alias-resolution
This skill detects when multiple concept pages in a vault refer to the same entity under different names and consolidates them into a single canonical page. Use it when maintaining a knowledge base where synonyms, alternative terminologies, or duplicate entries create fragmentation, ensuring unified content, redirected references, and updated cross-linking throughout the system.
git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine /tmp/alias-resolution && cp -r /tmp/alias-resolution/skills/alias-resolution ~/.claude/skills/alias-resolutionSKILL.md
# Alias Resolution
Detect when two concept pages refer to the same thing under different names. Merge into canonical page.
## Tool
`vault_search` + CC file operations + `vault_add_edge`
## Protocol
1. Search vault for the concept name and common synonyms
2. If multiple pages cover the same concept: choose canonical name
3. Merge content from duplicate into canonical page
4. Redirect all edges from duplicate to canonical
5. **Inline wikilinks:** After edge redirection, ensure the canonical page body contains `[[dir/slug]]` for all targets (dir/slug = target path minus `.md`). Place inline at semantically relevant locations. Skip if already present.
6. Delete duplicate page
7. Update index
## HARD-GATE
<HARD-GATE>
Before merging, verify the pages truly refer to the same concept (not related but distinct concepts).
</HARD-GATE>
## Yield
Returns: `{ merged: boolean, canonical: string, aliases_resolved: 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