axis-extraction
Axis-extraction identifies and extracts dimensions of variation from academic literature by analyzing how authors compare methods, discuss trade-offs, and highlight design choices. Use this skill when systematically mapping the conceptual landscape of a research domain, validating that extracted axes are independent, and documenting them as reusable dimensions for knowledge organization.
git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine /tmp/axis-extraction && cp -r /tmp/axis-extraction/skills/axis-extraction ~/.claude/skills/axis-extractionSKILL.md
# Axis Extraction Systematically extract axes of variation from literature. Look for how authors compare methods, what trade-offs they discuss, what design choices they highlight. ## Available SOPs - dimension-page-creation — create pages for identified dimensions - axis-validation — verify axes are independent and meaningful - wiki-search — check for existing dimension coverage ## Guiding Principles - **Comparison reveals axes.** When authors say "method A is X while method B is Y", X-Y is likely a dimension. - **Trade-offs are dimensions.** "You can have speed or accuracy" reveals the speed-accuracy dimension. - **Taxonomies are pre-built axes.** Existing classifications in the field are validated dimensions. - **Independence test.** If changing one axis always changes another, they're not independent. ## Minimum Yield <HARD-GATE> ≥2 candidate axes identified per invocation with independence assessment. </HARD-GATE> <!-- BEGIN available-tables (generated) --> ## Available SOPs Optional, no fixed order; the final leaf is always a sop. | SOP | When to use | | --- | --- | | axis-validation | SOP for validating that candidate axes are independent and meaningful. | | dimension-page-creation | SOP for creating a dimension page — documents an axis of variation with its values and semantics. | <!-- END available-tables (generated) -->
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