breakpoints, and constructing a multidimensional validity envelope.
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_inputDo 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.
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]Do not infer an envelope from a single favorable case. Mark extrapolation outside sampled axes as unsupported.
| 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. |
Append axes, values, perturbations, breakpoints, envelope, critical cases, scaling findings, and untested regions.
A research skill graph for AI-native science. 271 markdown files. No runtime, no dependencies, no build step.
Remove domain surface details to expose transferable relational/mechanistic structure at a chosen abstraction level.
Evaluate competing arguments against stated criteria and produce a reasoned verdict with uncertainty.
Move a scientific object up/down in abstraction or narrow/broaden selected scope dimensions (population, mechanism, context,…
Run structured attack/defense/adjudication over a claim, candidate, criterion set, or current winner. Perspective, target,…
Aggregate criterion or comparison results into an ordered recommendation under an explicit rule.
Abstract relational structure from source domains, map it to the target, validate depth, and instantiate transferable mechanisms.
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers…
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling…