with one click
visual-questions
Use Agent-Native Plans to ask rich visual intake questions when /visual-questions is explicitly requested before creating a UI plan or visual plan.
Menu
Use Agent-Native Plans to ask rich visual intake questions when /visual-questions is explicitly requested before creating a UI plan or visual plan.
| name | visual-questions |
| description | Use Agent-Native Plans to ask rich visual intake questions when /visual-questions is explicitly requested before creating a UI plan or visual plan. |
| metadata | {"visibility":"both"} |
Use /visual-questions when the next best step is not a plan yet, but a
reviewable visual intake: single-choice option rows, multi-select option rows,
freeform notes, mockup choices, sketch diagrams, and a generated answer summary
that feeds the next planning prompt. It composes with /visual-plan, /ui-plan,
/prototype-plan, and /plan-design.
Gate hard: skip this for tiny, unambiguous changes. If the agent can reasonably
infer the answer, prefer /ui-plan, /prototype-plan, /plan-design, or
/visual-plan directly and put assumptions in the plan.
Visual questions are an explicit intake command, not an automatic preflight for
/visual-plan, /ui-plan, /prototype-plan, or /plan-design.
create-visual-questions with a clear title, brief, source, and repo
path when known.questions for the default UI intake. Provide a custom questions array
only when the task has domain-specific choices.create-ui-plan for static UI
review, create-prototype-plan for click-through UI flows,
create-plan-design for high-fidelity branded UI review,
create-visual-plan for general plans or when a text plan already exists,
or update-visual-plan with targeted contentPatches to fold answers into
an active plan.get-plan-feedback before using the answers.Supported questions entries:
single: chip group where one option wins.multi: chip group where multiple options can be selected.freeform: textarea for constraints, inspirations, or things to avoid.visual: visual options with sketch previews — use for layout direction, flow
depth, surface choice, or diagram choices.Each option can include label, value, description, recommended,
preview, and bullets. Valid preview values match the wireframe surfaces:
desktop, mobile, popover, panel, component, split, flow, and
diagram. Pick the preview that matches the real footprint — do not offer a
desktop/mobile pair for a popover, panel, or component.
single, multi, and visual questions always render a write-in field, so a
reviewer can answer with their own option instead of the listed choices. Do not
add an explicit "Other" or "Something else" option yourself; set
allowOther: false only on the rare question where a free-text answer makes no
sense.
create-visual-questions: create the interactive intake plan.get-visual-plan: inspect the current visual question plan.get-plan-feedback: read comments before creating or updating the next plan.create-ui-plan: create a UI-first plan from the answers.create-prototype-plan: create a prototype-first plan from the answers when
interaction feel matters.create-plan-design: create a high-fidelity branded design plan from the
answers when visual polish is the primary review input.create-visual-plan: create a general visual plan from the answers, or pass
existing plan text as planText when the answers should shape an imported
plan.export-visual-plan: export answer plans as HTML, Markdown fallback,
structured JSON, and MDX files when the intake needs to be checked into a repo.read-visual-plan-source / patch-visual-plan-source: inspect or patch the
MDX source if another agent is operating from checked-in plan files.There are two ways into Plans.
Coding agent (CLI). Install once with the Agent-Native CLI. The command installs the Plans skills, registers the hosted Plans MCP connector, and authenticates it in the same step (a one-time browser sign-in at setup — this is intended), so the first tool call does not hit an OAuth wall:
agent-native skills add visual-plan
After that, /visual-plan (and /visual-recap, /ui-plan,
/prototype-plan, /plan-design, /visual-questions) generate a plan and open
the editor. Pass --no-connect to
register the connector without authenticating, then run
agent-native connect https://plan.agent-native.com whenever you are ready.
Browser (people you share with). Open the Plans editor and create & edit with no sign-up — you work as a guest. Sign in only when you want to save or share; signing in claims the plans you made as a guest into your account.
Sharing and commenting require an account: public/shared plans are viewable by anyone with the link, but commenting on them needs an agent-native account.
For fully offline, no-account use, run the Plans app locally and sync plans to your repo as MDX. This local mode is a separate advanced path, not the default hosted flow.
If a Plans tool returns needs auth, Unauthorized, or Session terminated,
do not keep retrying the tool. Authenticate the connector with
agent-native connect https://plan.agent-native.com (OAuth-capable hosts can
instead re-run /mcp and choose Authenticate), then continue once the connector
is available.
Hosted default: connect https://plan.agent-native.com/_agent-native/mcp. Do
not put shared secrets in skill files.
Use Agent-Native Plans for UI-first planning with an optional top pan/zoom wireframe canvas, a refined Notion-like document, rich tabs, diagrams, comments, drawing, and agent handoff.
Use Agent-Native Plans when coding-agent work needs an interactive structured plan document with inline diagrams, implementation maps, optional UI/product wireframes or prototypes, annotations, and comments.
Use Agent-Native Plans to turn a code change, PR diff, or git diff into a visual recap plan for high-altitude review — schema, API, file, and before/after changes as grounded structured blocks instead of a wall of diff.
Monitor a PR, fix feedback and CI failures until fully green for 30 min. Run with /babysit-pr <number>
Creating, editing, and managing extensions — sandboxed Alpine.js mini-apps that run inside iframes. Use when a user asks for a dashboard, widget, calculator, or any interactive mini-app that calls external APIs. Distinct from LLM "tools" (function calls) — see note below.
Query Prometheus-compatible metrics endpoints (self-hosted, Grafana Cloud Prom, AMP, etc.) via the prometheus action and as a dashboard panel source.