signalk-apis

signalk-apis is a skill for Claude Code from sailingnaturali/claude-skills. It costs 140 tokens per session (2,262 once invoked), scanned A, original, MIT.

A guide for using Signal K, a server and API system for live boat data. It explains how to read, stream, change, or provide data through its general data API and its purpose-built domain APIs.

In plain words
What is it for?
Building web apps, external tools, or server plugins that consume or provide navigation, weather, autopilot, history, and other marine data.
Why use it?
It prevents the common mistake of treating Signal K v2 as a replacement for v1. The guide explains that they serve different jobs and may be used together.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the signalk-apis plugin — 1 skill shipped together

Good fit Building web apps, external tools, or server plugins that consume or provide navigation, weather, autopilot, history, and other marine data.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sailingnaturali/claude-skills/signalk-apis
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add sailingnaturali/claude-skills --skill signalk-apis
Clone the repo
git clone --depth 1 https://github.com/sailingnaturali/claude-skills

Made for: Claude Code.

Or install signalk-apis, the plugin that ships this one along with the rest of its 1 skill.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for signalk-apis

README.md
[![agentmods](https://agentmods.dev/badge/skills/sailingnaturali/claude-skills/signalk-apis/github.svg)](https://agentmods.dev/skills/sailingnaturali/claude-skills/signalk-apis)
Your own site
<a href="https://agentmods.dev/skills/sailingnaturali/claude-skills/signalk-apis"><img src="https://agentmods.dev/badge/skills/sailingnaturali/claude-skills/signalk-apis/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for signalk-apis

Your own site · 80×15
<a href="https://agentmods.dev/skills/sailingnaturali/claude-skills/signalk-apis"><img src="https://agentmods.dev/badge/skills/sailingnaturali/claude-skills/signalk-apis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 140 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,262 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00140 $0.02262
Opus 5.5 $0.00056 $0.00905
Sonnet 5.5 $0.00028 $0.00452
Haiku 4.5 $0.00014 $0.00226

Measured 1mo ago against content hash 37c17d3ccb1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

signalk-apis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

signalk-apis/skills/signalk-apis/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Signal K APIs: v1 and v2 have different jobs

The most common misconception about the Signal K server APIs is that v2 is the successor of v1 and v1 is on its way out. Wrong — they serve different purposes and coexist by design:

  • v1 is the data-model API. One universal signal tree (navigation.*, environment.*, electrical.*, …) that every source feeds into, exposed three ways: REST snapshot, streaming WebSocket deltas, and PUT actuation. This is the way to read and stream live boat data, and nothing in v2 replaces it.
  • v2 is a set of domain APIs — course, resources, notifications, history, autopilot, weather (radar in development) — each a purpose-built REST contract (OpenAPI definitions under Documentation → OpenAPI in the admin UI) for operations the flat data model can't express well ("activate this route", "acknowledge this alarm", "give me yesterday's SOG"). The server owns the routes and keeps the data model consistent. Course and notifications are built into the server; the APIs that front hardware or storage — resources, autopilot, weather, history, radar — are implemented by plugins registering as providers.

New code typically uses both: stream positions over v1 while setting the course over v2.

Consumer side (webapps, external apps)

