nteract

Pull and triage submitted nteract diagnostics archives from Cloudflare using a diagnostics id/token. Use when investigating "submit logs" reports, runtimed/notebook/MCP diagnostic archives, telemetry diagnostics uploads, or failures where the user gives an id and token.

Frontend development for nteract UI/product surfaces, Elements fixtures, hot reload, dev daemon setup, MCP server workflow, TypeScript bindings via ts-rs, and reactive state work that touches RxJS streams, useSyncExternalStore stores, or WASM-backed notebook/runtime projections.

Automerge sync protocol internals, document model (OpSet, ChangeGraph, fork/merge, save/load lifecycle), and higher-level protocol design patterns. Use when debugging sync failures, reasoning about convergence, changing reconnection logic, working with document structure, diagnosing panics in op application, adding new sync streams, or evaluating architectural patterns from automerge-repo and samod.

Develop, debug, and manage the runtimed daemon, Python bindings, build system, and Python bindings. Use when working on daemon code, kernel issues, maturin builds, or xtask workflows.

Understand the MCP server session lifecycle: proxy supervision, daemon watch loop, session state machine, rejoin/reconnect races, and room eviction. Use when working on runt-mcp, runt-mcp-proxy, daemon_watch.rs, or any code that reads/writes the session Arc<RwLock<Option<NotebookSession>>>.

Release and version the project. Only invoke manually.

Architecture and documentation framing for cross-cutting repo decisions, docs taxonomy placement, ADRs, memos, PRDs, implementation plans, audits, measurements, runbooks, and source-grounded proposals. Use when deciding where durable docs belong, drafting or moving architecture/product/design docs, or promoting `.context/` notes into repo docs. Do not use for routine code changes unless they require durable cross-functional documentation.

The end-to-end cell execution pipeline from MCP tool call through daemon to kernel and back. Use when debugging execution failures, understanding output timing, investigating why outputs are missing or stale, or modifying the execute/run-all flow. Covers required_heads, CellQueued, RuntimeStateDoc polling, output-sync grace, and output resolution.

Generate trustworthy, accessible, agent-legible charts with Semiotic. Use whenever you produce a data visualization in a React/TypeScript app, stream a chart as generative UI, or pick a chart type for a dataset. Emit a validated config and run the trust loop — never hand-write chart JSX that breaks on first paint.

Use nteract notebooks as a persistent Python REPL. Trigger this skill whenever you're about to run python3 -c, write a throwaway .py script, or chain multiple shell commands for data exploration, analysis, plotting, or iterative computation. Notebooks preserve state between cells, show rich output, and can be used in realtime with users.