agentleFS
Sign inStart free
PthahnixPthahnix/De-Anthropocentric-Research-Engine/skills/assumption-stress-test/SKILL.md

assumption-stress-test

Skill504 starsChanged 50 days agoApache-2.0View on GitHub

Surface load-bearing assumptions, classify vulnerability, challenge or perturb them, and re-check causal logic.

1 other project uses 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 surviving result requires broader model and scaling variants, consider robustness-analysis as the next tactic.

    line 23
  3. Distinctive:

    Do not call a model robust when an untested high-vulnerability assumption carries the conclusion or when perturbation bounds are unstated.

    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

assumption-stress-test

Purpose

Expose load-bearing assumptions, classify their vulnerability, perturb them, and re-check causal validity.

Input contract

required: [claim_or_model, assumptions]
optional: [evidence, causal_graph, perturbation_bounds]
constraints: [each assumption must be traceable to a claim or causal link]

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 load-bearing assumptions.
  2. You MUST load skill classify-assumption-vulnerability to classify their vulnerability.
  3. You MUST load skill challenge-assumption to challenge each material assumption.
  4. You MUST load skill apply-perturbation to apply bounded perturbations.
  5. You MUST load skill validate-causal-link to re-check affected causal links. If the surviving result requires broader model and scaling variants, consider robustness-analysis as the next tactic. Deviation: omit perturbation only when the assumption is purely definitional; still record and classify it.

Output contract

produces: [assumption_register, vulnerability_map, perturbation_results, causal_recheck]
delta_fields: [findings, assumption_updates, uncertainties, decisions, open_questions]

Thresholds and quality gates

  • B: all load-bearing assumptions are classified; every challenged assumption has a perturbation or explicit non-perturbability reason; causal links are rechecked.

Failure and counterexamples

Do not call a model robust when an untested high-vulnerability assumption carries the conclusion or when perturbation bounds are unstated.

Provenance map

  • assumption-audit, assumption-stress-test, assumption-criticality, assumption-perturbation: resolved/concept according to exact v3 lookup; no near-name substitution.
  • Status: assumption-audit, assumption-stress-test, assumption-criticality resolved; assumption-perturbation concept (only package-prefixed variants found).

Preserved source criteria ledger

  • Preserve assumption surfacing, vulnerability classification, perturbation, and causal-link validation.

Context checkpoint / Delta notes

Append changed assumptions, perturbation deltas, causal failures, and unresolved questions.

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.

Check your setup, free