alexa

Solid

Expose HybridClaw as a custom Alexa skill and prepare guarded Alexa smart-home/device control payloads without exposing Amazon credentials.

AI & Automation 132 stars 12 forks Updated today MIT

Install

View on GitHub

Quality Score: 85/100

Stars 20%
71
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Alexa Use this skill for Amazon Alexa workflows in two narrow modes: 1. Expose HybridClaw as a custom Alexa skill through the Alexa Skills Kit (ASK). 2. Prepare guarded Alexa-as-device reads and write plans for the official Smart Home Skill API and the opt-in community Alexa Remote / `alexapy` surface. Do not use this skill for arbitrary Amazon API calls, shopping account access, or browser automation. Keep all credentials behind SecretRef and use the helper to build bounded payloads instead of hand-writing URLs, headers, cookies, or request bodies. ## Safety Rules 1. Validate every inbound ASK request before parsing slots or running an agent bridge. Reject invalid `Signature`, invalid `SignatureCertChainUrl`, signing certificates that do not cover `echo-api.amazon.com`, or timestamp drift of 150 seconds or more. 2. Never persist or echo Login with Amazon access tokens. The request token maps to a HybridClaw operator session outside the prompt through the F13 SecretRef rail. 3. Model output sent back to Alexa must be TTS-safe. Use `build-response` so markdown, code blocks, and very long URLs are stripped before SSML is built. 4. Path-B reads are green but privacy-sensitive because devices, list contents, routines, and last-command history can reveal household behavior. 5. Path-B writes are amber/red. Announcements, list mutations, device control, and routine triggers require exact F8/F14 approval that names the target room or device and th...

Details

Author
HybridAIOne
Repository
HybridAIOne/hybridclaw
Created
6 months ago
Last Updated
today
Language
TypeScript
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

openclaw

OpenClaw - Multi-channel AI gateway for messaging platforms with browser Control UI. Use when the project needs this capability or the user / team manifest asks for it. Use for specialized `openclaw` work when listed in TEAM.yaml or explicitly requested.

2 Updated today
rogue-dev-studio
AI & Automation Solid

hybridclaw-help

HybridClaw help. Primary skill for product questions about setup, configuration, commands, runtime behavior, and release notes.

132 Updated today
HybridAIOne
AI & Automation Listed

openclaw-deployment

This skill should be used when deploying or debugging a self-hosted OpenClaw (formerly Clawdbot/Moltbot) agent gateway — a Node.js personal-assistant service bridging Telegram/WhatsApp/Discord to an LLM with tool/skill access. Covers install, secure baseline config (loopback bind, token auth, exec approval gating), the two non-obvious config traps that silently break things (model selection vs. API key, exec security vs. ask), Telegram channel lockdown, configuring the web_search tool/Brave provider, voice-note transcription (tools.media.audio/Groq), memory indexing and its embedding-provider auth (openclaw memory index/status), evaluating ClawHub skills/plugins by real usage data, and building trustworthy custom skills instead of pulling from the unvetted ClawHub marketplace. Trigger phrases include "openclaw config", "openclaw gateway", "tools.exec.security", "openclaw model not found", "ProviderAuthError No API key found for provider openai", "exec denied security=deny", "openclaw dashboard", "openclaw pai

1 Updated yesterday
jackson2w