发现优质的 AI Agent 技能

Email, SMS, database storage & multi-agent coordination for AI agents. Gives your agent a real mailbox, phone number, and persistent storage — 63 tools covering email, SMS, database management, and inter-agent task delegation. Includes outbound security guard, spam filtering, human-in-the-loop approval, and automatic follow-up scheduling.

Ultra-lightweight SQLite database management optimized for OpenClaw agents with minimal RAM (~2-5MB) and storage overhead.

This skill provides a **Codebase Knowledge Graph** to help you navigate complex projects without reading thousands of files. It uses a local SQLite database to store file relationships, dependency layers, and symbol definitions.

Use this skill to connect to databases, explore schemas, run queries, estimate costs, and generate SQL from natural language.

- **Consistency**: Aligned `task-heartbeat.sh` default database path with the main `task` CLI (`$PWD/.tasks.db`). This resolves the "Suspicious" mismatch flag on ClawHub and ensures heartbeats correctly target the local workspace.

- category: system-monitoring - reads: process-list, cpu-usage, memory-usage - writes: sqlite-database, excel-files - network: none - external-apis: none

Kannaka supports [Dolt](https://github.com/dolthub/dolt) as an optional storage backend, replacing the default binary snapshots with a fully version-controlled SQL database that can be pushed to and pulled from [DoltHub](https://www.dolthub.com) — Git for data.

Kannaka gives your agent a living memory — not a database. Memories fade, dream, resurface when contextually relevant, and can be versioned and shared via DoltHub.

Complete database of security vulnerabilities detected by skill-security-audit.

You are a relationship intelligence agent. You remember everyone the user meets, track promises they've made, notice when relationships are cooling, and surface the right context at the right time. You're a best friend with perfect memory — not a database interface.

You are a relationship intelligence agent. You remember everyone the user meets, track promises they've made, notice when relationships are cooling, and surface the right context at the right time. You're a best friend with perfect memory — not a database interface.

Analyzes code for performance bottlenecks and provides suggestions for optimization (e.g., algorithmic improvements, caching, database indexing).