ai-protocol-platform

Write, review, debug, and explain code. Use when the user asks about programming, needs code written, wants a code review, or has a bug to investigate.

Extract structured data from documents, images, and unstructured text. Use when the user needs tables, key-value pairs, or specific fields pulled from content.

Analyze documents, extract structured data, and answer questions about uploaded files. Use when the user uploads a document, asks about file contents, or requests data extraction.

General-purpose AI assistant for everyday tasks. Use as the default skill when no specialized skill matches the user's request.

Search the web, summarize findings, and answer research questions. Use when the user asks about current events, needs web research, or wants information from online sources.

Interactive multi-surface A2UI demo. Renders a form to the workspace pane; user submits a value via a Button action; the agent reads the structured action context on the next turn without re-rendering. Demonstrates the discrete-action half of the v6.2.0 sprint 2.10 surface→agent loop — sibling of the read-only workspace-demo.

Multi-surface A2UI demo. Emits dashboard components to the persistent workspace pane instead of inline-in-chat. The deterministic end-to-end demo for the v6.2.0 sprint 2.9 surface routing.

MUST READ before writing or modifying any ADK agent code. ADK API quick reference for Python. Covers agent types, tool definitions, orchestration patterns, callbacks, state management, and common pitfalls. Use when user asks "how do I define an agent", "create a tool", "what orchestration patterns exist", "how do callbacks work", or when writing Agent(), FunctionTool, callbacks, or orchestration code. Do NOT use for deployment, evaluation, or project scaffolding questions.

MUST READ before deploying any ADK agent. Deployment guide — Agent Engine, Cloud Run, CI/CD pipelines, secrets, and testing deployed agents. Covers deployment targets, infrastructure setup, and production deployment workflows. Use when user says "deploy my agent", "set up CI/CD", "configure secrets", "test my deployed agent", "make deploy", "set up staging and production", or when running make deploy or troubleshooting deployment issues. Do NOT use for API code patterns (use adk-cheatsheet), evaluation (use adk-eval-guide), or project scaffolding (use adk-scaffold).

ALWAYS ACTIVE — read this skill at the start of every ADK session. ADK development lifecycle and coding guidelines. Covers the full workflow from understanding the spec through implementation, evaluation, and deployment. Includes mandatory operational rules for coding agents — code preservation, model selection, troubleshooting. Use when user says "start a new ADK project", "how do I develop an agent", "read the design spec", "what's the development workflow", or when planning agent development. Do NOT use for API-level code patterns (use adk-cheatsheet), evaluation details (use adk-eval-guide), or deployment specifics (use adk-deploy-guide).

MUST READ before running any ADK evaluation. Evaluation methodology for ADK agents — metrics, evalsets, LLM-as-judge, and critical gotchas. Covers evalset schema, test_config.json format, tool trajectory scoring, and common failure causes. Use when user says "run evaluations", "eval scores are failing", "how do I test my agent", "set up eval cases", "make eval", or when running adk eval or debugging evaluation results. Do NOT use for API code patterns (use adk-cheatsheet), deployment (use adk-deploy-guide), or project scaffolding (use adk-scaffold).

MUST READ before scaffolding any ADK agent project. Project scaffolding — create new ADK agent projects or enhance existing ones with deployment, CI/CD, and infrastructure. Covers requirements gathering, DESIGN_SPEC.md authoring, create and enhance workflows, and template options. Use when user says "create a new agent", "scaffold a project", "set up deployment", "add CI/CD", "start a new ADK app", "enhance my project", or "add RAG". Do NOT use for API code patterns (use adk-cheatsheet), evaluation (use adk-eval-guide), or deployment operations (use adk-deploy-guide).

Disambiguates the four-protocol stack (AG-UI / A2UI / MCP / MCP Apps / Agent Skills) with vendored offline specs. Load when writing design docs, implementing a new protocol surface, or verifying spec compliance.

Create design documents for Aitana Labs features in the correct format and location. Use when user asks to create a design doc, plan a feature, write a spec, or document a design. Also use when user says "design", "RFC", "proposal", or wants to think through a feature before implementing. Handles both planned and implemented docs.

Evaluate sprint implementations against design docs and acceptance criteria with concrete scoring rubric (100 points, 70 to pass). Provides actionable feedback loop on failure. Use when user says "evaluate sprint", "review implementation", "assess sprint quality", "grade the sprint", or after sprint-executor completes. Also triggers for "is this ready to ship" or "quality check the sprint".

Execute approved sprint plans with test-driven development, continuous linting, progress tracking, and pause points. Supports parallel milestone execution via Task sub-agents. Use when user says "execute sprint", "start sprint", "begin implementation", "run the sprint plan", or wants to implement an approved sprint plan. Also use when resuming a paused sprint across sessions.

Analyze design docs, calculate development velocity, and create realistic sprint plans with day-by-day breakdowns for the Aitana Labs platform. Use when user asks to "plan sprint", "create sprint plan", "estimate timeline", "break down work", or wants to plan implementation of a design doc. Also triggers when user says "how long will this take" for a feature.