@agent-native/core 0.145.4 → 0.145.6

package/dist/templates/default/.agents/skills/turn-into-app/references/fresh-project.md

@@ -0,0 +1,64 @@
+# Fresh Project source guide
+
+Use this guide when `/turn-into-app` is invoked in a new Claude or ChatGPT
+Project rather than after a completed thread.
+
+## What the host can provide
+
+The source is whatever the host put in the model's current context:
+
+- Project instructions: the job, audience, constraints, quality bar, and
+  approved tools or integrations.
+- Knowledge files and attachments: reference material, templates, examples,
+  and links that the app should use.
+- Past runs: only conversations or outputs the host actually supplied. They
+  are examples and evaluation material, not an automatic import of every
+  private Project conversation.
+- The current request: the app boundary, target workspace, name, and explicit
+  corrections.
+
+Do not infer hidden system prompts, account settings, private history, API keys,
+or credentials. The Dispatch MCP connector can start a workspace app creation,
+but it cannot unlock or scrape private Project content.
+
+## Source brief
+
+Write a compact brief before starting the app:
+
+```text
+Source: host-provided Claude/ChatGPT Project context
+Provenance: project instructions, selected knowledge files, and visible runs
+Project goal:
+Configuration and constraints:
+Knowledge sources:
+Repeatable workflow:
+Inputs and outputs:
+Judgment and review points:
+Representative runs: none, or 1-3 selected examples
+Integrations and permissions:
+Unknowns and follow-up:
+```
+
+Keep source references bounded. Prefer a file name, URL, resource ID, or short
+summary over a large pasted document. Do not put secrets or raw customer data
+in the brief.
+
+## Fresh-box setup
+
+Install the exported `turn-into-app` skill in the host when the host supports
+skills. For a ChatGPT Project or any host that exposes only the MCP connector,
+also place the skill instructions or this reference in the Project
+instructions/knowledge files. Then add and authenticate the Dispatch MCP
+connector from the packaged `adapters/chatgpt-mcp/connector.json`.
+
+In a new Project chat, say:
+
+```text
+Turn this project into an app. Use the visible Project instructions,
+knowledge files, and any selected successful runs as the source. Create the
+app in the connected Agent-Native workspace, keep the source brief bounded,
+and report the real path and verification result.
+```
+
+If the host does not show the Project instructions or files to the model, stop
+and request an export or attachment. Do not claim that the Project was read.

package/dist/templates/default/AGENTS.md

@@ -24,7 +24,12 @@ cross-cutting work and `self-modifying-code` when changing app source.
   unauthenticated URLs, or non-JSON responses.
 - Keep database code provider-agnostic and migrations additive. Do not use
   adapter-only database methods or production schema push commands.
-- All AI work goes through the agent chat. UIs do not call model providers.
+- All user-facing AI work goes through the agent chat. UI and server code do
+  not call model providers or inline LLM APIs directly, or hide AI-shaped
+  multi-step work in one action.
+  Keep actions deterministic and focused; use the AgentSidebar for research,
+  analysis, generation, recommendation, synthesis, and follow-ups in the same
+  thread.
 - Keep domain workflows on named routes and preserve the scaffold's full-page
   chat route. Use the right AgentSidebar for contextual AI and open it when a
   domain button hands work to the agent.

package/dist/templates/default/app/i18n/ar-SA.ts

@@ -232,6 +232,8 @@ const messages = {
     newTerminal: "محطة جديدة",
     panelOptions: "خيارات لوحة الوكيل",
     collapseSidebar: "طي الشريط الجانبي",
+    widenChat: "توسيع الدردشة إلى 75٪",
+    returnChatToLayout: "إعادة الدردشة إلى تخطيط الصفحة",
     hideChats: "إخفاء الدردشات",
     allChats: "جميع الدردشات",
     settings: "الإعدادات",
@@ -487,6 +489,10 @@ const messages = {
     noMembers: "لا يوجد أعضاء بعد.",
     memberCount_one: "{{count}} member",
     memberCount_other: "{{count}} members",
+    memberPagination: "ترقيم قائمة الأعضاء",
+    previousMemberPage: "الانتقال إلى صفحة الأعضاء السابقة",
+    nextMemberPage: "الانتقال إلى صفحة الأعضاء التالية",
+    memberPageStatus: "الصفحة {{page}} من {{totalPages}}",
     memberCount_zero: "{{count}} members",
     memberCount_two: "{{count}} members",
     memberCount_few: "{{count}} members",

