技能检索
context-engineering
This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.
crabnet
Interact with the CrabNet cross-agent collaboration registry. Use when discovering other agents' capabilities, registering your own capabilities, posting tasks for other agents, claiming/delivering work, or searching for agents who can help with specific skills. Enables agent-to-agent collaboration and task exchange.
beestat
Query ecobee thermostat data via Beestat API including temperature, humidity, air quality (CO2, VOC), sensors, and HVAC runtime. Use when user asks about home temperature, thermostat status, air quality, or heating/cooling usage.
nostr-weather
Specialized skill for NIP-Weather IoT data, powered by nostr-nak.
apple-health-skill
Talk to your Apple Health data — ask questions about your workouts, heart rate, activity rings, and fitness trends using AI.
imessage-signal-analyzer
Analyze iMessage (macOS) and Signal conversation history to reveal relationship dynamics — message volume, initiation patterns, silence gaps, tone samples, and recent exchanges. Use when asked to analyze messages, read message history, check conversation patterns, or evaluate a relationship based on text history. Works on macOS (iMessage + Signal), Linux/Windows (Signal only).
mlx-stt
Speech-To-Text with MLX (Apple Silicon) and opensource models (default GLM-ASR-Nano-2512) locally.
hergunmac
Access AI-powered football match predictions from hergunmac.com. Use when the user asks about football/soccer match predictions, betting tips, match analysis, team statistics, head-to-head data, or upcoming match insights. Covers worldwide leagues with confidence scores, AI reasoning, and historical performance tracking.
pattern-finder
Discover what two sources agree on — find the signal in the noise.