  • Discover, don't hardcode. GET /signalk returns the endpoints — and it advertises v1 only (signalk-http, signalk-ws, signalk-tcp). The v2 APIs are not in the discovery document; they live at the well-known /signalk/v2/api/... paths.
  • Read state (v1): GET /signalk/v1/api/vessels/self/<path with dots as slashes> — a leaf returns { value, $source, timestamp, meta } (meta carries units/description; multiple sources for one path appear under values keyed by $source).
  • Stream (v1): ws://…/signalk/v1/stream?subscribe=self|all|none, then send { "context": "vessels.self", "subscribe": [{ "path": "navigation.*", "period": 1000 }] }. Gotcha (as of 2.30.0): top-level leaf paths like name and mmsi are not deliverable via subscriptions — poll them over REST instead (signalk-server#2829).
  • Operate the boat (v2): e.g. course (GET/PUT /signalk/v2/api/vessels/self/navigation/course/...), resources CRUD (/signalk/v2/api/resources/<type>), notifications (GET/POST /signalk/v2/api/notifications, plus :id/acknowledge, :id/silence, acknowledgeAll, silenceAll, mob — this full surface ships in 2.30.0 even where older docs still mark it as pending). Writes return an envelope like { "state": "COMPLETED", "statusCode": 201, "id": "<uuid>" }.
  • Generic actuation (v1 PUT): PUT /signalk/v1/api/vessels/self/<path> with { "value": … }. The response is the v1 request envelope — { "state", "statusCode", "message", "href": "/signalk/v1/requests/<id>" }; poll href while state is PENDING. A path is only PUT-able if some plugin registered a handler for it (otherwise HTTP 405, "PUT not supported for <path>").
  • History (v2): GET /signalk/v2/api/history/values?paths=<p1[:aggregate]>,… with from/to (ISO 8601 timestamps), duration (seconds, or an ISO 8601 duration like PT1H), and optional resolution. Answered by a history provider plugin (signalk-parquet, signalk-to-influxdb2, signalk-questdb, …); with none installed you get 501 {"error":"No history api provider configured"}.
  • A v2 404 can mean "no provider", not "no API". Provider-backed routes mount per provider: with no resources provider, GET /signalk/v2/api/resources/waypoints is a plain 404; enable one and the same URL returns 200 {}. Autopilot routes behave the same. Only some APIs (history) exist unmounted-but-answering with a clean 501. Don't interpret 404 as "server too old".
  • Conventions: _default targets the default device (…/autopilots/_default/engage), _providers / ?provider=<id> targets a specific provider, _config addresses API configuration. Multi-device and multi-provider APIs all follow these.
  • Auth: with security disabled, the data and configuration routes above are open; with security enabled and allow_readonly on (the common setup), reads stay anonymous. Writes and protected reads need a token: POST /signalk/v1/auth/login with { "username", "password" }, then send it as a Bearer header (REST) or let the cookie ride (browser + WebSocket). Everything under /skServer/* and /plugins/* is admin — that's server-configuration surface, not data.
  • "Security disabled" is not "everything open" — applicationData inverts it. /signalk/v1/applicationData/{global,user}/… is per-user/per-app storage, so it is disabled when security is off rather than unguarded: the interface sees securityStrategy.isDummy() and returns early, registering only POST handlers that answer 405 security is not enabled. The GET handlers are never registered at all on that path, so reads fall through to a plain 404 rather than a 405. Enable security and both appear, global behind admin-write and user behind write. Verified in signalk-server 2.30.0+ (src/interfaces/applicationData.js).

Read the full file on GitHub · 118 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 118 lines · 140 tokens per session scan A 37c17d3ccb1f

Subscribe to this mod's changes

signalk-apis is a skill published in the GitHub repository sailingnaturali/claude-skills (3 stars, last pushed 14d ago), licensed MIT. It adds 140 tokens to every session and 2,262 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-07.

Related

Other skills, from other repositories

ruview-cli-api

Use the RuView wifi-densepose CLI binary (incl. MAT scan/status/zones/survivors/alerts/export subcommands), the REST API (wifi-densepose-api, Axum), and the browser/WASM build (wifi-densepose-wasm, wifi-densepose-wasm-edge). Use when integrating RuView into another program, scripting it from the shell, exposing it…

ruvnet/RuView · 104 tokens

amazon-alexa

Integracao completa com Amazon Alexa para criar skills de voz inteligentes, transformar Alexa em assistente com Claude como cerebro (projeto Auri) e integrar com AWS ecosystem (Lambda, DynamoDB, Polly, Transcribe, Lex, Smart Home).

sickn33/agentic-awesome-skills · 53 tokens

doca-socket-relay

Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…

NVIDIA/skills · 236 tokens

jetson-customize-pcie

Per-controller PCIe enable / disable / lanes / link-speed for a Jetson Thor or Orin custom carrier via ODMDATA + kernel-DT overlay. Do NOT use for UPHY lane allocation or endpoint-mode bring-up.

NVIDIA/skills · 53 tokens

deepep-to-cam-converter

A code migration skill for replacing DeepEP communication operations with CAM operations when moving mixture-of-experts code from CUDA/NCCL to Ascend NPUs.

XiaoLuoLYG/GOD · 63 tokens

telnyx-iot-curl

Manage IoT SIM cards, eSIMs, data plans, and wireless connectivity. Use when building IoT/M2M solutions. This skill provides REST API (curl) examples.

team-telnyx/ai · 45 tokens