AI & Agents Agent Skills for Windsurf (legacy)

Diagnose context stuffing vs. context engineering.

Scaffold a new MCP tool for the CodeScene MCP Server following the project's established patterns for directory structure, dependency…

Create new skills, modify and improve existing skills, and measure skill performance.

Develop examples for AI SDK functions. Use when creating, running, or modifying examples under examples/ai-functions/src to validate…

Canonical vocabulary for human-AI software work.

Use First Principles Framework (FPF) to solve problems, architect systems, evaluate alternatives, decompose complexity, classify problems…

Analyze mistakes with conversation length as potential cause (CAT-specific)

Remove an Agent roster entry from the active Mission agents.md without closing panes.

Check for updates and upgrade Ouroboros to the latest version

Infuses your development workflow with high-energy empathy and professional encouragement through an ENFP-style leadership persona.

Universal prompt engineering techniques for any LLM.

Review recent conversations to find improvements for CLAUDE.md files.

Multi-agent meta-orchestrator. Use when task spans 5+ files or 3+ modules, or when user says 'parallel', 'split this up', 'do all of…

Step-by-step complex reasoning for multi-variable problems.

Author a prompt-enhancement system prompt for a new ecosystem and register/update it on the orchestrator's prompt-analysis service.

Create and manage Databricks Agent Bricks: Knowledge Assistants (KA) for document Q&A, Genie Spaces for SQL exploration, and Supervisor…

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use…

Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation

Coordinates Claude agent teams via filesystem protocol.

Generate or update the agentic environment definition for AgentSmith, SkillSmith, and CommandSmith

Autonomously optimize any Claude Code skill by running it repeatedly, scoring against binary evals, mutating the prompt, and keeping…