agentleFS
PthahnixPthahnix/De-Anthropocentric-Research-Engine/skills/robustness-analysis/SKILL.md

robustness-analysis

Skill504 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

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
  1. Distinctive:

    Do not perform called SOP operations inline.

    line 16
  2. Very specific:

    If the result needs explicit validity boundaries, consider map-validity-envelope.

    line 23
  3. Distinctive:

    Do not call a conclusion robust when all variants share the same unchallenged assumption.

    line 33

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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.

  1. You MUST load skill surface-assumptions to surface assumptions.
  2. You MUST load skill generate-alternative-model to generate plausible alternatives.
  3. You MUST load skill assess-sensitivity to compare sensitivity across variants.
  4. You MUST load skill identify-load-bearing-factors to identify load-bearing factors.
  5. You MUST load skill analyze-scaling-regime to check scaling regimes. If the result needs explicit validity boundaries, consider map-validity-envelope. If apparent agreement may reuse evidence or priors, consider audit-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.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.