AC no-uv-filter-protection
用户在纠结"要不要装UV镜保护镜头"、问"UV镜有没有用"、或发现照片有炫光 想排查原因时调用。不适用于滤光镜创意使用（应调用其他滤光镜相关skill） 或纯器材购买建议。 Invoke when the user is debating "should I put a UV filter on my lens," asks "is a UV filter useful," or has lens flare and wants to troubleshoot. Not for creative filter usage (other filter skills) or pure gear purchase advice. 关键 trigger / Key triggers: "UV镜"、"天光镜"、"保护镜头"、"UV filter"、 "skylight filter"、"lens protection"、"lens flare"、 "should I use UV filter"、"do I need a UV filter"、"lens flare causes"。
用户在纠结"要不要装UV镜保护镜头"、问"UV镜有没有用"、或发现照片有炫光 想排查原因时调用。不适用于滤光镜创意使用（应调用其他滤光镜相关skill） 或纯器材购买建议。 Invoke when the user is debating "should I put a UV filter on my lens,"…
As a process C 63/100 · 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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "source_book" - note
frontmatter-keyunknown frontmatter key "source_chapter" - note
frontmatter-keyunknown frontmatter key "related_skills"
Process rating: all ten parameters 63/100
- 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
- 100Tools and files. No external tools needed
- 100Steps. 54 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 545 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
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 11 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 494: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 54 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.