seo-seranking

SE Ranking AI visibility analyst (extension). Tracks AI Share-of-Voice across ChatGPT, Gemini, Perplexity, AI Overviews, and AI Mode in a single query.

Quality

70%

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 ./extensions/seranking/skills/seo-seranking/SKILL.md

Quality

Content

72%

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

The body is concise, well-sectioned, and appropriately scoped for a simple skill, with concrete routing commands and named output fields. Its main gaps are the lack of an executable API-call example and missing validation/feedback checkpoints around the AI-visibility query workflow.

Suggestions

Add one executable example showing the actual SE Ranking API call (endpoint + request shape) for the ai-visibility command, so guidance is copy-paste ready.

Add an explicit validation/feedback step after the API query — e.g. check the unit-accounting response and the confidence note, and retry or surface an error if sample size is too small.

Confirm or create the referenced bundle files (scripts/dataforseo_costs.py, extensions/seranking/install.sh) so the inline references resolve to real paths.

Dimension	Reasoning	Score
Conciseness	The body (~43 lines) is lean and sectioned with no padding or basic-concept explanation; e.g. the 'AI Share-of-Voice scoring' section states output fields directly. Every token earns its place; matches the level-3 'lean and efficient' anchor.	3 / 3
Actionability	Concrete routing commands ('/seo seranking ai-visibility <brand>'), named output fields (chatgpt_sov etc.), and a named script are present, but there is no executable API call example — guidance like 'Report each as a percentage' is descriptive rather than copy-paste ready. Level 2 (some concrete guidance but incomplete); not level 1 because commands and fields are concrete, not level 3 due to missing executable API example.	2 / 3
Workflow Clarity	Steps are sequenced (prerequisites → routing → scoring fields → cost guardrails) and include a pre-call API-key validation, but the scoring/batch API calls lack validation checkpoints or an error-recovery feedback loop, which the rubric expects for batch operations. Not level 1 because a clear sequence exists; not level 3 because validation/feedback is implicit only.	2 / 3
Progressive Disclosure	Short, well-organized single-file skill with clear sections and no deeply nested references; no bundle files exist, so the simple-skill exception applies. Referenced paths (scripts/dataforseo_costs.py, install.sh) are mentioned but not bundled, yet the structure itself is clear and navigable. Matches level-3 for a simple skill.	3 / 3
	Total	10 / 12 Passed

Description

67%

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 distinctive, naming concrete platforms and a clear single-query action, but it omits any explicit 'Use when...' trigger clause, which caps completeness. Trigger terms are accurate but lean on specialized jargon over everyday user phrasing.

Suggestions

Add a 'Use when...' clause, e.g. 'Use when the user asks about brand visibility in ChatGPT/Gemini/Perplexity/AI Overviews/AI Mode or wants AI Share-of-Voice metrics.'

Broaden trigger terms with everyday phrasing like 'AI search mentions', 'LLM citations', or 'where does the brand appear in AI answers' alongside the niche jargon.

Dimension	Reasoning	Score
Specificity	Quotes 'Tracks AI Share-of-Voice across ChatGPT, Gemini, Perplexity, AI Overviews, and AI Mode in a single query' — names a concrete action and enumerates five specific platforms. Matches the level-3 anchor (multiple specific concrete actions); not level 2 because the action set is comprehensive rather than partial.	3 / 3
Completeness	Clearly states what the skill does but lacks any 'Use when...' or equivalent explicit trigger guidance — per the rubric this caps completeness at 2. Not level 3 because the 'when to use' trigger is absent; not level 1 because the 'what' is explicit and strong.	2 / 3
Trigger Term Quality	Relevant terms ('AI visibility', 'Share-of-Voice', named platforms) are present but specialized; common variations a user might say ('AI search tracking', 'LLM mentions', 'where does my brand show up in AI answers') are missing. Not level 1 because the niche terms are natural for the audience; not level 3 due to limited coverage.	2 / 3
Distinctiveness Conflict Risk	Targets a distinct niche (AI Share-of-Voice via SE Ranking) with platform-specific triggers unlikely to overlap with generic SEO skills. Not level 2 because the (extension) scoping and AI-SoV framing clearly separate it from sibling seo-* skills.	3 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: AgriciDaniel/claude-seo
Path: extensions/seranking/skills/seo-seranking/SKILL.md
Commit: 09d37c7

Reviewed: 4 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.