AC cloudflare-drop
Publish a static site (a folder of HTML/CSS/JS/images/fonts) to Cloudflare and get back a live, shareable URL in seconds. Use when you have a finished static page or site and need to hand someone a link they can open on any device — reports, mockups, one-off landing pages, AI-generated HTML, "give me a link I can share". Runs one packaged command (references/deploy.mjs) built on the Wrangler CLI, which is what Cloudflare's own agent guidance tells agents to use. Deploys permanently to your Cloudflare account when credentials are present, or as a 60-minute claimable preview when they are not — and says plainly which one you got. Bakes an expiry countdown into previews (matched to the real 60-minute limit; --ttl to shorten it), and fails open (deliver the file) rather than invent a link.
Publish a static site (a folder of HTML/CSS/JS/images/fonts) to Cloudflare and get back a live, shareable URL in seconds.
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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: 0. 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 53/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 41 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 21 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2287 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- high The skill tells the model to perform an irreversible action with no human approval
- 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
- +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
- +2Single-language instructions
- +3Description length 796: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 21 items
- +4Has examples (3 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.