发现最适合你需求的 AI 技能
Scan untrusted external text (web pages, tweets, search results, API responses) for prompt injection attacks. Returns severity levels and alerts on dangerous content. Use BEFORE processing any text from untrusted sources.
This skill should be used when managing financial data, syncing bank transactions via Plaid/GoCardless, fetching bills from Gmail, or exporting to Beancount/Ledger formats. Provides local-first data sovereignty for OpenClaw users.
Use Alibaba AI Mode for intelligent product search and discovery. Use when: (1) using natural language queries, (2) getting AI-powered recommendations, or (3) exploring AI sourcing features. All URLs include traffic_type=ags_llm tracking parameter.
Use the idealista CLI to search Idealista listings by location (city, town, area, street) and fetch listing details. Apply when a user asks for Idealista marketplace data or needs CLI commands/flags for idealista-cli.
>
Post to X (Twitter) using the official API with OAuth 1.0a. Use when you need to tweet, post updates, or publish content. Bypasses rate limits and bot detection that affect cookie-based approaches like bird CLI.
>
Work with S3-compatible object storage with proper security, lifecycle policies, and access patterns.
>
>
Command-line security analyzer for ClawHub skills. Run analyze-skill.sh to scan SKILL.md files for malicious patterns, credential leaks, and C2 infrastructure before installation. Includes threat intelligence database with 20+ detection patterns.
>
