AC urban-renewal-analyst
This skill should be used when the user wants to analyze an urban renewal or renovation scene from a photo. It performs a structured multi-dimensional on-site analysis covering overall environment, structural form, facade, hard landscaping, furniture & fixtures, and greenery. It then recommends renovation strategies (automatically calibrated to the severity of issues found) and generates optimized Gemini 3 image-to-image prompts in multiple styles (photorealistic, architectural visualization, watercolor/hand-drawn). Each dimension is scored 1–5 with a total composite score. Trigger phrases include "帮我分析这张城市更新图片", "分析改造现场", "城市更新现场分析", "帮我看看这个场地怎么改", "生成改造提示词", "图生图提示词".
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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: 4. 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 59/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 92 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1717 tokens
- 100Running it twice. No mutating operations
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
- +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
- +5Description quotes 6 example trigger phrases
- +3Description length 678: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 92 items
- +4Has examples (14 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.