axis-validation
The axis-validation skill tests whether candidate research dimensions are independent and practically useful by checking pairwise independence, searching for empirical examples of independent variation, and removing dimensions that either always co-vary with others or lack meaningful variation. Use this during research framework development to ensure analytical axes are orthogonal and capture distinct aspects of the study space.
git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine /tmp/axis-validation && cp -r /tmp/axis-validation/skills/axis-validation ~/.claude/skills/axis-validationSKILL.md
# Axis Validation
Verify that candidate dimensions are truly independent and meaningful.
## Tool
`vault_query_graph` + `vault_search`
## Protocol
1. For each pair of candidate dimensions, check: can one change without the other changing?
2. Search literature for examples where dimensions vary independently
3. If dimensions always co-vary, merge them into one
4. If a dimension has only 1 value in practice, it's not a useful dimension — remove it
## HARD-GATE
<HARD-GATE>
Must test pairwise independence for all candidate dimensions.
</HARD-GATE>
## Yield
Returns: `{ validated: string[], merged: string[], removed: string[] }`Experiment-specific - summarize the DARE executor's research design into a clean research_result report, forced to write back into the spec file produced by formated-specs.
Experiment-specific - replaces writing-specs, emits DARE's 4-layer call plan as a clean research_graph schema. Last step forces load formated-result.
loss-1 judge - read a sample's full dialogue and decide whether the user simulator semantically enacted its Policy Card. check-blind.
loss-2 judge - pairwise quality comparison across the n rungs within one topic; decide monotonicity and endpoint separation. check-blind, D1-D5 only.
Strategy: Inference to the best explanation in the face of anomalies
Remove components one by one, observe system changes to reveal hidden
Map system architecture to ablatable units for ablation studies
Design ablation studies to isolate component contributions in ML systems