BB voice-match-humanizer
Use this skill when a user is actively managing voice profiles or asking for a rewrite tied to a specific saved profile. Specific triggers: 'rewrite this in my [profile-name] voice,' 'sound like me using my [profile-name] profile,' 'build a voice profile from these samples,' 'analyze my writing samples in [path/folder],' 'score this text for AI patterns,' 'compare my [profile A] and [profile B] profiles,' 'diff these two profiles,' 'make a [platform] variant of my [profile-name],' 'has my voice drifted from my [profile-name] profile,' 'check this against my saved profile,' 'list my voice profiles,' or 'update my [profile-name] profile with new samples.' Do NOT trigger on: requests to bypass AI-detection tools for academic dishonesty, generic editing/proofreading/simplifying/brainstorming, writing from scratch with no profile context, or casual mentions of voice or tone outside an active profile workflow. The skill builds and applies voice profiles that capture a person's writing fingerprint (sentence patterns, vocabulary, tone, quirks); supports profile comparison, per-platform sub-variants, drift detection, and AI-pattern scoring; stores profiles as local markdown files.
As a process B 69/100 · Nearly there — weak spots: inputs and preconditions, progress reporting
How to improve
- Shorten the description to 1024 characters.
- 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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1190 chars, limit 1024
Process rating: all ten parameters 69/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4877 tokens
- 100Steps. 90 steps
- 100Failures and branches. 14 branches, has a failure section
- 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 11 top-level sections: this looks like several domains in one skill
- medium 4 test cases, all positive: not one "should refuse" or "should ask first"
- low No test case covers injection arriving through data
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1190: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 34 headings
- +3Step-by-step instructions: 90 items
- +3Output format is stated explicitly
- +4Has examples (13 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 59.