发现优质的 AI Agent 技能
聚合 Claude Skills、LangChain、AutoGPT 等优质资源，助力开发者快速构建智能应用
MFA Word (Security Gatekeeper)
1. **Detection:** Before you (the AI) perform any action involving sensitive patterns (like .env, .ssh, passwords, or deletions), you MUST call `check_gate_status`. 2. **Standard Mode:** If `check_gate_status` returns "OPEN", you may proceed. This session is valid for 15 minutes. 3. **Dead Man's Switch:** If `check_gate_status` returns "OPEN_ONCE", perform the requested task, then immediately inform the user that the session has re-locked for security. 4. **Challenge:** If `check_gate_status` re
Memory Guard - Agent Memory Integrity & Security
Protect your agent's memory files from injection, tampering, and drift.
PostWall Email Skill
PostWall is a security layer between AI agents and email. Use this skill to: - Read emails that have been approved by the human - Send emails via draft submission (requires human approval before sending)
mind-security
Deepfake detection powered by [Bittensor Subnet 34](https://bitmind.ai). The detection model evolves continuously through adversarial competition — generation miners push realism while detection miners improve accuracy.
Domain: Security Risks
> Deep reference for Domain 3 in SKILL.md. > Load this file when running L3 analysis or when SKILL.md thresholds need clarification. > > **Input:** `DATA.security`, `DATA.gateway_err_log`, `DATA.identity`, `DATA.config` > **Output:** status (✅/⚠️/❌) + score (0–100) + risk classification + findings + fix hints
Domain: Security Risks
> Deep reference for Domain 3 in SKILL.md. > Load this file when running L3 analysis or when SKILL.md thresholds need clarification. > > **Input:** `DATA.security`, `DATA.gateway_err_log`, `DATA.identity`, `DATA.config` > **Output:** status (✅/⚠️/❌) + score (0–100) + risk classification + findings + fix hints
Security Best Practices for Model Routing
Comprehensive security guidance for multi-model routing systems.