package/dist/templates/default/app/i18n/de-DE.ts

@@ -234,6 +234,8 @@ const messages = {
     newTerminal: "Neues Terminal",
     panelOptions: "Optionen im Agentenpanel",
     collapseSidebar: "Seitenleiste einklappen",
+    widenChat: "Chat auf 75 % verbreitern",
+    returnChatToLayout: "Chat zurück ins Layout",
     hideChats: "Chats ausblenden",
     allChats: "Alle Chats",
     settings: "Einstellungen",
@@ -476,6 +478,10 @@ const messages = {
     noMembers: "Noch keine Mitglieder.",
     memberCount_one: "{{count}} member",
     memberCount_other: "{{count}} members",
+    memberPagination: "Seitennavigation der Mitgliederliste",
+    previousMemberPage: "Zur vorherigen Mitgliederseite",
+    nextMemberPage: "Zur nächsten Mitgliederseite",
+    memberPageStatus: "Seite {{page}} von {{totalPages}}",
     youAreRole: "You are {{role}}",
     changeRole: "Rolle wechseln",
     removeMember: "Mitglied entfernen",

package/dist/templates/default/app/i18n/en-US.ts

@@ -229,6 +229,8 @@ const messages = {
     newTerminal: "New terminal",
     panelOptions: "Agent panel options",
     collapseSidebar: "Collapse sidebar",
+    widenChat: "Widen chat to 75%",
+    returnChatToLayout: "Return chat to layout",
     hideChats: "Hide chats",
     allChats: "All chats",
     settings: "Settings",
@@ -466,6 +468,10 @@ const messages = {
     noMembers: "No members yet.",
     memberCount_one: "{{count}} member",
     memberCount_other: "{{count}} members",
+    memberPagination: "Member list pagination",
+    previousMemberPage: "Go to previous member page",
+    nextMemberPage: "Go to next member page",
+    memberPageStatus: "Page {{page}} of {{totalPages}}",
     youAreRole: "You are {{role}}",
     changeRole: "Change role",
     removeMember: "Remove member",

package/dist/templates/default/app/i18n/es-ES.ts

@@ -235,6 +235,8 @@ const messages = {
     newTerminal: "Nueva terminal",
     panelOptions: "Opciones del panel de agentes",
     collapseSidebar: "Contraer barra lateral",
+    widenChat: "Ampliar el chat al 75 %",
+    returnChatToLayout: "Devolver el chat al diseño",
     hideChats: "Ocultar chats",
     allChats: "Todos los chats",
     settings: "Ajustes",
@@ -482,6 +484,10 @@ const messages = {
     noMembers: "Aún no hay miembros.",
     memberCount_one: "{{count}} member",
     memberCount_other: "{{count}} members",
+    memberPagination: "Paginación de la lista de miembros",
+    previousMemberPage: "Ir a la página anterior de miembros",
+    nextMemberPage: "Ir a la página siguiente de miembros",
+    memberPageStatus: "Página {{page}} de {{totalPages}}",
     memberCount_many: "{{count}} members",
     youAreRole: "You are {{role}}",
     changeRole: "Cambiar rol",

package/dist/templates/default/app/i18n/fr-FR.ts

@@ -236,6 +236,8 @@ const messages = {
     newTerminal: "Nouvelle borne",
     panelOptions: "Options du panneau d'agent",
     collapseSidebar: "Réduire la barre latérale",
+    widenChat: "Élargir le chat à 75 %",
+    returnChatToLayout: "Remettre le chat dans la mise en page",
     hideChats: "Masquer les discussions",
     allChats: "Toutes les discussions",
     settings: "Paramètres",
@@ -481,6 +483,10 @@ const messages = {
     noMembers: "Aucun membre pour le moment.",
     memberCount_one: "{{count}} member",
     memberCount_other: "{{count}} members",
+    memberPagination: "Pagination de la liste des membres",
+    previousMemberPage: "Accéder à la page précédente des membres",
+    nextMemberPage: "Accéder à la page suivante des membres",
+    memberPageStatus: "Page {{page}} sur {{totalPages}}",
     memberCount_many: "{{count}} members",
     youAreRole: "You are {{role}}",
     changeRole: "Changer de rôle",

