Loading...
Loading...
Found 14 Skills
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, AutoGen)
Add policy enforcement, zero-trust identity, and execution sandboxing to AI agents with Microsoft's Agent Governance Toolkit
Skill converted from mcp-deploy-manage-agents.prompt.md
ALWAYS invoke this skill at the START of every session before doing any other work. This skill ensures the host project has agent governance rules (skill routing, pre-implementation protocol, issue tracking conventions) installed in its context file. It is idempotent — if rules are already present, it exits silently. Without this skill running first, other swain skills (swain-design, swain-do, swain-release) will not be routable.
Skill for using Paperclip — open-source orchestration platform for running autonomous AI-agent companies with org charts, budgets, governance, and heartbeats.
Configure Cedar policy enforcement and Ed25519 signed receipts for Claude Code tool calls. Use when setting up projects that need cryptographic audit trails, policy-gated tool execution, or compliance-ready evidence of agent actions.
Comprehensive map for multi-brain, orchestration, and agent governance. Triggers when users ask to 'view the orchestration ecosystem', 'how do agents work together?', 'multi-brain workflows', or 'give agents access'.
Trae-optimized PUA high-agency governance skill for npx skills installation. Only activate it in scenarios such as explicit PUA requests, repeated task failures, user frustration, giving-up/passive behavior, or unverified task completion. Do not trigger it for normal first-attempt tasks.
Design enterprise-grade agent systems with Microsoft's agent framework patterns: role separation, workflow control, policy boundaries, and observability. Use when users need robust organizational agent workflows, governance, and maintainable multi-agent architecture.
General Architecture Specification for CS-RAG Project, unifies global architecture cognition and architecture design constraints, provides entry points for layered inspection, impact analysis, interface contracts, dependency injection and pluggable governance.
Run a session retrospective against the CLAUDE.md, skills, and hooks — identify guidance violations, stale rules, and gaps. Use when user says 'reflect on this session', 'what did we learn', 'post-mortem this work', 'what should we update in CLAUDE.md', or 'are our skills still right'. Do NOT use for code review (use /review-diff), PR prep (use /create-pr), or creating new skills from scratch (use /create-or-audit-skill).
Enforces complete execution, mode-aware delivery, compact sub-agent communication, independent agent-review gating, validation, and reporting for implementation, bugfix, hardening, documentation, specification, architecture, design, review, and post-mortem tasks. Use whenever work must be completed, reviewed, validated, or documented through an explicit execution mode instead of handled ad hoc.