BA Translate
Translates and localizes text, software strings, documents, subtitles, and marketing copy between any language pair. Use when translating anything, when fixing a translation that reads machine-made, or when localizing a product: ICU plurals and gender, placeholders that must survive, string catalogs (JSON, XLIFF, .po, .strings, .xcstrings, ARB, RESX, YAML), locale codes and fallback chains, RTL and bidi breakage, CJK typography, mojibake, text expansion that overflows the UI, subtitle timing and reading speed, hreflang and multilingual SEO, glossaries, translation memory and fuzzy matches, and post-editing machine output. Use when choosing register (tu/vous, tú/usted, du/Sie, keigo), between es-ES and es-419 or zh-Hans and zh-Hant, or when a certified, legal, or medical translation carries liability. Not for writing original copy natively in one language (spanish, french, german, japanese, chinese) or generating captions from audio (video-captions).
As a process A 82/100 · Runs to the end — weak spots: inputs and preconditions, running it twice, progress reporting
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 19. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
body-longSKILL.md body ≈ 6934 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 82/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 11 mutating operations with no state check
- 70Execution cost. Instruction body is 6934 tokens
- 100Tools and files. No external tools needed
- 100Steps. 42 steps
- 100Result and completion. Output format and completion criterion are stated
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 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
- +3Description length 963: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 12 headings
- +3Step-by-step instructions: 42 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.