BA Writing
Drafts, edits, and rewrites prose in the user's own voice — emails, posts, essays, memos, proposals, social copy. Use when asked to write, draft, edit, tighten, shorten, rewrite, or proofread something; when a draft reads flat, wordy, robotic, or "not like me"; when a piece will not start, a sentence will not come out right, or the ending trails off; when an email has to deliver bad news, say no, chase a reply, or make an ask that lands; when a post needs a hook, a headline, or a cut to fit a limit; when order, transitions, or paragraph structure are the real problem; when writing in a second language, or matching a house style, spelling variant, or word count. Learns and reuses their voice across sessions. Not for grammar-only fixes (`grammar`), sales copy (`copywriting`), book manuscripts (`book-writing`), journal papers (`academic-writing`), narrative craft (`storytelling`), versioned draft-and-audit workflows (`write`), or inbox triage and follow-ups (`email-management`).
As a process A 81/100 · Runs to the end — weak spots: inputs and preconditions, running it twice
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: 16. 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 ≈ 6161 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 81/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 23 mutating operations with no state check
- 70Failures and branches. 5 branches
- 70Execution cost. Instruction body is 6161 tokens
- 100Tools and files. No external tools needed
- 100Steps. 44 steps
- 100Result and completion. Output format and completion criterion are stated
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- 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
- high The skill tells the model to perform an irreversible action with no human approval
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 990: 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.