AB run402
Provision Postgres databases, deploy static sites, generate images, and build full-stack webapps on Run402 using x402 micropayments. Use when the user asks to build a webapp, deploy a site, create a database, generate images, or mentions Run402.
As a process B 68/100 · Nearly there — weak spots: result and completion, inputs and preconditions, 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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Exfiltration
net-credential-useSKILL.md:426Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)Functions access secrets via `process.env.SECRET_NAME`. Deployed to Lambda. Accessible at `https://api.…com/functions/v1/<name>`.
vendor-hostquoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:561High-entropy token-like string (may be an id, hash or a credential) (placeholder value)- `X-Ru…ng: <micros>` (allowance-paid only)
placeholder
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 68/100
- 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
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4773 tokens
- 100Tools and files. No external tools needed
- 100Steps. 25 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- low 24 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (4 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
- +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 245: enough signal without eating the budget
- +4Structure: 45 headings
- +3Step-by-step instructions: 25 items
- +4Has examples (33 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.