AB wjs-translating-subtitles
Use when the user has an SRT (or transcript text) in one language and wants it translated to another, with punctuation-bounded re-segmentation so cues end at real sentence breaks. Simplified Chinese (zh-CN) and English (en) are first-class targets; other targets follow the same rules. Outputs a target-language SRT or bilingual SRT — no audio, no burn-in. Triggers — "翻译字幕", "翻成中文", "translate this SRT", "中英双语字幕", "把这个 SRT 翻译成 X", "bilingual subtitles".
Use when the user has an SRT (or transcript text) in one language and wants it translated to another, with punctuation-bounded re-segmentation so cues end at…
As a process B 65/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting
The same skill appears in 1 more place: ClawHub
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: 2. 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
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 4 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 85Steps. 72 steps, 3 vague phrases
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2487 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (4 tags): a typed call is more reliable
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)
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +3Description length 455: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 72 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.