AB pdf-translator
Translate PDF documents while preserving original formatting. Converts PDF pages to images for layout analysis, extracts text and embedded images, translates content using agent's multilingual capabilities, and generates LaTeX code to recreate the original document structure with translated text. Special support for arXiv papers: when user provides arXiv ID (e.g., "2310.12345") or arXiv URL (e.g., "https://arxiv.org/abs/2310.12345" or "https://arxiv.org/pdf/2310.12345.pdf"), automatically download the source TeX files, translate the LaTeX content, and compile to PDF.
As a process B 70/100 · Nearly there — weak spots: when it triggers, 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: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Translate PDF documents while preserving original formatting. Conv… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 70/100
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (pdf-translator) differs from the folder (pdf-translate-skill)
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 170 steps
- 100Failures and branches. 6 branches, has a failure section
- 100Execution cost. Instruction body is 3984 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low 11 top-level sections: this looks like several domains in one skill
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 3 example trigger phrases
- +3Description length 573: enough signal without eating the budget
- +4Structure: 41 headings
- +3Step-by-step instructions: 170 items
- +3Output format is stated explicitly
- +4Has examples (19 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.