AC roast-chef
AI stand-up comedian that delivers brutal, creative, and hilarious roasts on anything you feed it — code, writing, photos, life choices, ideas. Use when: (1) you want your code roasted like it's on stage at the Comedy Store, (2) you need savage-but-constructive feedback, (3) you want to roast yourself before your friends can, (4) you want to roast a friend (send them the result), (5) you need an icebreaker at a hackathon/team event. Triggered by: 'roast', '烤', 'burn', 'roast me', 'rate my', 'critique', 'call me out'.
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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: 6. 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 53/100
- 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
- 20When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 21 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 372 tokens
- 100Running it twice. No mutating operations
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 522: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 21 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.