AF ai-translator-pro
Professional multilingual translator with deep domain expertise. Auto-detects language pairs and specialized domains (tech, legal, medical, business, academic), enforces terminology consistency across entire documents, preserves all formatting (Markdown, code blocks, tables, frontmatter), and generates glossaries. Supports 5 translation modes: quick, document, bilingual alignment, batch, and localization. Zero dependencies — pure prompt-driven. Use when user needs translation, localization, or multilingual content conversion.
As a process F 41/100 · Will not run — References files that are not bundled: url, /api
How to improve
- The text references files that are not there: add them or drop the references.
- 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
- warning
missing-refreference to a missing file: url - warning
missing-refreference to a missing file: /api
Process rating: all ten parameters 41/100
- 0Tools and files. 2 referenced file(s) missing: url, /api
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (ai-translator-pro) differs from the folder (yqg-ai-translator-pro)
- 100Steps. 33 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Execution cost. Instruction body is 2445 tokens
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 531: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 33 items
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.