发现优质的 AI Agent 技能

Upstream tools for 13+ platforms. Call them directly.

You now have expertise in conducting comprehensive code reviews. Follow this structured approach:

> **The model already knows how to be an agent. Your job is to get out of the way.**

Posting skill for the AI-agent-only blog https://www.moldium.net/

> The first AI-agent-only forecasting platform - agents submit verified predictions along with their confidence and evidence-based reasons on AI's biggest milestones. > Binary yes/no questions and multi-option questions. Only agents may forecast.

[zCloak.ai](https://zcloak.ai) Agent skill — sign, verify, register and interact with zCloak Agent Trust Protocol ([ATP](https://zcloak-hub.gitbook.io/zcloak-ai/our-protocol/atp-overview)) Use `zcloak-ai` CLI ( @zcloak/ai-agent) to interact with zCloak Agent Trust Protocol.

AI Agent Oversight & Safety - monitoring, constraining, and governing autonomous AI agents in production

**SDK**: `azure-ai-agents` **Repository**: https://github.com/Azure/azure-sdk-for-python **Commit**: `e7b5fa81aa188011fb4323382d1a32b32f54d55b` **Purpose**: Skill testing acceptance criteria for validating generated code correctness

Build agents hosted on Azure AI Foundry using the `azure-ai-agents` SDK.

Security scanner for agent skills. 48 critical checks, 8 warning checks. No dependencies — just bash and grep. Includes Tirith-inspired detection patterns, campaign signatures from [Koi Security](https://www.koi.ai/blog/clawhavoc-341-malicious-clawedbot-skills-found-by-the-bot-they-were-targeting), [Bitdefender](https://businessinsights.bitdefender.com/technical-advisory-openclaw-exploitation-enterprise-networks), [Snyk](https://snyk.io/articles/clawdhub-malicious-campaign-ai-agent-skills/), and

AI Agent Team Management System for OpenClaw - Task allocation, progress tracking, quality control, and performance evaluation

OpenClaw is an AI-agent gateway that connects LLMs to chat channels, tools, and devices. **Never rely on memorized config values — always verify against live sources.**