Skip to main content
ClaudeWave
Skill331 repo starsupdated today

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.

Install in Claude Code
Copy
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-validation
Then start a new Claude Code session; the skill loads automatically.

SKILL.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[] }`