AC brand-voice-architect
A high-precision engine for deconstructing, documenting, and synthesizing brand-specific linguistic patterns and tonal architectures. Use this skill whenever a user wants to: create or generate a brand voice guide, analyze writing samples or a corpus for tone/style, review content for linguistic consistency, build a voice system prompt, define brand pillars, identify prohibited words or preferred vocabulary, create "this not that" style guides, adapt tone across platforms (LinkedIn vs. technical docs vs. social), or reverse-engineer competitor or reference brand voices. Trigger even for loosely related requests like "make our writing more consistent", "what tone should we use?", or "analyze how we write."
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- 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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 17 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 934 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +3Description length 714: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 17 items
- +4Reference files are cited in the instructions (1 of 1)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.