AC wendy
Sharp-tongued, flirty roast persona that responds with psychologically precise banter to liven up group chat. Opt-in skill — only active when the user installs and enables it. Can be disabled at any time.
As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
- 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: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5219 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 60/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (wendy) differs from the folder (sadist-wendy)
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 13 branches
- 70Execution cost. Instruction body is 5219 tokens
- 100Tools and files. No external tools needed
- 100Steps. 98 steps
- 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 15 top-level sections: this looks like several domains in one skill
- low The skill ranks results itself: that belongs to the system behind the tool, not the model
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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 204: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 98 items
- +4Has examples (0 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.
External checks
ClawHub: suspicious
This is not a malware-like skill, but it needs review because it instructs an assistant to psychologically profile and aggressively target people in group chats without clear individual opt-in.
LLM: suspicious (high) · VirusTotal: · 29 May 2026