菜单
Handle Chat-only Canvasight Run output in the current Codex thread. Use when a Run arrives through the native widget host bridge, when a browser/dev Run is queued for await_canvasight_run fallback, or when legacy Plan or Goal node data must be treated as Chat.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Check for or install official stable Canvasight plugin releases. Use when the user asks “更新 Canvasight”, “升级 Canvasight”, “把 Canvasight 更新到最新版”, “检查 Canvasight 更新”, “Canvasight 有更新吗”, “update/upgrade Canvasight”, “check for Canvasight updates”, or whether the installed Canvasight version is current. Do not use for ordinary Canvasight troubleshooting, development-checkout Git pulls, canvas content edits, or updates to unrelated Codex plugins.
Create, refine, or replace Canvasight graphs through write_canvasight_graph; combine professional content Skills with Canvasight's validated horizontal graph structure; and assign explicit or clearly matched Skills to individual nodes. Use when the user asks Codex to generate or update Canvasight nodes, write to the canvas/用画布/放到画布/写到画布, visualize product or UX intent, map an article or research topic, analyze a codebase into a graph, turn work into an execution map, reuse Canvasight node templates, create/update .scatter/scatter.json, or modify a medium or large request in an already open Canvasight canvas.
Open, reopen, attach, and verify Canvasight's Codex native widget, or explicitly open a browser fallback. Use when the user asks to start Canvasight, open the Canvasight workspace, 打开画布, 打开 Canvasight, 恢复最近项目, attach the current Codex task, or verify whether a native canvas actually became ready.
Canvasight plugin index. Use when the user explicitly mentions Canvasight or Scatter, says 打开画布 / 打开 Canvasight, and the request spans multiple Canvasight workflows, or when a Canvasight canvas is already open/attached and a later request is ambiguous or large enough to decide whether it should route through graph writing before direct execution.
Follow Canvasight's Agent Team, role-registry, and agent-report protocol. Use when a Canvasight Run payload has structuredContent.agentTeam.enabled true, or when the user explicitly asks to enable, disable, configure, audit, or include Canvasight Agent Team, ROSTER.md, agent reports, issue reports, solution reports, integration summaries, or the AGENTS.md + role-registry + agent-reports collaboration workflow. Do not use for normal Canvasight opening, Run payload handling, graph writing, troubleshooting, or ordinary code changes unless this protocol is explicitly involved.
Diagnose and fix Canvasight plugin, MCP, native-widget readiness, host bridge, daemon, browser fallback, Run delivery, install, cache, or connection problems. Use when the widget is stuck on Opening Canvasight, await_canvasight_widget_ready returns timeout or failed, React never mounts, a tool falsely appears successful while the canvas is unusable, tools are missing or stale, Transport closed appears, Run does not reach the current task, localhost fails, or Canvasight behavior does not match the installed version.
| name | canvasight-run |
| description | Handle Chat-only Canvasight Run output in the current Codex thread. Use when a Run arrives through the native widget host bridge, when a browser/dev Run is queued for await_canvasight_run fallback, or when legacy Plan or Goal node data must be treated as Chat. |
Use this skill to handle Canvasight Run payloads as Chat follow-ups.
claim_canvasight_thread before clicking Run in an old tab so the daemon scopes the queued Run to the current thread. A bare 5173 page without an explicit claim must be treated as unbound, not as a sent Run.await_canvasight_run. If await_canvasight_run is not callable, use tool_search for Canvasight tools first. If it is callable but fails with Transport closed, report canvasight_mcp_transport_closed: the fallback queue cannot be consumed from this stale task. Inspect mcp-lifecycle.log when available, then reload or use a new task with current Canvasight tools.sessionId when available; use projectPath to attach to the next queued Run from any active session in that project.structuredContent as the source of truth for the next Codex action.structuredContent.agentTeam.enabled is true, use canvasight-agent-team before executing the task. Read its schema and ROSTER.md before assigning or rebuilding a role.Normal Canvasight Run delivery must come from the Codex native widget host bridge, using either MCP Apps ui/message or Codex/OpenAI compatibility window.openai.sendFollowUpMessage. If the UI reports browser_fallback_no_bridge, the page was opened through browser fallback/dev URL instead of the native widget; reopen with open_canvasight after tool_search, or receive the queued fallback with await_canvasight_run. If those visible Canvasight MCP tools fail with Transport closed, stop, inspect mcp-lifecycle.log, and report canvasight_mcp_transport_closed instead of promising queued recovery in the same stale thread. Browser URLs and bare dev pages must not silently pretend success: if no claim exists, the UI must report unbound_dev_session; otherwise it queues the payload for await_canvasight_run. Do not treat Codex app-server turn/start as a Run delivery path.
Native open must have received the active task's explicit CODEX_THREAD_ID and passed the instance-bound await gate with verified fullscreen React/project/canvas evidence; Run is accepted only from that same instance. Do not use a missing hostCapabilities.message declaration alone to disable Run after the MCP App handshake succeeds. Call sendMessage and treat only its resolved Promise as sent.
Read references/run-output-contract.md for Chat delivery and legacy-node normalization.