ares-skills

Use when a user wants to translate text to or from any Indian language — Hindi, Tamil, Telugu, Bengali, Marathi, Kannada, Malayalam, Gujarati, Punjabi, Urdu, Odia, Assamese, Sanskrit — or says "translate this message", "translate this to Hindi", "what does this say in Tamil", "convert to Marathi", or similar. Also handles global languages (Spanish, French, Arabic, Chinese, Japanese, Korean, etc.). Uses Gemini 2.5 Flash. Also use when asked to detect what language a piece of text is written in.

Phrase-triggered emergency stop system for AI agents. Instantly halts all agent automation when a trigger phrase is detected in session logs, or via manual flag. Use when setting up a safety kill switch, emergency stop, or pause-all-automation mechanism for autonomous agents. Survives restarts via LaunchAgent watchdog.

The CRICD framework for structuring sub-agent task prompts — Context, Relevance, Instruction, Constraints, Demonstration. Produces dramatically better output from any LLM sub-agent. Use when spawning sub-agents, writing task prompts, or structuring complex instructions for AI models.

Formal protocol for draft → critique → revise loops in AI agent workflows. Defines when to use critique loops (money, public publishing, strategy) and when to skip (simple edits, routine coding). Prevents both over-engineering simple tasks and under-reviewing critical ones.

Monitor OpenClaw Gateway health by tailing logs for error patterns — 429 rate limits, auth failures, delivery failures, timeouts. Alert when error rate crosses thresholds. Use when setting up production monitoring for an OpenClaw Gateway deployment, or when a user says "watch the gateway", "monitor gateway errors", "alert me on gateway failures".

A 5-tier dispatch framework for coding tasks in AI agent workflows. Routes tasks from SIMPLE (one-file typo fix) to FULL (multi-day feature build) with appropriate rigor at each level. Prevents over-engineering simple tasks and under-planning complex ones.

Use when a user sends an audio file and asks "what is this song?", "identify this track", "shazam this", or similar. Accepts any audio format (OGG, MP3, WAV, M4A). Returns title, artist, album, release date, and Spotify/Apple Music links via the AudD API.

Inject live system health into agent context at session open. Cron script checks integrations, disk, gateway status, active sessions — writes compact JSON. Agent reads it before answering any status question. Eliminates stale-recall failures where agents answer from memory instead of live state. Use when setting up always-current system awareness for an autonomous agent.

Deploy an AI chatbot in a Twitch channel that responds to a configurable trigger word (e.g. !bot), engages viewers with AI replies, and requires no Twitch API key — uses pure WebSocket IRC.

Monitor Twitch channels going live, auto-record streams with streamlink, optionally upload recordings to Google Drive, and send WhatsApp notifications when streamers go online or finish.

Use when a user asks for a cost report, model usage summary, token spend breakdown, API costs, or says "how much did I spend this week?", "show me my API costs", "what's my model spend?", "weekly cost summary", or "usage report". Parses OpenClaw JSONL session logs and aggregates per-model token usage and dollar cost for the last 7 days.

Auto-generate a reality-first weekly log from daily memory logs, git history, and agent state. Uses Claude to synthesize what actually happened — not a strategic filter, not a curated narrative. Supports backfill by week number. Use when a user says "weekly recap", "what happened this week", "weekly capture", or "reality check".

Use when a user sends a voice note and wants it transcribed, or says "transcribe this voice note", "what did I say?", "convert voice to text", or "transcribe this audio". Handles OGG, MP3, WAV, and other audio formats. Outputs transcription with content classification (Idea/Task, Draft, or Note). Uses mlx_whisper large-v3-turbo for Apple Silicon — fully local, no API cost.