package/dist/templates/default/app/i18n/hi-IN.ts

@@ -221,6 +221,8 @@ const messages = {
     newTerminal: "नया टर्मिनल",
     panelOptions: "एजेंट पैनल विकल्प",
     collapseSidebar: "साइडबार समेटें",
+    widenChat: "चैट को 75% चौड़ा करें",
+    returnChatToLayout: "चैट को लेआउट में वापस लाएँ",
     hideChats: "चैट छुपाएं",
     allChats: "सभी चैट",
     settings: "सेटिंग्स",
@@ -459,6 +461,10 @@ const messages = {
     noMembers: "अभी कोई सदस्य नहीं है.",
     memberCount_one: "{{count}} member",
     memberCount_other: "{{count}} members",
+    memberPagination: "सदस्य सूची पृष्ठांकन",
+    previousMemberPage: "पिछले सदस्य पृष्ठ पर जाएं",
+    nextMemberPage: "अगले सदस्य पृष्ठ पर जाएं",
+    memberPageStatus: "पृष्ठ {{page}} / {{totalPages}}",
     youAreRole: "You are {{role}}",
     changeRole: "भूमिका बदलें",
     removeMember: "सदस्य हटाएँ",

package/dist/templates/default/app/i18n/ja-JP.ts

@@ -230,6 +230,8 @@ const messages = {
     newTerminal: "新しいターミナル",
     panelOptions: "エージェントパネルのオプション",
     collapseSidebar: "サイドバーを折りたたむ",
+    widenChat: "チャットを75%に広げる",
+    returnChatToLayout: "チャットをレイアウトに戻す",
     hideChats: "チャットを非表示にする",
     allChats: "すべてのチャット",
     settings: "設定",
@@ -466,6 +468,10 @@ const messages = {
     actions: "操作",
     noMembers: "メンバーはまだいません。",
     memberCount_other: "{{count}} members",
+    memberPagination: "メンバー一覧のページネーション",
+    previousMemberPage: "前のメンバーページへ移動",
+    nextMemberPage: "次のメンバーページへ移動",
+    memberPageStatus: "{{totalPages}}ページ中{{page}}ページ",
     youAreRole: "You are {{role}}",
     changeRole: "役割を変更する",
     removeMember: "メンバーの削除",

package/dist/templates/default/app/i18n/ko-KR.ts

@@ -225,6 +225,8 @@ const messages = {
     newTerminal: "새로운 터미널",
     panelOptions: "상담원 패널 옵션",
     collapseSidebar: "사이드바 접기",
+    widenChat: "채팅을 75% 너비로 넓히기",
+    returnChatToLayout: "채팅을 레이아웃으로 되돌리기",
     hideChats: "채팅 숨기기",
     allChats: "모든 채팅",
     settings: "설정",
@@ -458,6 +460,10 @@ const messages = {
     actions: "작업",
     noMembers: "아직 구성원이 없습니다.",
     memberCount_other: "{{count}} members",
+    memberPagination: "멤버 목록 페이지 매김",
+    previousMemberPage: "이전 멤버 페이지로 이동",
+    nextMemberPage: "다음 멤버 페이지로 이동",
+    memberPageStatus: "{{totalPages}}페이지 중 {{page}}페이지",
     youAreRole: "You are {{role}}",
     changeRole: "역할 변경",
     removeMember: "회원 삭제",

package/dist/templates/default/app/i18n/pt-BR.ts

@@ -234,6 +234,8 @@ const messages = {
     newTerminal: "Novo terminal",
     panelOptions: "Opções do painel do agente",
     collapseSidebar: "Recolher barra lateral",
+    widenChat: "Ampliar o chat para 75%",
+    returnChatToLayout: "Retornar o chat ao layout",
     hideChats: "Ocultar bate-papos",
     allChats: "Todos os bate-papos",
     settings: "Configurações",
@@ -478,6 +480,10 @@ const messages = {
     noMembers: "Ainda não há membros.",
     memberCount_one: "{{count}} member",
     memberCount_other: "{{count}} members",
+    memberPagination: "Paginação da lista de membros",
+    previousMemberPage: "Ir para a página anterior de membros",
+    nextMemberPage: "Ir para a próxima página de membros",
+    memberPageStatus: "Página {{page}} de {{totalPages}}",
     memberCount_many: "{{count}} members",
     youAreRole: "You are {{role}}",
     changeRole: "Mudar função",

