BC English
Writes and corrects English that reads like a native wrote it — any variety, any register. Use when text sounds stiff, robotic, translated, or AI-generated; when a sentence is grammatically fine but "sounds wrong"; when choosing between US, UK, Australian, Canadian, Irish or Indian spelling, vocabulary and punctuation, or when a document mixes them; when a first language keeps leaking through — articles, prepositions, tense, false friends, word order; when formality must be calibrated for an email, a client, or a meeting; when idioms, phrasal verbs, slang or collocations land wrong or sound dated; when commas, hyphens, capitalization, quotes, dates or numbers need a house rule; when confusable words, jargon or hedging blur the meaning; and for pronunciation, small talk, and improving on purpose. Not for grammar-only fixes (`grammar`), translation (`translate`), IELTS or TOEFL prep (`ielts`, `toefl`), or drafting in your own voice (`writing`).
As a process C 61/100 · Has gaps — 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: 15. 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 ≈ 5649 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 61/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 13 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (read) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 5 branches
- 70Execution cost. Instruction body is 5649 tokens
- 100Steps. 45 steps
- 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 11 top-level sections: this looks like several domains in one skill
- high The skill tells the model to perform an irreversible action with no human approval
- low The response is described with custom markup (3 tags): a typed call is more reliable
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 956: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 11 headings
- +3Step-by-step instructions: 45 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.