How to use
- Copy the installation command and review the source package before installing it in your own agent environment.
- Check the source document for required tools, credentials and supported hosts.
- Describe your input and desired deliverable; review the output against the source material.
npx skills add https://github.com/yogsoth-ai/de-anthropocentric-research-engine --skill enumerate-validator-assumptionsBefore you start
- Installation does not include a model subscription, API allowance or permission to access your files.
- Repository stars and installation counts describe activity, not an independent quality or security test.
Original skill document
Rendered from the source repository. Headings, examples, code, tables, links, and referenced images are preserved.
enumerate-validator-assumptions
Purpose
Enumerate assumptions embedded in a validator, benchmark, sandbox, or test.
Input contract
yaml
required: [validator_artifact, target_claim]
optional: [data_generation, measurement, simulator, oracle, metric, initialization, acceptance_rule]
constraints: [assumptions must be classified by source and role]Procedure
- Inspect data generation, measurement, simulator, oracle, metric, initialization, and acceptance.
- Record each assumption and its relation to the target.
- Mark evidence, uncertainty, and potential circularity.
If validator assumptions and dependencies are explicit, consider build-noncircularity-matrix as the next tactic.
Output contract
yaml
produces: [validator_assumption_inventory, dependency_links, circularity_candidates]
delta_fields: [findings, evidence_updates, uncertainties, open_questions]Quality gates
- No assumption is omitted merely because it is conventional.
Failure and counterexamples
An unstated assumption remains unknown, not independent.
Provenance map
- resolved: circular-validation-audit
