ai-governance skills

719 tagged ai-governance, measured the same way as everything else here.

Browse within: ai-coding 243agentic-ai 167agent-orchestration 155AI Safety 139cli 137agent-runtime 112ai-coding-assistant 108agentive-os 100ai-evolution 100ai-lifeform 100anti-hallucination 100ai-security 92ai-tools 87Autonomous Agents 83

code-executor-mcp

50

CSOAI-ORG/code-executor-mcp

Skill Claude CodeCodex

Secure code execution in sandboxed environments. Run Python, JavaScript, and shell commands safely with tier-based permissions.

not rated 0 6d ago A 0 tokens original MIT

CSOAI-ORG/csoai-static-deploy2

Skill Claude CodeCodex

Check whether an AI model's PUBLIC artifacts meet EU AI Act Article 50 transparency signals (license declared, task declared, model card present) and get back a deterministic, signable result. Use this instead of reasoning about Article 50 obligations from memory — it returns observed facts from the public model-info…

not rated 0 4d ago A 100 tokens original MIT

memory-search-mcp

52

CSOAI-ORG/memory-search-mcp

Skill Claude CodeCodex

Long-term memory and context retrieval for AI agents. Semantic search across conversation history with care-weighted relevance.

not rated 0 6d ago A 0 tokens original MIT

web-research-mcp

53

CSOAI-ORG/web-research-mcp

Skill Claude CodeCodex

Intelligent web research with source validation. Automated research synthesis with citation tracking and fact verification.

not rated 0 6d ago A 0 tokens original MIT

mima-close-gaps

54

mimaworks/governance-mcp

Skill Claude CodeCodex

Run the compliance copilot loop — observe posture, identify gaps, dry-run proposed evidence records where possible, present for human approval, then write approved records. Use when the user asks to close compliance gaps, improve their EU AI Act score, or fix failing governance gates.

not rated 0 2mo ago A 60 tokens

hybrid-routing

55

mgannotti/scout-plugin-hybrid-routing

Skill Claude CodeCodex

Route a task to the right model across a hybrid stack — Scout's hosted cloud models, on-device runtimes (Ollama, LM Studio, Foundry Local, llama.cpp, vLLM), and org-hosted endpoints — by classifying it on sensitivity, role and difficulty, and enforcing an egress boundary so confidential and restricted content never…

not rated 0 1mo ago A 138 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: