robustness-analysis
Skill505 starsChanged 52 days agoApache-2.0View on GitHub
Generate plausible model variants and test whether conclusions converge across assumption/model choices.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- yuiseki/GeoAI-master-skillstheir own version, first seen Oct 17, 2026
- Pthahnix/De-Anthropocentric-Research-Engineword for word, first seen Oct 9, 2026
Other versions2 projects use a version of this.
Word for word · 1
- Pthahnix/De-Anthropocentric-Research-Engine★ 504100% same
Edited · 0
None found.
Wrote their own version · 1
- yuiseki/GeoAI-master-skills★ 3same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository270 other files it gives its agents.
- abstract-structureSkill
- adjudicate-exchangeSkill
- adjust-abstraction-scopeSkill
- adversarial-deliberationSkill
- aggregate-rankingSkill
- analogical-discoverySkill
- analyze-constraints-readinessSkill
- analyze-experiment-resultsSkill
- analyze-future-scenariosSkill
- analyze-heterogeneitySkill
- analyze-interventionSkill
- analyze-leaderboard-dynamicsSkill
- analyze-patent-citation-networkSkill
- analyze-scaling-regimeSkill
- analyze-temporal-trajectorySkill
- apply-perturbationSkill
- apply-question-frameworkSkill
- apply-separation-principleSkill
- apply-stage-gateSkill
- apply-veto-filterSkill
- appreciative-reframeSkill
- assess-construct-validitySkill
- assess-evidence-saturationSkill
- assess-goal-feasibilitySkill
- assess-patent-claim-scopeSkill
- assess-patent-legal-statusSkill
- assess-prior-art-and-claimsSkill
- assess-problem-wickednessSkill
- assess-publication-biasSkill
- assess-question-qualitySkill
- assess-ranking-consistencySkill
- assess-readiness-dimensionSkill
- assess-removabilitySkill
- assess-sensitivitySkill
- assess-system-boundarySkill
- assumption-stress-testSkill
- atomize-claimSkill
- atomize-conceptSkill
- attach-evidence-to-relationSkill
- audit-benchmark-validitySkill
- audit-convergence-independenceSkill
- audit-data-contaminationSkill
- audit-explanatory-compressionSkill
- audit-reporting-qualitySkill
- audit-structural-equivalenceSkill
- audit-structure-consistencySkill
- audit-study-validitySkill
- audit-validator-independenceSkill
- biologize-problemSkill
- biomimetic-transferSkill
- build-concept-fanSkill
- build-current-reality-treeSkill
- build-domain-ontologySkill
- build-failure-chainSkill
- build-noncircularity-matrixSkill
- calibrate-adversarial-confidenceSkill
- calibrate-probability-forecastSkill
- canonicalize-entitySkill
- categorize-evidenceSkill
- challenge-assumptionSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Do not perform called SOP operations inline.
- Very specific: line 23
If the result needs explicit validity boundaries, consider map-validity-envelope.
- Distinctive: line 33
Do not call a conclusion robust when all variants share the same unchallenged assumption.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
robustness-analysis
Purpose
Generate plausible model variants and test whether conclusions converge across assumptions and model choices.
Input contract
required: [base_model, conclusion, load_bearing_assumptions]
optional: [evidence, alternative_models, sensitivity_dimensions]
constraints: [variants must preserve the declared target question]Execution protocol
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
- You MUST load skill
surface-assumptionsto surface assumptions. - You MUST load skill
generate-alternative-modelto generate plausible alternatives. - You MUST load skill
assess-sensitivityto compare sensitivity across variants. - You MUST load skill
identify-load-bearing-factorsto identify load-bearing factors. - You MUST load skill
analyze-scaling-regimeto check scaling regimes. If the result needs explicit validity boundaries, considermap-validity-envelope. If apparent agreement may reuse evidence or priors, consideraudit-convergence-independence. Deviation: omit scaling analysis only when the model has no scale variable; document the reason.
Output contract
produces: [model_variant_set, convergence_assessment, fragility_flags, load_bearing_factors]
delta_fields: [findings, hypothesis_updates, uncertainties, decisions]Thresholds and quality gates
- B: at least two plausible variants are compared; conclusion changes, invariants, and fragility drivers are explicit.
Failure and counterexamples
Do not call a conclusion robust when all variants share the same unchallenged assumption.
Provenance map
robustness-testing,multi-model-convergence,alternative-model-generation,convergence-assessment,fragility-flagging: resolved.assumption-enumeration: intermediate (only package-prefixed variants exist).
Preserved source criteria ledger
- Preserve multi-model convergence and explicit fragility reporting.
Context checkpoint / Delta notes
Append variants, changed assumptions, convergence results, and fragility flags.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

