paper-to-intuition
Transforms an academic paper into deep, multi-layered understanding. Use when asked to explain a paper, break down a research paper, understand an arXiv paper, or build intuition for a technical concept from a paper. Generates explanations at multiple levels plus visual intuition diagrams.
quality-gates
This skill should be used when the user asks to "check quality gates", "validate against standards", "read AGENTS.md", "enforce project patterns", "follow constitution.md", "validate code quality", or needs guidance on quality standards enforcement in k2-dev workflows.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications.
openapi-toolkit-mistralai-dart
Automates updating mistralai_dart when Mistral AI OpenAPI spec changes. Fetches latest spec, compares against current, generates changelogs and prioritized implementation plans. Use for: (1) Checking for API updates, (2) Generating implementation plans for spec changes, (3) Creating new models/endpoints from spec, (4) Syncing local spec with upstream. Triggers: "update api", "sync openapi", "new endpoints", "api changes", "check for updates", "update spec", "api version", "fetch spec", "compare spec", "what changed in the api", "implementation plan".
context-aware-delegation
Understand agent context isolation and write effective prompts for spawned agents. Use when orchestrating multi-agent workflows to ensure subagents receive complete, self-contained context.
integration-test
Full SDK integration test that runs actual queries through the Claude SDK sandbox. Use after making changes to SDK client code, session management, skill loading, network proxy, voice/TTS, or image generation. Runs real prompts through the SDK to verify the complete path works.
orchestrator-directives-skill
Cost-first delegation patterns and decision frameworks for multi-AI coordination
google-adk-python
Build AI agents with Google's Agent Development Kit (ADK) Python. Use when building AI agents with tool integration, multi-agent systems, workflow agents (sequential, parallel, loop), or deploying to Vertex AI.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
moai-docs-unified
Enhanced docs unified with AI-powered features. Enhanced with Context7 MCP for up-to-date documentation.
limacharlie-call
**REQUIRED for ALL LimaCharlie operations** - list orgs, sensors, rules, detections, queries, and 179 functions. NEVER call LimaCharlie MCP tools directly. Use cases: 'what orgs do I have', 'list sensors', 'search IOCs', 'run LCQL query', 'create detection rule'. This skill loads function docs and delegates to sub-agent.
goose-recipes
Create, validate, and work with Goose recipes - reusable AI agent configurations that package specific setups for tasks. Use when creating recipe.yaml/recipe.json files, configuring Goose extensions, parameters, retry logic, structured outputs, or debugging recipe validation errors.
pop-knowledge-lookup
Queries cached external documentation and blog content for authoritative, up-to-date information. Sources include Claude Code docs, engineering blog, and configured knowledge bases with 24-hour TTL caching. Use when you need current information about Claude Code features, hooks, or best practices. Do NOT use for general coding questions - rely on training knowledge or web search instead.
dispatching-parallel-agents
Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently
ai-safety-auditor
Audit AI systems for safety, bias, and responsible deployment
create-plan
Analyzes design docs and existing projects to create detailed, actionable implementation plans for Claude Code. Use when the user asks to create an implementation plan, analyze a feature, or break down tasks.
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
model-deployment
LLM deployment strategies including vLLM, TGI, and cloud inference endpoints.
behavioral-modes
AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.
