AB otterkit-tunnel
Expose a local port to the internet via OtterKit tunnel, or create a webhook endpoint to capture incoming HTTP requests. Give your OpenClaw gateway a public HTTPS URL for incoming webhooks (/hooks/wake, /hooks/agent), capture and replay webhook deliveries, and protect tunnels with HTTP Basic auth. Use when the user asks to "tunnel", "expose", "share my localhost", needs a public URL for a local service or for OpenClaw webhooks, needs a webhook endpoint to capture requests, or wants to re-test a webhook handler against a previously received payload.
Expose a local port to the internet via OtterKit tunnel, or create a webhook endpoint to capture incoming HTTP requests.
As a process B 65/100 · Nearly there — weak spots: result and completion
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
-
low Exfiltration
exfil-webhook-urlSKILL.md:147Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)--forward https://hooks.slack.com/services/T00/B00/xxxx \
placeholder
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 65/100
- 0Result and completion. Does not say what the result is
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, 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
- 85Steps. 15 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2804 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (3 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
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +3Description length 554: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 15 items
- +4Has examples (18 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.