Agent Skills Hub

familiar-add-tool

Scaffold and register new sensor, actuator, or service tools for familiar-ai, automating file creation and boilerplate integration in agent.py and config.py.

building-ai-agent-on-cloudflare

Build stateful AI agents on Cloudflare Workers using the Agents SDK. Features real-time WebSockets, persistent state management, scheduled background tasks, and native tool integration for production-ready deployments.

strategic-compact

Enhance workflow efficiency by performing manual context compaction at logical task boundaries instead of relying on unpredictable auto-compaction.

prompt-injection-test

A testing utility designed to simulate prompt injection attacks and validate security scanners for AI agent skills.

session-investigator

Analyze and debug fast-agent session histories, tool execution logs, and conversation timing to resolve performance bottlenecks, tool loops, and unexpected session terminations.

indirect-injection-detection

Detects indirect prompt injection and goal hijacking in AI agents by evaluating how they process external content like RAG, documents, and web data.

response-compliance

Run OpenResponses API compliance tests to validate schema adherence, streaming responses, and endpoint reliability for LobeHub integrations.

ring:testing-skills-with-subagents

A meta-skill for building robust AI agent skills using a TDD approach: define failure (RED), implement the skill (GREEN), and plug rationalization loopholes (REFACTOR).

voice-extractor

Extract and document authentic writing voice from samples. Create comprehensive voice guides for AI training, ghostwriting, and brand consistency.

openrouter-trending-models

Fetch and analyze current trending programming models from OpenRouter. Ideal for selecting models for reviews, optimizing AI costs, and staying updated on AI coding trends with real-time pricing and context window data.

creating-opencode-agents

Expert guidance and configuration standards for creating specialized OpenCode AI agents, including YAML frontmatter, tool permissions, and operational modes.

research-tool

Advanced web search and reasoning tool for OpenClaw agents. Features citation-heavy synthesis, multi-step reasoning, and live internet access via OpenRouter.