package/dist/templates/default/app/i18n/zh-CN.ts

@@ -219,6 +219,8 @@ const messages = {
     newTerminal: "新航站楼",
     panelOptions: "代理面板选项",
     collapseSidebar: "收起侧边栏",
+    widenChat: "将聊天窗口加宽到 75%",
+    returnChatToLayout: "将聊天窗口恢复到布局中",
     hideChats: "隐藏聊天记录",
     allChats: "所有聊天记录",
     settings: "设置",
@@ -443,6 +445,10 @@ const messages = {
     actions: "操作",
     noMembers: "暂无成员。",
     memberCount_other: "{{count}} members",
+    memberPagination: "成员列表分页",
+    previousMemberPage: "转到上一页成员",
+    nextMemberPage: "转到下一页成员",
+    memberPageStatus: "第 {{page}} 页，共 {{totalPages}} 页",
     youAreRole: "You are {{role}}",
     changeRole: "改变角色",
     removeMember: "删除成员",

package/dist/templates/default/app/i18n/zh-TW.ts

@@ -217,6 +217,8 @@ const messages = {
     newTerminal: "新航站樓",
     panelOptions: "代理面板選項",
     collapseSidebar: "收起側邊欄",
+    widenChat: "將聊天視窗加寬至 75%",
+    returnChatToLayout: "將聊天視窗放回版面配置",
     hideChats: "隱藏聊天紀錄",
     allChats: "所有聊天紀錄",
     settings: "設定",
@@ -441,6 +443,10 @@ const messages = {
     actions: "操作",
     noMembers: "尚無成員。",
     memberCount_other: "{{count}} 位成員",
+    memberPagination: "成員列表分頁",
+    previousMemberPage: "前往上一頁成員",
+    nextMemberPage: "前往下一頁成員",
+    memberPageStatus: "第 {{page}} 頁，共 {{totalPages}} 頁",
     youAreRole: "你的角色是 {{role}}",
     changeRole: "改變角色",
     removeMember: "刪除成員",

package/dist/templates/headless/.agents/skills/actions/SKILL.md

@@ -20,6 +20,24 @@ Before creating any custom REST/API route for app data, inspect `actions/` and t
 
 **Stop trigger:** the moment you are about to create a file under `server/routes/api/` — or add server middleware to guard one — stop and check it against the exception list in *When You Still Need Custom `/api/` Routes* below. If it is not on that list, write a `defineAction` instead. This applies even when you already started the route; abandoning a half-written action to hand-roll routes is the exact failure this rule exists to prevent.
 
+## Keep actions deterministic and composable
+
+An action may call a provider API, validate or normalize data, and persist
+records without being an AI feature. Keep those operations deterministic,
+focused, and independently useful to the agent. Do not put LLM calls or a
+second model runtime in ordinary actions. The only narrow exception is the
+`completeText()` text-in/text-out escape hatch described in
+`delegate-to-agent`; it must not own tools, chat history, run state, side
+effects, or user steering.
+
+When a workflow is framed as research, analysis, generation, recommendation,
+or synthesis, or spans several provider calls and writes, route the user into
+the AgentSidebar and let the agent orchestrate focused actions. Do not hide an
+AI-shaped workflow behind one opaque `generate-*` or `create-*` action just
+because its implementation is deterministic. A visible user-initiated run
+should use `sendToAgentChat({ openSidebar: true })`, and its follow-ups should
+continue in the same thread rather than a separate freeform input.
+
 ## Why
 
 Actions give the agent callable tools with structured input/output, AND they give the frontend a typed client contract through hooks. One implementation serves both the agent and the UI. They keep the agent's chat context clean, they're reusable, and they can be tested independently.

package/dist/templates/headless/.agents/skills/agent-native-toolkit/SKILL.md

@@ -56,6 +56,11 @@ The repeated app shell has two distinct navigation surfaces:
   labeled as local, preview, or analyze. For original/generated review, stack
   the source above the result by default and use side-by-side only for short,
   highly scannable content.
+- Deterministic implementation does not make an AI-shaped experience
+  deterministic. If the user expects research, analysis, generation,
+  recommendation, synthesis, visible progress, or steering, route the button
+  to the AgentSidebar and let the agent call focused actions. Keep revisions in
+  the same thread instead of adding a second freeform prompt box.
 - Standalone apps with `AgentSidebar` must resolve one assistant-ui runtime
   context. Match direct assistant-ui pins to the installed core/toolkit peer
   graph, use Vite dedupe/aliases when linked dependencies can split contexts,

