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 validate-causal-linkBefore 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.
validate-causal-link
Purpose
Audit a causal relation for clarity, existence, sufficiency, and logical completeness using CLR-style checks.
Input contract
yaml
required: [causal_relation, source_evidence, boundary_conditions]
optional: [causal_graph, alternative_explanations, clr_checklist]
constraints: [the relation has explicit cause and effect; distinguish clarity, existence, sufficiency, and logical completeness]Procedure
- Parse the causal relation and define its scope and terms.
- Check whether the stated cause exists and is connected to the effect.
- Test sufficiency, omitted conditions, and alternative explanations.
- Record each CLR result and return a validated, weakened, or unresolved link.
Output contract
yaml
produces: [causal_link_assessment, clr_results, missing_conditions, evidence_requests]
delta_fields: [findings, evidence_updates, hypothesis_updates, uncertainties]Quality gates
- All eight CLR categories are retained when the caller supplies the full checklist.
- Clarity, existence, sufficiency, and logical completeness are reported separately.
- A causal label is not accepted when evidence supports only association.
Parameterization
The caller must provide the cause/effect schema, evidence and boundary conditions, CLR checklist, alternative-explanation fields, and verdict vocabulary.
Failure and counterexamples
Reject links with undefined variables, missing scope, circular support, or causal language unsupported by the evidence.
Provenance map
- resolved: deep-insight/clr-validation
Preserved source criteria ledger
| source | physical line | kind | source criterion |
|---|---|---|---|
| deep-insight/clr-validation | 13 | structural | Retain eight CLR validation categories for causal claims: clarity, existence, sufficiency, and logical completeness are explicit checks. |
