synabun 1.3.0 → 2.0.0-beta

package/skills/leonardo/SKILL.md

@@ -24,6 +24,15 @@ This is a **100% browser-based** workflow. Leonardo.ai runs in SynaBun's headed
 
 **Critical workflow:** Always configure settings (model, style, dimensions, etc.) BEFORE calling `leonardo_browser_generate`. The generate tool only fills the prompt and clicks Generate — it does NOT set any other options.
 
+## Runtime Compatibility
+
+- **Interactive choice prompt** means an interactive option card the user clicks — not plain text choices.
+  - **Claude Code (REQUIRED path):** `AskUserQuestion` is a deferred tool — its schema is not loaded by default. Before the first prompt in this skill, call `ToolSearch` with query `select:AskUserQuestion` to load it, then call `AskUserQuestion` with 2-4 options. NEVER write the choices as plain text — the sidepanel will render text as static markdown, not an interactive card.
+  - **OpenCode (REQUIRED path):** call the native `question` tool — the sidepanel renders it as an interactive card via the `/question.asked` event. NEVER write the choices as plain text.
+  - **Codex (REQUIRED path):** call `request_user_input` — the sidepanel renders it as an interactive card. NEVER write the choices as plain text.
+  - **Other runtimes:** only when no interactive tool exists, fall back to a concise plain-text multiple-choice question and wait for the user's reply.
+- **Load/read a module file** means: use whatever local file-reading mechanism exists in the current runtime. Do not depend on a tool literally being named `Read`.
+
 ---
 
 ## Step 1 — Route or Quick Mode
@@ -42,7 +51,7 @@ Parse `$ARGUMENTS` to determine the path:
 
 **Interactive menu** (args empty or unrecognized):
 
-Use `AskUserQuestion` with options:
+Use an interactive choice prompt with options:
 
 - **Create Video** — "Expert-guided video creation with full control over models, motion, styles, and prompt engineering"
 - **Create Image** — "Expert-guided image creation with model selection, style presets, dimensions, and prompt engineering"
@@ -53,21 +62,21 @@ Use `AskUserQuestion` with options:
 
 ## Step 2a — Video Prompter
 
-Read the video prompter module:
+Load/read the video prompter module:
 ```
-Read $SKILL_DIR/modules/video-prompter.md
+Load/read $SKILL_DIR/modules/video-prompter.md
 ```
-Follow that module's instructions completely. It will guide you through a comprehensive questionnaire using `AskUserQuestion`, covering: concept, model selection, motion controls, motion elements, style stacking (Vibe + Lighting + Color Theme), dimensions, prompt enhancement, negative prompt, and more. When the module produces final parameters, proceed to **Step 3: Execute**.
+Follow that module's instructions completely. It will guide you through a comprehensive questionnaire using interactive choice prompts, covering: concept, model selection, motion controls, motion elements, style stacking (Vibe + Lighting + Color Theme), dimensions, prompt enhancement, negative prompt, and more. When the module produces final parameters, proceed to **Step 3: Execute**.
 
 ---
 
 ## Step 2b — Image Prompter
 
-Read the image prompter module:
+Load/read the image prompter module:
 ```
-Read $SKILL_DIR/modules/image-prompter.md
+Load/read $SKILL_DIR/modules/image-prompter.md
 ```
-Follow that module's instructions completely. It will guide you through a comprehensive questionnaire using `AskUserQuestion`, covering: concept, model selection, style preset, dimensions, number of images, and prompt engineering. When the module produces final parameters, proceed to **Step 3: Execute**.
+Follow that module's instructions completely. It will guide you through a comprehensive questionnaire using interactive choice prompts, covering: concept, model selection, style preset, dimensions, number of images, and prompt engineering. When the module produces final parameters, proceed to **Step 3: Execute**.
 
 ---
 
@@ -101,9 +110,9 @@ browser_snapshot
 
 ### 3c. Configure ALL settings in the UI
 
-Read the browser guide module for detailed UI navigation instructions:
+Load/read the browser guide module for detailed UI navigation instructions:
 ```
-Read $SKILL_DIR/modules/browser-guide.md
+Load/read $SKILL_DIR/modules/browser-guide.md
 ```
 
