Group overlapping skill documents into ranked merge, migrate, and cross-reference reports.
npx skills add https://github.com/thistleknot/skills --skill consolidation-thistleknot
Please help me install this Agent Skill. Skill: consolidation Source: https://github.com/thistleknot/skills/tree/main/consolidation Command: npx skills add https://github.com/thistleknot/skills --skill consolidation-thistleknot
Consolidation eliminates drift in a growing skill library by identifying duplicated or overlapping content across multiple skill documents and proposing the correct governance action.
Run consolidation to produce consolidation_report.md and ranked merge/migrate/xref prescriptions for the current skills corpus.
High-intent search queries and answers about installing and using this skill.
To deduplicate overlapping documentation in a knowledge base, the process extracts subject–predicate–object triplets, computes pairwise semantic similarity, and emits ranked group reports with merge, migrate, or cross-reference prescriptions.
Semantic similarity clustering in repo maintenance identifies duplicated or overlapping content across skill documents by decomposing nearest-neighbor chains above a similarity threshold to isolate meaningful merge candidates.
You should run documentation governance during skill-library growth, after batches of edits, or when search results appear contradictory across multiple files, ensuring drift is eliminated by proposing correct governance actions.
Yes, consolidation uses networkx for graph clustering and scikit-learn for semantic similarity computations, leveraging these dependencies to build pairwise similarity matrices and decompose them into nearest-neighbor chains.
The best way to generate merge-ready reports for overlapping documents is extracting triplets with optional NLI soft matching, classifying adjacent links by similarity thresholds, and emitting ranked group documentation artifacts.
Consolidation runs do not block on embedding recomputation because the system uses an async embedding queue server that decouples the process, allowing it to leverage cached checkpoint data instead of recalculating synchronously.
sparq-orgMeasure structural similarity between RDF entities using predicate-IDF-weighted Jaccard similarity.
zhu637882-stackConsolidate session learnings into a searchable repository with export formats.
robertbr123Build and manage vector databases for RAG and semantic search with Qdrant.
lawve-aiIdentify governance and risk issues in AI deployments and vendor relationships.
