AC geo-claw
Top-tier GEO (Generative Engine Optimization) expert agent for managing daily AI visibility operations. Use this skill whenever someone wants to optimize brand visibility in AI search engines (ChatGPT, Perplexity, 豆包, Kimi, DeepSeek, 文心一言, Claude), run AIEO diagnostics, create AI-optimized content, monitor AI mention rates, build question libraries, or execute any GEO/AEO/AIEO workflow. Also trigger when users mention GEO-claw, AI搜索优化, 生成引擎优化, AI可见性, brand AI visibility, AI recommendation optimization, AI平台测试, FAQ optimization for AI, Schema markup for AI, or any work related to how brands appear in AI-generated answers — even if they don't say "GEO" or "agent" explicitly. Any AI visibility or generative search optimization work qualifies.
As a process C 50/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
How to improve
- 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: 37. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 50/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 20 mutating operations with no state check
- 40Consistency. Frontmatter name (geo-claw) differs from the folder (moments-geo-claw)
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 6 branches
- 70Execution cost. Instruction body is 4541 tokens
- 100Steps. 67 steps
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
- medium 4 test cases, all positive: not one "should refuse" or "should ask first"
- low No test case covers injection arriving through data
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 749: enough signal without eating the budget
- +4Structure: 41 headings
- +3Step-by-step instructions: 67 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (20 of 20)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.