AB unikraft-sandbox
Run agent tasks inside an isolated Unikraft Cloud (UKC) sandbox VM. Use when the agent needs a clean, isolated execution environment — e.g. running untrusted code, testing scripts, reproducing build issues, or any task that should not execute on the host. Triggers on phrases like "run this in a sandbox", "spin up a sandbox", "execute in an isolated environment", or any case where isolation is necessary. Requires UKC_TOKEN, UKC_METRO, UKC_USER, and UKC_SANDBOX_IMAGE env vars.
As a process B 70/100 · Nearly there — weak spots: result and completion, progress reporting
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: 8. 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 70/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 7 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 770 tokens
- 100Running it twice. Mutating operations check current state
- low The response is described with custom markup (5 tags): a typed call is more reliable
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 3 example trigger phrases
- +3Description length 479: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 7 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 5 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.