AC vibe-code
Discipline skill for vibe-driven development — turns mood, feel, and outcome-shaped requests into shippable code without the usual drift, hallucinated APIs, and silent scope creep. Use when a collaborator describes software by feel rather than spec ("make it feel snappy", "vibe-code a dashboard", "like Linear but cozy", "build me something that does X, you figure out the rest"), when a prototype is being built from a vibe instead of a ticket, or when the request mixes aesthetic intent with vague behavior. Enforces a four-line Vibe Lock before any code is generated, names the specific failure modes of vibe coding, and gives concrete patterns for translating a vibe into a runnable slice. Keywords: vibe coding, vibe code, build me, make it feel, aesthetic, mood, taste, prototype, scaffold from idea, natural-language to code, intent-driven, ambient spec, Karpathy.
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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: 2. 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 59/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 2 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 31 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2295 tokens
- 100Progress reporting. Reports progress
- 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)
- +3Description length 872: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Structure: 13 headings
- +3Step-by-step instructions: 31 items
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.