AB tianshu-short-script
根据主题与时长生成短视频口播分镜表：镜号、秒数、画面、口播、花字/字幕提示。 Use when: 用户要做短视频、口播、分镜、抖音/B 站/视频号脚本；用户说「口播脚本」「分镜表」「60 秒视频怎么拍」。 NOT for: 直接导出剪映工程文件；复杂多机位院线级分镜（本 skill 偏口播/Vlog 结构）。
As a process B 65/100 · Nearly there — weak spots: inputs and preconditions, failures and branches, progress reporting
How to improve
For the model run — optional
- 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
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 65/100
- 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
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 5 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 193 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
- +5Description has no quoted example phrases that should trigger the skill
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 155: enough signal without eating the budget
- +4Structure: 5 headings
- +3Step-by-step instructions: 5 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 94.
External checks
ClawHub: suspicious
The skills are mostly coherent, but the bundled autoreview helper gives nested review agents full unsandboxed authority by default, which deserves manual review before use.
LLM: suspicious (high) · VirusTotal: · 29 May 2026