菜单
Build AgentDock Coach and portfolio chat UIs with assistant-ui. Use when upgrading the advisor panel, adding generative UI for launch commands, or scaffolding chat in agentdock/ui. Triggers: "coach UI", "chat panel", "assistant-ui", "Hey Coach".
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
| name | chatbot-builder |
| description | Build AgentDock Coach and portfolio chat UIs with assistant-ui. Use when upgrading the advisor panel, adding generative UI for launch commands, or scaffolding chat in agentdock/ui. Triggers: "coach UI", "chat panel", "assistant-ui", "Hey Coach". |
| origin | agentdock |
Canonical skill: D:\projects\skills\chatbot-builder\SKILL.md
Human doc: docs/CHATBOT_BUILDER.md
AgentDock-specific rules on top of the portfolio standard.
ui/ onlychat.js → POST /api/chat127.0.0.1 only; runtime fetches same-originjson commands block format until shared parser is extractedReplace the bespoke chat panel in ui/ with:
<AssistantRuntimeProvider runtime={useAgentDockRuntime(sessionId)}>
<Thread />
</AssistantRuntimeProvider>
See references/agentdock-integration.md (copy of portfolio reference).
Pull before each Coach turn:
GET /api/scan
GET /api/profiles
GET /api/portfolio/health
memory.md excerpt (server-side)
vitals (when Vitals module lands)
chat.js command | UI gate |
|---|---|
showMessage, openUrl | Inline OK |
runScan, generatePlan | Confirm chip |
launch, setMemory, switchProject | Approval card |
| File | Change |
|---|---|
ui/package.json | Add @assistant-ui/react, adapter package |
ui/src/components/coach/ | Thread + runtime hook |
ui/src/lib/agentdockRuntime.ts | External store → /api/chat |
chat.js | Optional: export parseCoachCommands() |
package.json server bundlelaunch commands from Coach.env values in context JSONreferences/agentdock-integration.mdD:\projects\skills\chatbot-builder\references\assistant-ui.mdD:\projects\docs\AI_OS_ARCHITECTURE.mdGenerate and critically evaluate grounded ideas about a topic. Use when asking what to improve, requesting idea generation, exploring surprising directions, or wanting the AI to proactively suggest strong options before brainstorming one in depth. Triggers on phrases like 'what should I improve', 'give me ideas', 'ideate on X', 'surprise me', 'what would you change', or any request for AI-generated suggestions rather than refining the user's own idea.
Create structured plans for multi-step tasks -- software features, research workflows, events, study plans, or any goal that benefits from breakdown. Also deepens existing plans with interactive sub-agent review. Use when the user says 'plan this', 'create a plan', 'how should we build', 'break this down', or when a brainstorm doc is ready for planning. Use 'deepen the plan' or 'deepening pass' for the deepening flow. For exploratory requests, prefer ce-brainstorm first.
Execute work efficiently while maintaining quality and finishing features
Explore requirements and approaches through collaborative dialogue, then write a right-sized requirements document. Use when the user says "let's brainstorm", "what should we build", or "help me think through X", presents a vague or ambitious feature request, or seems unsure about scope or direction -- even without explicitly asking to brainstorm.
Structured code review using tiered persona agents, confidence-gated findings, and a merge/dedup pipeline. In interactive mode it applies safe, verified fixes and commits them when the working tree is clean (it never pushes); in mode:agent it reports only and the caller applies. Use when reviewing code changes before creating a PR.
Document a recently solved problem to compound your team's knowledge or CONCEPTS.md, the project's shared domain vocabulary.