agent-governance
This skill is for DevOps & Infrastructure and helps you implement agent access controls, add audit trails for ai agents, and create intent classification for safety.
Patterns and techniques for adding governance, safety, and trust controls to AI agent systems. Use this skill when: - Building AI agents that call external tools (APIs, databases, file systems) - Implementing policy-based access controls for agent tool usage - Adding semantic intent classification to detect dangerous prompts - Creating trust scoring systems for multi-agent workflows - Building audit trails for agent actions and decisions - Enforcing rate limits, content filters, or tool restrictions on agents - Working with any agent framework (PydanticAI, CrewAI, OpenAI Agents, LangChain, Aut...
Helps you
- Implement agent access controls
- Add audit trails for ai agents
- Create intent classification for safety
- Enforce rate limits on agent tools
- Design trust scoring systems
- Build governance policies for agents
Install
Copy into ~/.claude/skillsgit clone --depth 1 https://github.com/github/awesome-copilot
cp -r awesome-copilot/skills/agent-governance ~/.claude/skills/agent-governanceWhat it can use
The author didn’t declare which tools this skill uses. Read the SKILL.md before installing it.
safetyguardrailsauditpolicymulti-agenttool-use
Also in github/awesome-copilot
View the repoUse this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like "map this code...
Run the AgentRC readiness assessment on the current repository and produce a static HTML dashboard at reports/index.html. Wraps `npx github:...
Generate tailored AI agent instruction files via AgentRC instructions command. Produces .github/copilot-instructions.md (default, recommende...
Help the user pick, write, or apply an AgentRC policy. Policies customise readiness scoring by disabling irrelevant checks, overriding impac...
Use this skill when the user shares ad campaign performance data and asks what to cut, scale, or test. Trigger for prompts like "analyze my...
Add educational comments to the file specified, or prompt asking for file to comment if one is not provided.
Write, debug, and optimize Adobe Illustrator automation scripts using ExtendScript (JavaScript/JSX). Use when creating or modifying scripts...
Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loop...
Check any AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 risks. Use this skill when: - Evaluating an agent sys...
Find, evaluate, and assemble the smallest compatible set of AI Agent Skills for an end-to-end natural-language goal. Use when a user wants S...
Verify supply chain integrity for AI agent plugins, tools, and dependencies. Use this skill when: - Generating SHA-256 integrity manifests f...
Comprehensive AI prompt engineering safety review and improvement prompt. Analyzes prompts for safety, bias, security vulnerabilities, and e...
Other DevOps & Infrastructure skills
Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only throug...
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wan...
Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before f...
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-comm...
Generate an interactive bash wizard that walks a human through a manual procedure — third-party setup, a one-off migration, an A→B state tra...
Manage Google Apps Script projects.