BB Japanese
Writes and edits Japanese that reads as if a native wrote it — casual, 敬体, or full keigo. Use when composing anything in Japanese (LINE or Slack message, business email, 履歴書, 退職願, 議事録, note or X post, speech, 年賀状, contract clause, manga or game dialogue), or when Japanese text sounds stiff, textbook, translated or AI-generated; when 尊敬語 and 謙譲語, 二重敬語, させていただく, 了解 versus 承知, or さん versus 様 come out wrong; when は/が, particles, transitivity, mixed 敬体 and 常体, kanji-versus-kana balance, 送り仮名 or 全角 punctuation are off; when counters, 万/億 grouping, 令和 dates, addresses or a name's reading are needed; when slang, 絵文字 or dialect have to be calibrated to a reader; or when a refusal, apology or request must land. Not for translating an existing source text (`translate`), other languages (`chinese`, `korean`), or travelling in Japan (`japan`).
As a process B 77/100 · Nearly there — weak spots: inputs and preconditions, 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: 22. 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 ≈ 7961 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 77/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 6 branches
- 70Execution cost. Instruction body is 7961 tokens
- 100Tools and files. No external tools needed
- 100Steps. 46 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 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 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 842: 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: 46 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.