AC file-translate
Immersive file & image translation — preserving original layout, formatting, and visuals. Drop in a PDF, Word, PPT, Excel, image, ePub and get back a fully translated version that looks like it was authored natively. Supports 100+ languages for text, 14 for images, and all major document formats. Use when user asks to translate a file, document, image, spreadsheet, slide deck, or any text. Triggers: "翻译", "translate", "翻译这个文件", "translate this image", "把这个翻译成中文/英文", "document translation", "图片翻译", "文档翻译", "file translation", "translate PDF", "translate Word". Requires env TRANSLATE_360_API_KEY (360 AI Platform API key). Files and images are uploaded to api.360.cn for processing — do not use with confidential or sensitive documents unless you accept this data transfer.
As a process C 52/100 · Has gaps — weak spots: result and completion, failures and branches, consistency
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 52/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (file-translate) differs from the folder (360-translate)
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 36 steps
- 100Execution cost. Instruction body is 1417 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 778: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 36 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 100.