entity-optimizer

Build entity presence in Knowledge Graph, Wikidata, AI systems for brand recognition and citations. 实体优化/知识图谱

Quality

66%

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

Fix and improve this skill with Tessl

tessl review fix ./.cursor/skills/entity-optimizer/SKILL.md

Quality

Content

71%Weight 40%Scale 1-5

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

The content is well-structured with strong progressive disclosure (verified one-level references) and a clear sequenced workflow with validation checklists. Its main weakness is moderate verbosity in the conceptual intro that assumes too little of Claude's existing knowledge.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient (templates, checklists, reference callouts earn their place) but includes unnecessary explanation Claude already knows — the entity definition ("Entities — the people, organizations, products...") and the "Why entities matter for SEO + GEO" bullets — so it lands at the "mostly efficient with some unnecessary explanation" anchor rather than the lean anchor of 4.	3 / 5
Actionability	It provides concrete copy-paste report templates, specific AI test queries ("What is [entity name]?", "Who founded [entity name]?"), explicit signal categories, and points to real reference files for detail; as an instruction-only skill this is actionable with only minor gaps, matching the "mostly executable guidance" anchor at 4 rather than fully self-contained at 5.	4 / 5
Workflow Clarity	A clear Step 1/2/3 sequence plus a dedicated Validation Checkpoints section with Input and Output checklists gives strong sequencing, but there is no explicit validate→fix→retry feedback loop, leaving it just below the checkpoint-plus-feedback-loop anchor of 5.	4 / 5
Progressive Disclosure	The SKILL.md is a clear overview with well-signaled one-level-deep references to five verified bundle files (entity-signal-checklist.md, example-audit-report.md, entity-type-reference.md, knowledge-panel-wikidata-guide.md, knowledge-graph-guide.md), with content appropriately split and easy navigation, matching the top anchor exactly.	5 / 5
	Total	16 / 20 Passed

Description

61%Weight 40%Scale 1-5

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

The description is specific and distinct, naming concrete target systems and including multilingual trigger terms, but it lacks an explicit "Use when..." clause, which caps its completeness at 3. Adding a trigger clause would substantially raise the score.

Suggestions

Append a "Use when..." clause naming concrete user triggers, e.g. "Use when the user says their brand has no Knowledge Panel, Google doesn't recognize their entity, or they need Wikidata/entity disambiguation."

Add the natural trigger term "knowledge panel" (and "knowledge card") to the description, since these are among the most common user phrases for this task.

Broaden the action verbs beyond a single "Build" — e.g. "Audits, builds, and disambiguates entity presence" — to reflect the multiple concrete actions the skill performs.

Dimension	Reasoning	Score
Specificity	Names the domain and three concrete target systems ("Knowledge Graph, Wikidata, AI systems") but offers only one action verb ("Build entity presence"), matching the anchor for 1-2 concrete actions without comprehensive coverage rather than the several-action anchor at 4.	3 / 5
Completeness	It clearly states what ("Build entity presence in Knowledge Graph, Wikidata, AI systems for brand recognition and citations") but contains no "Use when..." clause or equivalent trigger guidance, which the rubric explicitly caps at 3.	3 / 5
Trigger Term Quality	Good keyword coverage including "Knowledge Graph", "Wikidata", "AI systems", "brand recognition", "citations", plus multilingual synonyms ("实体优化/知识图谱"), but omits common natural phrases like "knowledge panel" that users would say, keeping it below the comprehensive anchor of 5.	4 / 5
Distinctiveness Conflict Risk	The entity/Knowledge-Graph/Wikidata niche is clearly distinct from generic skills, but "brand recognition" and "citations" create minor overlap risk with closely related SEO/GEO skills in the same library, so it is mostly distinct rather than minimal-conflict at 5.	4 / 5
	Total	14 / 20 Passed

Validation

87%

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 — 14 / 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

	Total	14 / 16 Passed

Repository: MODSetter/SurfSense
Path: .cursor/skills/entity-optimizer/SKILL.md
Commit: be4a191

Reviewed: 15 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.