neon-pilot

Use when deciding between follow-up queues, scheduled callbacks, automation-owned attention, wakeups, and async follow-up surfaces.

Use when a task benefits from JavaScript orchestration, explicit phases, structured progress logs, parallel fanout, or multiple daemon-backed subagents coordinated through the workflow tool.

Use when starting, inspecting, rerunning, following up, or cancelling durable background commands or subagents.

Use when designing, creating, editing, building, validating, installing, or debugging Neon Pilot extensions, application pages, contributions to existing applications, or complete first-class applications from the bundled desktop app. This skill is self-contained and must be used without a Neon Pilot source checkout.

Use when working with the built-in desktop Workbench Browser, browser comments, browser snapshots, CDP actions, screenshots, or the browser versus agent-browser boundary.

Use the unified Neon Pilot CLI/control plane for self-administration, delegated agent control, conversations, workspace/sidebar state, runs, automations, extensions, settings, and extension-contributed administration surfaces.

Use when installing, inspecting, or explaining Codex and Claude Code style agent plugins in Neon Pilot.

Use when controlling native desktop applications through Cua Driver. Prefer browser tools for web-only tasks.

Use when running Neon Pilot feature QA from docs/feature-qa-status.md with parallel discover-and-fix worker agents, isolated dev app instances, evidence collection, bug queue triage, and parent-owned final validation/status updates.

Create a typed visual diff review artifact. Use when the user invokes /diff-review, asks for a visual review of current git or workspace changes, wants changed files summarized by risk, or needs a source-backed review matrix artifact.

Create a typed visual plan review artifact. Use when the user invokes /plan-review, asks to critique or review a plan, wants risks and gaps in a proposed implementation, or needs a visual review matrix for a plan file, message, or scope.

Create a typed project recap conversation artifact. Use when the user invokes /project-recap, asks for a context-switching recap, wants a visual summary of project state, decisions, progress, blockers, or next steps.

Create a typed slide deck conversation artifact. Use when the user invokes /slides, asks for slides, a presentation, briefing deck, deck artifact, or wants source material converted into viewport-based slides.

Create a typed visual explainer conversation artifact. Use when the user invokes /visualize, asks to visualize a topic, wants a visual explanation, diagram-backed explainer, implementation map, concept breakdown, or asks for an artifact with visual-explainer defaults.

Use when creating, updating, inspecting, or rendering conversation artifacts, HTML reports, Mermaid diagrams, LaTeX outputs, or project deliverables.

Use when creating, inspecting, validating, running, or troubleshooting daemon-backed scheduled automations and conversation callbacks.

Use when deciding whether behavior belongs in an instruction file, durable doc, reusable skill, tool, or extension.

Use when you have a goal to work toward across multiple turns, or when the user asks you to own a task and keep going without waiting for input.