.claude/skills/lightningproxRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Call AI models (Claude, GPT, Gemini, DeepSeek, Mistral and more) through LightningProx (lightningprox.com), paid per request in Bitcoin Lightning sats instead of provider API keys. Anthropic (/v1/messages) and OpenAI (/v1/chat/completions) formats, tool calling, streaming. Payment is L402 or an optional LightningProx spend token. Use it when the user wants a model answer billed through LightningProx and agrees to pay.
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
.claude/skills/lightningproxRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/lightningproxRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/lightningproxRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.
clawhub install @unixlamadev-spec/lightningproxclawhub inspect @unixlamadev-spec/lightningprox --version 4.1.0This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
sha256:3c69e0e59aadf1c84dd8209aa66b1fcbbde11599822f3cab535ed92bcb139301CHANGELOG.mdlightningprox.jsonskill-card.mdSKILL.md4.1.0: current models via /v1/models, tool calling on both endpoints, failed calls never charged, optional spend token (L402), sends-and-costs section