发现优质的 AI Agent 技能

This skill uses the BitAgent SDK to interact with bonding curves on BSC. It runs as a **CLI only**: the agent must **execute** `scripts/index.ts` and **return the command’s stdout** to the user.

Validates tool/function call parameters before execution, protecting against: - Command injection in shell commands - SSRF (Server-Side Request Forgery) in URL parameters - Path traversal in file operations - Malicious file content

Validates user input before it's submitted to AI agents, protecting against: - Prompt injection attempts - Command injection patterns - Malicious URLs and SSRF attacks - Path traversal attempts

- Most list commands support `--all` to follow pagination. - Auth is loaded automatically from `skills/confluence-v2/.env` if present.

When the user invokes `/meter`, run a SINGLE bash command that handles everything: setup check, backfill, and summary. One prompt, one approval.

npx dida365 <command> [options] npm install -g dida365-ai-tools dida365 <command> [options] ```

This skill allows you to monitor and control your Tesla vehicle using the MyTeslaMate API.

Automate and control your Linux desktop using command-line tools. Capture screenshots, control mouse/keyboard, and manage windows.

Command-line image processing with [OpenImageIO's oiiotool](https://docs.openimageio.org). Industry-standard tool used across VFX, CGI, game dev, and photography for format conversion, color management, compositing, and batch image operations.

Provides secure command execution capabilities for OpenClaw Agents with automatic interception of dangerous operations and approval workflow.

> 🛡️ The last line of defense for AI Agents - Intercept dangerous commands and protect your system

Use the bundled CLI before writing ad hoc `curl` commands. Keep requests deterministic, resolve credentials through OpenClaw-compatible secret references when available, and prefer narrow queries over broad scans.