Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →asgeirtj/claude-api-in-prototypes
Call Claude from your HTML artifacts via window.claude.complete
Passed 19 of 21 test cases with the skill, and 9 of 21 without it.
and 12 more in the full report
11 fixed9 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
In an interactive HTML artifact calling Claude via the built-in browser helper, what is the default maximum output token cap if no `max_tokens` parameter is specified?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies 1024 as the default maximum output token limit | Missed | Passed |
The instructions your model reads when the skill loads.
Your HTML artifacts can call Claude via a built-in helper. No SDK or API key needed.
<script>
(async () => {
const text = await window.claude.complete("Summarize this: ...");
// or with a messages array:
const text2 = await window.claude.complete({
messages: [{ role: 'user', content: '...' }],
});
})();
</script>
Calls default to claude-haiku-4-5 with a 1024-token output cap. The body may also set model (haiku/sonnet families only), max_tokens (up to 32000), system, tool_choice, and client tools — standard Messages API shapes, except each tool also carries run: async (input) => string and the helper executes tool calls in-page and loops (max 8 model calls), resolving with the final text. Handler throws become is_error tool_results. Server tools (web search etc.) are rejected; no streaming; rate-limited 15 calls/minute per user, loop iterations included. Shared artifacts run under the viewer's quota.
test cases passed, vs 9 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.