发现最适合你需求的 AI 技能
For token distribution on Solana 5000x cheaper than SPL (rewards, airdrops, depins, ...). @lightprotocol/compressed-token (TypeScript). Reference examples for custom claim support.
管理 OpenClaw 长会话防爆机制(80%自动归档、自动轮换新会话、低 token 交接)及定时任务安装。用户提到 compacting context、会话过长、自动总结归档、session 轮换、LaunchAgent 定时任务时使用。
Connect to the user's Android phone via the VAGUS MCP server. Read phone sensors (motion, location, environment), device state (battery, connectivity, screen, notifications, clipboard), and act through the phone (haptics, TTS, notifications, clipboard). Use when you need physical-world awareness or need to reach the user through their phone.
Create, join, and manage teams on OpenAnt. Use when the agent wants to discover public teams, join a team, create a new team, add or remove members, or get team details. Covers "find teams", "join a team", "create team", "team members", "manage my team".
Use when accessing Outlit customer intelligence through the `outlit` CLI or Outlit MCP tools, including customer lookups, timelines, facts, semantic search, revenue or churn analysis, SQL analytics, setup, or troubleshooting agent access to Outlit data.
Manage installed skills lifecycle: suggest by context, track installations, check updates, and cleanup unused.
|
面向外部 OpenClaw 的达人推广方案制定 Skill。基于 RAGTOP 三个工具接口(list_kb/list_doc/retrieval)执行四阶段工作流:规则提炼、案例总结、达人筛选、方案生成。
Indestructible agent memory — permanently stored, never lost. Save decisions, identity, and context as a memory chain on the Autonomys Network. Rebuild your full history from a single CID, even after total state loss.
Scrapling-only, deterministic web crawler with clean SRP architecture, presets, checkpointing, and JSONL/report outputs.
Set a one-shot reminder delivered via Telegram at a specific time or after a duration. Use when the user asks to be reminded of something, set an alarm, or schedule a future notification. Always use this skill instead of the cron tool directly — it handles chat ID resolution and delivery.
Assesses wind turbine gearbox health from multi-sensor and inspection data. Classifies damage severity (1-5), identifies root cause, and recommends shutdown or monitoring actions.