package/dist/templates/headless/.agents/skills/turn-into-app/SKILL.md

@@ -1,10 +1,10 @@
 ---
 name: turn-into-app
 description: >-
-  Turn a proven thread, skill, or workflow into a runnable Agent-Native app
-  with simple buttons, visible agent steps, preview, and deployment handoff.
-  Use when a user invokes `/turn-into-app` or asks to make a workflow into an
-  app.
+  Turn visible project context, a proven thread, skill, or workflow into a
+  runnable Agent-Native app with simple buttons, visible agent steps, preview,
+  and deployment handoff. Use when a user invokes `/turn-into-app` or asks to
+  make a workflow into an app.
 user-invocable: true
 scope: both
 metadata:
@@ -17,34 +17,72 @@ metadata:
 
 This is an end-to-end build skill, not a request for an app proposal.
 
-- With no argument, use the current thread as the source. This is the normal
-  invocation at the end of a successful workflow.
+- With no argument, choose the source in this order: visible project context,
+  then the current thread. A fresh Claude or ChatGPT Project is a valid source
+  on its first turn. Treat its visible project instructions, knowledge files,
+  and supplied past runs as the source; a completed thread is not required.
+  Treat the current turn as a request or configuration unless it contains a
+  concrete repeatable workflow.
 - With a named skill or local workflow, read that source and package it
   immediately, even at the beginning of a thread. For example,
   `/turn-into-app /some-skill` means “turn `/some-skill` into an app.”
 - With an attachment or path, read the supplied artifact as the source.
 - Do not ask the user to restate context that is already in the thread.
-- When invoked from an Agent-Native app, keep the current thread as the source
-  and use the available workspace/coding-agent handoff when the current runtime
-  cannot edit files. Do not claim the app exists without an actual path and
-  verification result.
+- When invoked from an Agent-Native app, use its visible project context first,
+  then the current thread, and use the available workspace/coding-agent
+  handoff when the current runtime cannot edit files. Do not claim the app
+  exists without an actual path and verification result.
 
 ## Source support
 
-Supported source paths today are the current Codex thread, a named skill, or a
-local workflow/transcript supplied as a path or attachment. An exported
-ChatGPT or Claude transcript can use the same local-file path today.
+Supported source paths today are visible Claude or ChatGPT Project context, the
+current Codex or host thread, a named skill, or a local workflow/transcript
+supplied as a path or attachment. An exported ChatGPT or Claude transcript can
+use the same local-file path today.
 
-ChatGPT shared-conversation import and Claude web conversation/project import
-are **coming soon**. Do not claim private web access, invent an importer, add
-fake OAuth, or scrape a logged-in page without an explicit supported adapter.
-If a user gives one of those URLs before an adapter exists, ask for an export or
-transcript instead and treat it as imported source material.
+Claude and ChatGPT Project context is supported only when the host supplies it
+to the model in the current context. The MCP connector does not read hidden
+project chats, private URLs, account settings, or credentials. Do not claim
+private web access, invent an importer, add fake OAuth, or scrape a logged-in
+page. If the needed context is not visible, ask for an export, transcript, or
+attachment and treat that artifact as imported source material.
 
 Deliver a fresh app in a new directory, implement the repeatable workflow with
 buttons and agent handoffs, start its dev server, verify the main path, and
 continue through build/deployment handoff. Do not stop at a plan.
 
+## Fresh project context mode
+
+When the source is a fresh Claude or ChatGPT Project, build a short source brief
+before creating the app. Read the host-provided context in this order:
+
+1. Project instructions and configuration: goal, audience, constraints, output
+   standards, approved tools, and integration expectations. Treat these as
+   product configuration, not as a transcript.
+2. Knowledge files and attachments: read the relevant files fully, preserve
+   their provenance, and reduce them to bounded references, IDs, URLs, or
+   summaries for the new app. Do not copy secrets or large raw payloads into
+   prompts or SQL.
+3. Past runs or examples that are actually visible in the context: select at
+   most 1-3 successful, representative runs. Extract repeatable decisions and
+   review criteria. Treat one-off answers and private data as examples, not as
+   product behavior. If no runs are supplied, proceed from the instructions
+   and knowledge files and say that examples were not available.
+4. The current turn: use it for the requested app boundary, target workspace,
+   naming, and any explicit corrections.
+
+Record the brief with these headings before handoff: source and provenance,
+project goal, configuration and constraints, knowledge sources, repeatable
+workflow, inputs and outputs, judgment and review points, representative runs,
+integrations and permissions, and unknowns. This is the compact contract for
+the app. It keeps the new app useful without pretending that hidden Project
+history was imported. See [the fresh Project reference](references/fresh-project.md)
+for the host setup and brief template.
+
+If the visible Project context has no concrete repeatable job, ask for one
+focused clarification or a representative artifact. Do not fall back to a
+generic “what app do you want to make?” builder.
+
 ## Source selection guard
 
