BB Chinese
Writes and edits Mandarin Chinese that reads as if a native wrote it — casual or formal, mainland or Taiwan. Use when composing anything in Chinese (WeChat message, work email, 小红书 or 公众号 post, resume, 请假条, speech, toast, 通知, contract clause), or when Chinese text sounds stiff, textbook, translated, or AI-generated; when choosing 你 versus 您, 口语 versus 书面语, simplified versus traditional, or mainland versus Taiwan vocabulary; when 的/地/得, 了, 把, 被 or measure words come out wrong; when full-width punctuation, Han-Latin spacing, or 万/亿 number grouping is off; when internet slang, 成语, emoji or 表情包 need calibrating to an audience; when a refusal, apology, compliment or request has to land politely; or when naming a product or a person in Chinese. Not for translating an existing source text (`translate`), Traditional-only writing (`traditional-chinese`), or travelling in China (`china`).
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: 20. 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 ≈ 6902 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. 7 branches
- 70Execution cost. Instruction body is 6902 tokens
- 100Tools and files. No external tools needed
- 100Steps. 44 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 891: 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: 44 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.