AB vibbit-skills
Call Vibbit OpenAPI to complete five capabilities — AI image generation, parse Douyin/Xiaohongshu/Bilibili links, viral video breakdown, query available avatar list, initialize avatar voiceover video workflow. When users say "generate an image / AI image", "parse this Douyin/Xiaohongshu/Bilibili link", "break down this viral video / video breakdown", "show me my avatars / list avatars", or "use XX avatar for voiceover / initialize avatar video / avatar voiceover", this skill should be triggered proactively, even if the user doesn't explicitly mention "vibbit" or "openapi". As long as the task maps to one of these five capabilities and the user is working with the Vibbit/willing-agentcy system, prioritize this skill over writing HTTP requests manually.
As a process B 70/100 · Nearly there — weak spots: result and completion, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Exfiltration
net-redirectable-api-keyscripts/vibbit.js:257Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "display_description"
Process rating: all ten parameters 70/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 47 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 9 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3012 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 761: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 47 items
- +4Has examples (7 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.