 The generated app must implement the concrete workflow found in the source. It
@@ -151,6 +189,14 @@ pnpm exec agent-native add-app <slug> --template=chat
 Do not use `create` for an existing workspace; it scaffolds a new standalone
 workspace rather than adding an app to the current one.
 
+When the source came from a fresh external Project and the target is a Builder
+workspace, prefer the available Dispatch MCP workspace handoff after writing
+the source brief. Call `start-workspace-app-creation` with a concise prompt,
+the inferred app id, and the brief's repeatable workflow. Pass selected
+workspace resource IDs when they are available, rather than pasting entire
+knowledge files. Continue from the returned workspace path or Builder handoff
+and report the actual verification result.
+
 Use a first-party template only when it materially fits the workflow. Keep the
 new app independent from the source thread's working tree unless the user
 explicitly asks to extend an existing app.
@@ -167,13 +213,20 @@ should make the repeated path obvious without hiding the agent's judgment:
 - Give each important repeated moment a clear button, such as “Analyze,”
   “Suggest options,” “Draft,” “Review,” or “Publish.” Use the source's actual
   vocabulary when it is clear.
-- Put deterministic reads, writes, approvals, and publishing in `actions/`
-  with `defineAction`. The UI and agent must call the same action surface.
+- Put deterministic reads, writes, approvals, provider fetches, and publishing
+  in focused `actions/` with `defineAction`. The UI and agent must call the
+  same action surface.
+- If a workflow is framed as research, analysis, generation, recommendation,
+  or synthesis, start it in the AgentSidebar and let the agent orchestrate
+  those actions. Do not hide an AI-shaped multi-step workflow behind one
+  opaque action just because the implementation is deterministic.
 - Use application state for the current screen, selected item, and focused
   object so the agent can see where the user is.
-- Use `sendToAgentChat({ message, context, submit: true })` for intentional
-  button-triggered agent work. Use `submit: false` when the user should review
-  or edit the proposed prompt first.
+- Use `sendToAgentChat({ message, context, submit: true, openSidebar: true })`
+  for intentional button-triggered agent work. Use `submit: false` when the
+  user should review or edit the proposed prompt in the AgentSidebar first.
+  Keep follow-up and revision prompts in that same thread; do not add a second
+  freeform textbox beside the result.
 - Pass IDs, URLs, and bounded summaries in context. Do not paste large provider
   dumps into prompts, call an LLM directly from the browser, or invent fake
   progress.

package/dist/templates/headless/.agents/skills/turn-into-app/agents/openai.yaml

@@ -1,4 +1,4 @@
 interface:
   display_name: "Turn Into App"
-  short_description: "Turn a thread or skill into a runnable app"
-  default_prompt: "Scan the current thread, turn the workflow into a new Agent-Native app with clear buttons, run it locally, verify it, and complete the deployment handoff."
+  short_description: "Turn project context or a workflow into a runnable app"
+  default_prompt: "Use the visible project context first, then any supplied workflow. Turn the instructions, knowledge files, and selected successful runs into a new Agent-Native app with clear buttons, run it locally, verify it, and complete the deployment handoff."

package/dist/templates/headless/.agents/skills/turn-into-app/references/fresh-project.md

