geo-content-optimizer

Optimize content for AI citations in ChatGPT, Perplexity, AI Overviews, Gemini, Claude. AI引用优化/GEO优化/AI搜索

Quality

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.cursor/skills/geo-content-optimizer/SKILL.md

Quality

Content

52%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 skill is well-structured with real references and a clear sequenced workflow including validation checkboxes, but it is noticeably verbose and leans on fill-in-the-blank templates rather than fully executable guidance. Tightening the prose and moving the inlined benchmark tables into their reference file would most improve it.

Suggestions

Cut the motivational preamble and resolve the duplicate 'When This Must Trigger' intro sentences to reduce verbosity from anchor 2 toward 3-4.

Move the inlined CORE-EEAT priority table and 14-row post-optimization self-check into references/core-eeat-benchmark.md, keeping only a short pointer in SKILL.md.

Replace the fill-in-the-blank report templates with at least one fully concrete worked example per workflow step so the guidance is copy-paste ready rather than placeholder-driven.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: it carries motivational preamble ('As AI systems increasingly answer user queries directly...'), two competing 'When This Must Trigger' intro sentences, restated checklists, and large inlined tables, amounting to several padded sections beyond just minor over-explanation.	2 / 5
Actionability	Concrete numeric rules (25-50 word definitions, ≥5 data points, ≥1 citation per 500 words, JSON-LD FAQPage) and a worked before/after example are present, but the core workflow outputs are fill-in-the-blank templates ([X], [Definition 1]) rather than executable commands, matching the 'some concrete guidance but template/placeholder' anchor.	3 / 5
Workflow Clarity	A clear five-step sequence is followed by a post-optimization self-check table and separate input/output validation checkboxes; it falls short of anchor 5 because the self-check is a status table rather than a true validate→fix→retry feedback loop.	4 / 5
Progressive Disclosure	Three real, one-level-deep references (geo-optimization-techniques.md, ai-citation-patterns.md, quotable-content-examples.md) are clearly signaled with good section structure, but the large inlined CORE-EEAT benchmark table and 14-row self-check table duplicate content that belongs in the referenced core-eeat-benchmark.md.	4 / 5
	Total	13 / 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 a clear, multilingual, niche-specific statement of what the skill does with strong trigger-term coverage, but it lacks an inline 'Use when...' clause and lists only one concrete action, capping completeness and specificity. Moving the when_to_use trigger phrasing into the description and naming more discrete actions would raise it.

Suggestions

Append an explicit trigger clause to the description, e.g. 'Use when optimizing content for ChatGPT, Perplexity, AI Overviews, Gemini, or Claude citations.'

Name a few concrete actions beyond 'optimize' (e.g. 'add quotable definitions, inject citations, structure FAQ schema') to lift specificity from 3 to 4-5.

Fold the most common English trigger variants ('AI search optimization', 'get cited by AI') into the description so trigger-term quality approaches comprehensive coverage.

Dimension	Reasoning	Score
Specificity	The phrase 'Optimize content for AI citations' names the domain plus one concrete action (optimizing for AI citations) and enumerates target engines, but does not list several distinct concrete actions, matching the anchor for 'Names domain and 1-2 concrete actions, but not comprehensive'.	3 / 5
Completeness	The 'what' is clear ('Optimize content for AI citations'), but the description itself contains no explicit 'Use when...' trigger clause — that guidance lives in the separate when_to_use field, so per the rubric a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Natural terms include 'AI citations', 'GEO优化', 'AI引用优化', 'AI搜索' plus named engines (ChatGPT, Perplexity, Gemini, Claude), giving good multilingual synonym coverage; falls short of anchor 5 only because a few common English variations (e.g. 'AI search optimization') are absent.	4 / 5
Distinctiveness Conflict Risk	The GEO/AI-citation niche with named engines and multilingual triggers is mostly distinct with only minor overlap risk; the generic leading verb 'Optimize content' keeps it just short of the clearly-niche anchor 5.	4 / 5
	Total	14 / 20 Passed

Validation

81%

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 — 13 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: MODSetter/SurfSense
Path: .cursor/skills/geo-content-optimizer/SKILL.md
Commit: 031a7dc

Reviewed: 1 day 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.