Agent skill · data analytics · aiskillstore
entity-optimizer
Use when the user asks to "optimize entity presence", reconcile an entity identity, or update canonical Knowledge Graph facts; audits and maintains machine-facing identity, sameAs, schema, disambiguation, and AI-recognition evidence through the entities registry. Not for page-level AI-citation readiness - use geo-content-optimizer; not for human-facing brand canon - use narrative-registry. 实体优化/知识图谱
Why this skill is useful
Provides domain-specific knowledge for optimizing entity presence in Knowledge Graphs, including reconciliation and auditing processes not commonly known to AI.
What it needs
Requires python3 installed locally. About 4k tokens when loaded. Last updated 2026-08-07. 405 stars on the source repository.
What this skill does
Entity Optimizer The canonical machine-facing entity authority. It records identity and recognition facts with provenance; it does not own positioning, brand voice, claim approval, or page copy. Quick Start Skill Contract Unit: one stable, non-PII entity aggregate ID. Reads: memory/events/entities.ndjson, memory/projections/entities.json, the Narrative and claims projections, verified source records, and optional rendered views. Writes: authorized entity events through scripts/registry-events.py; a Markdown view under memory/entities/ may then be regenerated from accepted projection state. Done when: the six signal categories have Pass/Partial/Fail/Unknown observations with evidence, identity conflicts are resolved or left open, every accepted change has an event ID/offset/revision, and verify entities passes. Only a host-capability entity-optimizer principal may accept/reject proposals or upsert/transition canonical entity state. Other skills may append only operation: propose. A host-capability memory-management principal may tombstone or erase under explicit authority. The NDJSON stream is canonical; JSON and Markdown projections are rebuildable views and must never be edited as authority. Layer Boundary This registry owns machine-facing identity: canonical type, aliases, schema type, QID, sameAs, domain, disambiguation evidence, and observed recognition state. narrative-registry owns human-facing canon: positioning, message system, voice, naming, and approved descriptions. offer-claims-registry owns claim substantiation. Entity descriptions may render Narrative canon but must carry narrativecanonid, narrativecanonversion, and claimsprojectionoffset; they never override either registry. Handoff Summary Use skill-contract.md. Include changed event IDs, latest projection offset/revision, unresolved identity conflicts, Narrative/claims dependency tuple, and one next skill. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aiskillstore/entity-optimizer