@@ -0,0 +1,64 @@
+# Fresh Project source guide
+
+Use this guide when `/turn-into-app` is invoked in a new Claude or ChatGPT
+Project rather than after a completed thread.
+
+## What the host can provide
+
+The source is whatever the host put in the model's current context:
+
+- Project instructions: the job, audience, constraints, quality bar, and
+  approved tools or integrations.
+- Knowledge files and attachments: reference material, templates, examples,
+  and links that the app should use.
+- Past runs: only conversations or outputs the host actually supplied. They
+  are examples and evaluation material, not an automatic import of every
+  private Project conversation.
+- The current request: the app boundary, target workspace, name, and explicit
+  corrections.
+
+Do not infer hidden system prompts, account settings, private history, API keys,
+or credentials. The Dispatch MCP connector can start a workspace app creation,
+but it cannot unlock or scrape private Project content.
+
+## Source brief
+
+Write a compact brief before starting the app:
+
+```text
+Source: host-provided Claude/ChatGPT Project context
+Provenance: project instructions, selected knowledge files, and visible runs
+Project goal:
+Configuration and constraints:
+Knowledge sources:
+Repeatable workflow:
+Inputs and outputs:
+Judgment and review points:
+Representative runs: none, or 1-3 selected examples
+Integrations and permissions:
+Unknowns and follow-up:
+```
+
+Keep source references bounded. Prefer a file name, URL, resource ID, or short
+summary over a large pasted document. Do not put secrets or raw customer data
+in the brief.
+
+## Fresh-box setup
+
+Install the exported `turn-into-app` skill in the host when the host supports
+skills. For a ChatGPT Project or any host that exposes only the MCP connector,
+also place the skill instructions or this reference in the Project
+instructions/knowledge files. Then add and authenticate the Dispatch MCP
+connector from the packaged `adapters/chatgpt-mcp/connector.json`.
+
+In a new Project chat, say:
+
+```text
+Turn this project into an app. Use the visible Project instructions,
+knowledge files, and any selected successful runs as the source. Create the
+app in the connected Agent-Native workspace, keep the source brief bounded,
+and report the real path and verification result.
+```
+
+If the host does not show the Project instructions or files to the model, stop
+and request an export or attachment. Do not claim that the Project was read.

package/dist/templates/workspace-core/.agents/skills/actions/SKILL.md

@@ -20,6 +20,24 @@ Before creating any custom REST/API route for app data, inspect `actions/` and t
 
 **Stop trigger:** the moment you are about to create a file under `server/routes/api/` — or add server middleware to guard one — stop and check it against the exception list in *When You Still Need Custom `/api/` Routes* below. If it is not on that list, write a `defineAction` instead. This applies even when you already started the route; abandoning a half-written action to hand-roll routes is the exact failure this rule exists to prevent.
 
+## Keep actions deterministic and composable
+
+An action may call a provider API, validate or normalize data, and persist
+records without being an AI feature. Keep those operations deterministic,
+focused, and independently useful to the agent. Do not put LLM calls or a
+second model runtime in ordinary actions. The only narrow exception is the
+`completeText()` text-in/text-out escape hatch described in
+`delegate-to-agent`; it must not own tools, chat history, run state, side
+effects, or user steering.
+
+When a workflow is framed as research, analysis, generation, recommendation,
+or synthesis, or spans several provider calls and writes, route the user into
+the AgentSidebar and let the agent orchestrate focused actions. Do not hide an
+AI-shaped workflow behind one opaque `generate-*` or `create-*` action just
+because its implementation is deterministic. A visible user-initiated run
+should use `sendToAgentChat({ openSidebar: true })`, and its follow-ups should
+continue in the same thread rather than a separate freeform input.
+
 ## Why
 
 Actions give the agent callable tools with structured input/output, AND they give the frontend a typed client contract through hooks. One implementation serves both the agent and the UI. They keep the agent's chat context clean, they're reusable, and they can be tested independently.

package/dist/templates/workspace-core/.agents/skills/agent-native-toolkit/SKILL.md

@@ -56,6 +56,11 @@ The repeated app shell has two distinct navigation surfaces:
   labeled as local, preview, or analyze. For original/generated review, stack
   the source above the result by default and use side-by-side only for short,
   highly scannable content.
+- Deterministic implementation does not make an AI-shaped experience
+  deterministic. If the user expects research, analysis, generation,
+  recommendation, synthesis, visible progress, or steering, route the button
+  to the AgentSidebar and let the agent call focused actions. Keep revisions in
+  the same thread instead of adding a second freeform prompt box.
 - Standalone apps with `AgentSidebar` must resolve one assistant-ui runtime
   context. Match direct assistant-ui pins to the installed core/toolkit peer
   graph, use Vite dedupe/aliases when linked dependencies can split contexts,