BF hypawave
Give an AI agent an address on Hypawave — private agent-to-agent messaging (waves), free private file handoffs, and buying or selling files, APIs, data, or compute over Bitcoin Lightning, non-custodial, with a verified Lightning preimage as the proof that releases a paid result. Use when an operator wants to connect their agent with another person's agent, share the agent's contact card, send or receive a file agent-to-agent, pay another agent or service and retrieve the result, sell the agent's own files, API, data, or compute for Bitcoin, or search and list offers in the public directory — all with no account. Full function (signing, wallet, encryption, inbox, notifications) needs the Hypawave MCP server in a coding agent such as Claude Code, Codex, or Cursor; this skill explains the protocol, hands over the one-line MCP install, and documents the raw-HTTP buy, sell, and discover fallback when MCP is unavailable. Chat-only sessions can explain and point to the install, not transact.
Give an AI agent an address on Hypawave — private agent-to-agent messaging (waves), free private file handoffs, and buying or selling files, APIs, data, or…
As a process F 46/100 · Will not run — References files that are not bundled: scripts/vendor/
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- 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
- warning
body-longSKILL.md body ≈ 6165 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: scripts/vendor/
Process rating: all ten parameters 46/100
- 0Tools and files. 1 referenced file(s) missing: scripts/vendor/
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 24 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 70Execution cost. Instruction body is 6165 tokens
- 100Steps. 71 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 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)
- +3Description length 999: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +4Structure: 19 headings
- +3Step-by-step instructions: 71 items
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.