github/awesome-copilot
Overview
This skill captures patterns and techniques for adding governance, safety, and trust controls to AI agent systems. It describes composable policies, intent classification, tool-level enforcement, trust scoring, and append-only audit trails to keep agents accountable and safe. Use the patterns with any agent framework to limit capabilities, detect dangerous prompts, and maintain compliance.
How this skill works
The skill inspects agent inputs and tool invocations through a layered pipeline: intent classification runs first to flag risky prompts, then policy checks (allowlist/blocklist, content filters, rate limits, and approval gates) decide whether to allow, review, or deny actions. Tool calls are wrapped with decorators that enforce policy and record audit entries. Trust scores track agent reliability over time and can gate sensitive operations.
When to use it
- When agents call external tools (APIs, databases, shell commands) and need constrained access
- For multi-agent workflows where delegation requires trust boundaries and selection
- In production deployments with compliance, auditing, or safety requirements
- When preventing data exfiltration, privilege escalation, or prompt injection
- To enforce rate limits, content filters, or require human approval for risky actions
Best practices
- Model policies as serializable configuration (YAML/JSON) and compose them from broad to specific with most-restrictive-wins semantics
- Run semantic intent classification before any tool execution to block or flag dangerous prompts early
- Wrap every external tool with a governance decorator that enforces policy and appends audit events
- Use decay-based trust scores to adjust autonomy over time and gate sensitive operations by threshold
- Keep an append-only audit trail (JSONL) for denied actions and human review, and export logs to aggregation systems
Example use cases
- Govern a support bot that can search docs and create tickets but cannot access customer SSNs
- Block prompt-injection attempts before they trigger dangerous tool calls like shell_exec
- Maintain trust scores for multiple worker agents and choose the most trusted delegate for a task
- Enforce per-request rate limits and content pattern checks on document retrieval tools
- Produce auditable JSONL logs for compliance reviews and security investigations
FAQ
Compose policies with most-restrictive-wins: merge blocklists and patterns, intersect allowed tool lists, and take the minimum rate limit.
When should intent classification run?
Always run intent classification as a pre-flight check before policy evaluation and any tool execution to catch malicious prompts early.
27 skills
This skill helps you implement governance, safety, and audit controls for AI agents, enabling policy enforcement, threat detection, and trusted tooling.
This skill converts Markdown to HTML using marked.js or pandoc-like methods, enabling fast rendering for templates, docs, and static sites.
This skill interprets shorthand and natural language descriptions to produce production-ready JavaScript code with robust patterns and best practices.
This skill guides you through learning GitHub Copilot CLI with interactive tutorials, tailored tracks, and on-demand Q&A.
This skill generates comprehensive, runnable unit tests across languages using a multi-agent pipeline, ensuring coverage, compatibility, and project-conformant
This skill generates concise, actionable meeting minutes for short internal meetings, capturing decisions, attendees, and clear action items with owners and
This skill helps you identify the least-privilege Azure role that meets required permissions and generates CLI and Bicep guidance for assignment.
This skill analyzes Azure resource groups and generates detailed Mermaid diagrams showing resource relationships to help you understand architecture quickly.
This skill scaffolds a new GitHub Copilot Agent Skill by generating a SKILL.md with frontmatter and optional resources based on prompts.
This skill visually inspects websites from local or remote hosts to identify design issues and suggest source-level fixes.
This skill helps Copilot query Live Microsoft 365 data via WorkIQ to summarize emails, meetings, docs, and teams for actionable insights.
This skill performs AI-powered exploratory testing of web apps with scoutqa, autonomously exploring, verifying flows, and surfacing issues.
This skill validates and previews Azure Bicep deployments, detects syntax issues, permissions, and what-if results to prevent failures.
This skill generates ASCII and Unicode ASCII PlantUML diagrams for terminals and docs, converting PlantUML text into readable ASCII art across diagram types.
This skill generates breadboard circuit mockups and visual diagrams using HTML5 Canvas for retro electronics projects.
This skill helps you streamline Azure Static Web Apps deployment and local development using SWA CLI for configuration, testing, and CI/CD.
This skill helps you create, validate, and troubleshoot Snowflake semantic views using the CLI, ensuring correct DDL and validated results.
This skill helps you configure and contribute VS Code extension commands following official guidelines, ensuring proper titles, categories, visibility, and
This skill enables efficient image processing with ImageMagick, resizing, format conversion, and metadata retrieval for batch operations and thumbnails.
This skill helps you localize every aspect of VS Code extensions, from settings to messages, across languages.
This skill generates high-quality PRDs for software features including executive summaries, user stories, technical specs, and risk analysis.
This skill enables iterative self-evaluation and refinement of AI outputs to improve quality-critical results across code, reports, and analyses.
This skill helps you create conventional git commits by analyzing diffs, staging changes intelligently, and generating accurate messages.
This skill helps you embed agentic Copilot workflows in apps, enabling streaming responses, tool integration, and session management.
This skill helps you manage Azure DevOps resources via the Azure CLI extension, enabling streamlined project, pipeline, and repo administration.
This skill guides you to instrument a web app with Azure App Insights for comprehensive telemetry and improved observability.
This skill manages NuGet packages in .NET projects using the dotnet CLI, ensuring safe additions, removals, and version updates with restoration.
