Skills

#agent-safety
Decision-Grade Reasoning (DGR)@dgr-ai-labs
#decision-record#llm-reasoning

Audit-ready decision artifacts for LLM outputs - assumptions, risks,…

Security, Agents, Knowledge
Updated 1mo ago 3 4.9k
Prompt Shield Publish@stlas
#prompt-injection#firewall

Prompt Injection Firewall for AI agents. 113 detection patterns, 14 threat…

Security
Updated 6mo ago 0 2.1k
AI Agent OPSEC — Runtime Classified Data Enforcer@theshadowrose
#opsec#classified

Prevent your AI agent from leaking classified terms to external APIs,…

Security
Updated 6mo ago 0 1.6k
Semantic Shield@simplysemantics
#saas-component#trust

AI skill safety validation — real human experts vet skills, plugins, and MCP…

Security
Updated 6mo ago 1 1.1k
Anti-Infinite-Loop Guard@kofna3369
#loop-prevention#termination

Anti-Infinite-Loop Guard — Prevents agents from getting stuck in repetitive…

Other
Updated 6mo ago 1 990
Edvisage Trust Checker@edvisage
#prompt-injection#trust

A protocol-layer trust verification skill for AI agents. Before you read,…

Security
Updated 6mo ago 1 913
merlin-security-sentinel@thepoorsatitagain
#prompt-injection#credentials

Use this skill when the user asks about securing their OpenClaw installation,…

Security, Agents
Updated 6mo ago 0 964
Nous Safety@dario-github
#agent-safety#datalog

Ontology-driven Agent safety layer. Install it and your agent gets runtime…

Knowledge
Updated 6mo ago 0 799
Optimize Prompt@margaretzybgl
#prompt-engineering#prompt-optimization

优化、压缩与审计 AI Prompt · Optimize prompts

Development, Agents, Knowledge
Updated 3mo ago 0 1.3k
MCP Precheck@policylayer
#mcp#mcp-security

Check MCP servers against the PolicyLayer registry before connecting to them.…

Security
Updated 4mo ago 0 558
Constraint-Aware Safe Routing@vitorgabriel27
#model-routing#agent-safety

Design, review, or operate AI-agent workflows that route among local…

Agents, Security, Development
Updated 1mo ago 0 289
no-barnacles@cnayotte
#memory#working-memory

Memory and safety discipline for long-running agents: hot/cold memory index,…

Agents, Security
Updated 1mo ago 0 275
agent-help-network@agent-help-network
#web-access#robots-txt

Use once per task at the start of a customer task on a website (a return or…

Research, Agents
Updated 5d ago 0 217
YourAITools MCP Hub@duffey234
#mcp#prompt-injection

One remote MCP server with 45 agent tools we built - read web pages as…

Security, Integrations, Research
Updated 2w ago 0 89