AB geo-plan-generator
Generate a complete AI-GEO (Generative Engine Optimization) marketing plan for a client and deliver it as two artifacts: a Word document (the presenter's teleprompter, full detail) and a minimal display-only PPTX (10-12 slides, lots of white space, one core point per slide). Works in two input modes — detailed mode when the user supplies target keywords and/or a source plan, and light mode when the user supplies only a company website or basic company info, in which case the agent self-researches the industry and auto-generates about 10 core GEO demand keywords before proceeding. Use when a user asks to make or redo a GEO marketing plan, an AI 搜索优化方案, a 生成式引擎优化方案, or wants a client-ready Word plus PPT for GEO, especially built on the 360 智见 (360 Zhijian) GEO methodology.
Generate a complete AI-GEO (Generative Engine Optimization) marketing plan for a client and deliver it as two artifacts: a Word document (the presenter's…
As a process B 65/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "agent_created"
Process rating: all ten parameters 65/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 7 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 109 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3205 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 16 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
- +4Description does not say when NOT to use the skill (false activations)
- +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
- +3Description length 781: enough signal without eating the budget
- +4Structure: 26 headings
- +3Step-by-step instructions: 109 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.