AC grok-geo
Diagnose a brand's visibility, recommendations, citations, competitor presence, factual accuracy, and content gaps in AI-assisted web search. Use for GEO audits, AI search visibility analysis, AI citation analysis, brand-versus-competitor comparisons, website GEO content diagnostics, ChatGPT/豆包/DeepSeek/通义千问/智谱 GLM/Kimi/文心一言/Claude/Gemini/Perplexity brand mention analysis, AI search optimization, and generative engine optimization (GEO) reports. Supports 17+ AI engines (8 international + 9 Chinese). Do not use for ordinary copywriting, general SEO keyword research, social-media scraping, guaranteed-ranking requests, or content publishing.
Diagnose a brand's visibility, recommendations, citations, competitor presence, factual accuracy, and content gaps in AI-assisted web search.
As a process C 63/100 · Has gaps — weak spots: result and completion, consistency, progress reporting
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 0. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "summary"
Process rating: all ten parameters 63/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (grok-geo) differs from the folder (geo-agent-skill)
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 70 steps
- 100Failures and branches. 6 branches, has a failure section
- 100Execution cost. Instruction body is 1711 tokens
- 100Running it twice. No mutating operations
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 23 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 646: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 70 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.