 Follow the browser guide to set each parameter via `browser_click`, `browser_fill`, `browser_evaluate`, etc. The guide maps every setting to its UI element.
@@ -142,7 +151,7 @@ browser_wait timeout: 10000
 browser_screenshot
 ```
 
-Show the user the results and offer follow-up actions via `AskUserQuestion`:
+Show the user the results and offer follow-up actions via an interactive choice prompt:
 
 - **Generate Again** — "Same settings, new generation"
 - **Modify & Regenerate** — "Tweak the prompt or settings"

package/skills/leonardo/modules/image-prompter.md

@@ -1,16 +1,22 @@
 # Image Prompter — Guided Questionnaire
 
-Guide the user through creating the perfect image on Leonardo.ai. Ask questions using `AskUserQuestion`, then engineer the optimal prompt and configure all browser settings.
+Guide the user through creating the perfect image on Leonardo.ai. Ask questions using an interactive choice prompt, then engineer the optimal prompt and configure all browser settings.
 
 **Important:** This is a browser-based workflow. After the questionnaire, you'll set all parameters in the Leonardo.ai UI using browser tools, then fill the prompt and click Generate.
 
+**Runtime compatibility:** An **interactive choice prompt** means an interactive option card the user clicks — not plain text choices.
+- **Claude Code (REQUIRED path):** `AskUserQuestion` is a deferred tool — its schema is not loaded by default. Before the first prompt in this skill, call `ToolSearch` with query `select:AskUserQuestion` to load it, then call `AskUserQuestion` with 2-4 options. NEVER write the choices as plain text — the sidepanel will render text as static markdown, not an interactive card.
+- **OpenCode (REQUIRED path):** call the native `question` tool — the sidepanel renders it as an interactive card via the `/question.asked` event. NEVER write the choices as plain text.
+- **Codex (REQUIRED path):** call `request_user_input` — the sidepanel renders it as an interactive card. NEVER write the choices as plain text.
+- **Other runtimes:** only when no interactive tool exists, fall back to a concise plain-text multiple-choice question and wait for the user's reply.
+
 ---
 
 ## Phase 1 — Vision (What do you want to create?)
 
 Ask the user to describe their image concept. If `$TOPIC` was set by the router, use it as the starting point and skip asking — but still categorize it.
 
-**Do NOT use AskUserQuestion here** — this requires free-text input. Output a natural chat message:
+**Do NOT use an interactive choice prompt here** — this requires free-text input. Output a natural chat message:
 
 > **What kind of image do you want to create?**
 > Describe your vision — subject, scene, mood, purpose. You can also paste or drag reference images for inspiration.
@@ -32,7 +38,7 @@ Store as `$CATEGORY`.
 
 ## Phase 2 — Model Selection
 
-Present model options based on `$CATEGORY`. Use `AskUserQuestion`:
+Present model options based on `$CATEGORY`. Use an interactive choice prompt:
 
 > **Which image model should we use?**
 
@@ -69,7 +75,7 @@ Store as `$MODEL`.
 
 Check if the user attached images with their **current message** (file paths appear at the top of the prompt). Do NOT check `image_staged` here — old staged images are not reference candidates.
 
-**If images are attached to the current message**, present options based on the selected model's capabilities. Use `AskUserQuestion`:
+**If images are attached to the current message**, present options based on the selected model's capabilities. Use an interactive choice prompt:
 
 > **You have N reference image(s) available. How should Leonardo use them?**
 
@@ -90,7 +96,7 @@ Store as `$REFERENCE_TYPE` and `$REFERENCE_PATHS`.
 
 **If no images are attached**, ask the user if they'd like to use reference images. First check if `$MODEL` supports any reference types from the table above — if it supports NONE, skip this phase silently.
 
-If the model supports at least one reference type, use `AskUserQuestion`:
+If the model supports at least one reference type, use an interactive choice prompt:
 
 > **Would you like to use reference images?**
 > Reference images let Leonardo match a style, composition, or visual from an existing image.
@@ -98,7 +104,7 @@ If the model supports at least one reference type, use `AskUserQuestion`:
 - **Yes** — "I have images I'd like to use as reference"
 - **No** — "Continue without reference images"
 
-If **Yes**, respond with this message (plain text, not AskUserQuestion):
+If **Yes**, respond with this message (plain text, not an interactive choice prompt):
 
 > **Attach your reference image(s) to the chat.**
 > Copy the message below, paste it in the input box, attach your images, and send:
@@ -114,7 +120,7 @@ If **No**, continue to Phase 3.
 
 ## Phase 3 — Style Preset
 
-Use `AskUserQuestion`:
+Use an interactive choice prompt:
 
 > **What visual style do you want?**
 
@@ -148,7 +154,7 @@ Store as `$STYLE`.
 
 ## Phase 4 — Dimensions & Composition
 
-Use `AskUserQuestion`:
+Use an interactive choice prompt:
 
 > **What dimensions/aspect ratio?**
 
