entity-registry

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. 实体注册/知识图谱

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A lean, actionable, protocol-grade skill body with a clear sequenced workflow, validation checkpoint, and well-signaled one-level-deep references to verified bundle files. The only notable weakness is moderate redundancy in authority/qualification language that inflates tokens.

Suggestions

Consolidate the repeated host-capability/authority caveats into a single "Authority" callout so the same constraint is not restated across the Skill Contract, Instructions step 6–7, and the closing "Never" list.

Tighten the privacy paragraph by moving the legal-basis mechanics into a reference file and keeping only the operational rule inline, reducing qualification sentences like "This is operational guidance, not legal advice."

Dimension	Reasoning	Score
Conciseness	The body is dense and avoids explaining concepts Claude already knows, but repeated authority caveats ("host-capability principal", "Never edit... by hand") and qualifying clauses ("This is operational guidance, not legal advice") could be tightened without losing meaning.	2 / 3
Actionability	Provides fully executable commands ("python3 \"$AARON_SKILLS_ROOT/scripts/registry-events.py\" get entities <aggregate-id>", "verify entities", connector calls) and concrete Quick Start examples that are copy-paste ready.	3 / 3
Workflow Clarity	A numbered 1–9 Instructions sequence is paired with explicit Decision Gates stop-conditions and a terminal "Run verify entities" validation checkpoint, giving clear feedback loops for a fragile batch/authority operation.	3 / 3
Progressive Disclosure	Sections are well-organized and bundle references (entity-signal-checklist.md, knowledge-graph-guide.md, knowledge-panel-wikidata-guide.md) all resolve to real files in ./references/ and are signaled one level deep in the Reference Materials section.	3 / 3
	Total	11 / 12 Passed

Description

85%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, well-scoped description that pairs concrete capabilities with explicit positive and negative triggers and clear sibling-skill disambiguation. Its main weakness is trigger phrasing that is more technical than what a typical user would naturally say.

Suggestions

Soften jargon-heavy triggers by adding plain-language variants a user might actually say (e.g., "fix entity info shown to AI", "claim a Knowledge Panel", "link my entity to Wikidata") alongside the technical terms.

Consider including one or two everyday trigger phrases ("why does ChatGPT/Perplexity get my company wrong") to broaden natural-keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("audits and maintains", "reconcile an entity identity", "update canonical Knowledge Graph facts") applied to specific domain objects (sameAs, schema, disambiguation, AI-recognition evidence), matching the highest anchor.	3 / 3
Completeness	Explicitly answers what ("audits and maintains machine-facing identity... through the entities registry") and when ("Use when the user asks to..."), with additional negative triggers, satisfying both halves with explicit triggers.	3 / 3
Trigger Term Quality	Includes a natural "Use when the user asks to..." framing and domain terms like "Knowledge Graph" and "entity identity", but the triggers lean technical ("canonical Knowledge Graph facts", "sameAs", "machine-facing identity") and omit common user-facing variations, so it stops short of full coverage.	2 / 3
Distinctiveness Conflict Risk	Clear niche (machine-facing entity identity) plus explicit "Not for... use geo-content-optimizer" and "not for human-facing brand canon - use narrative-registry" disambiguation, making conflicts with sibling skills unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

75%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 14 suspicious	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	12 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: protocol/entity-registry/SKILL.md
Commit: 4a77c48

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.