@@ -169,7 +175,7 @@ Store as `$DIMENSIONS`.
 
 ## Phase 5 — Quantity & Details
 
-Use `AskUserQuestion`:
+Use an interactive choice prompt:
 
 > **How many images do you want?**
 
@@ -186,7 +192,7 @@ Store as `$NUM_IMAGES`.
 
 You've gathered all the technical settings. Now get the user's **detailed creative vision** before engineering the prompt.
 
-**Do NOT use AskUserQuestion here** — this requires free-text input. Output a natural chat message summarizing the config and asking for the detailed description:
+**Do NOT use an interactive choice prompt here** — this requires free-text input. Output a natural chat message summarizing the config and asking for the detailed description:
 
 > **Here's your setup:**
 > - **Model:** $MODEL
@@ -243,13 +249,13 @@ Using `$CREATIVE_BRIEF` from Phase 5.5 and all style context, craft the perfect
 > ```
 > [If negative prompt: **Negative:** `[negative prompt]`]
 
-Then use `AskUserQuestion` for review:
+Then use an interactive choice prompt for review:
 > **How does this prompt look?**
 - **Looks good — generate** — "Use this prompt as-is and proceed to generation"
 - **Tweak it** — "I want to adjust the prompt before generating"
 - **Rewrite it** — "Start the prompt from scratch with different direction"
 
-If **Tweak it**: ask what they want changed (plain text, not AskUserQuestion), apply changes, show the updated prompt, and ask again.
+If **Tweak it**: ask what they want changed (plain text, not an interactive choice prompt), apply changes, show the updated prompt, and ask again.
 If **Rewrite it**: ask for new direction (plain text), re-engineer from scratch, show the new prompt, and ask again.
 
 ### Build negative prompt (if applicable)

package/skills/leonardo/modules/video-prompter.md

@@ -1,16 +1,22 @@
 # Video Prompter — Guided Questionnaire
 
-Guide the user through creating the perfect video on Leonardo.ai. Ask questions using `AskUserQuestion`, then engineer the optimal prompt and configure all browser settings.
+Guide the user through creating the perfect video on Leonardo.ai. Ask questions using an interactive choice prompt, then engineer the optimal prompt and configure all browser settings.
 
 **Important:** This is a browser-based workflow. After the questionnaire, you'll set all parameters in the Leonardo.ai UI using browser tools, then fill the prompt and click Generate.
 
+**Runtime compatibility:** An **interactive choice prompt** means an interactive option card the user clicks — not plain text choices.
+- **Claude Code (REQUIRED path):** `AskUserQuestion` is a deferred tool — its schema is not loaded by default. Before the first prompt in this skill, call `ToolSearch` with query `select:AskUserQuestion` to load it, then call `AskUserQuestion` with 2-4 options. NEVER write the choices as plain text — the sidepanel will render text as static markdown, not an interactive card.
+- **OpenCode (REQUIRED path):** call the native `question` tool — the sidepanel renders it as an interactive card via the `/question.asked` event. NEVER write the choices as plain text.
+- **Codex (REQUIRED path):** call `request_user_input` — the sidepanel renders it as an interactive card. NEVER write the choices as plain text.
+- **Other runtimes:** only when no interactive tool exists, fall back to a concise plain-text multiple-choice question and wait for the user's reply.
+
 ---
 
 ## Phase 1 — Vision (What do you want to create?)
 
 Ask the user to describe their video concept. If `$TOPIC` was set by the router, use it as the starting point and skip asking — but still categorize it.
 
-**Do NOT use AskUserQuestion here** — this requires free-text input. Output a natural chat message:
+**Do NOT use an interactive choice prompt here** — this requires free-text input. Output a natural chat message:
 
 > **What kind of video do you want to create?**
 > Describe your vision — what happens in the scene, what's the mood, what's the purpose? You can also paste or drag reference images for inspiration.
@@ -31,7 +37,7 @@ Store as `$CATEGORY`. This informs model and style recommendations.
 
 ## Phase 2 — Model Selection
 
-Present model options based on the user's concept and budget tolerance. Use `AskUserQuestion`:
+Present model options based on the user's concept and budget tolerance. Use an interactive choice prompt:
 
 > **Which video model should we use?**
 
@@ -70,7 +76,7 @@ Store as `$MODEL`.
 
 Check if the user attached images with their **current message** (file paths appear at the top of the prompt). Do NOT check `image_staged` here — old staged images are not reference candidates.
 
-**If images are attached to the current message**, present options based on the selected model's capabilities. Use `AskUserQuestion`:
+**If images are attached to the current message**, present options based on the selected model's capabilities. Use an interactive choice prompt:
 
 > **You have N reference image(s) available. How should Leonardo use them?**
 
@@ -85,7 +91,7 @@ Options — show ONLY those supported by `$MODEL` (see model-advisor.md video ca
 
 Store as `$START_FRAME`, `$END_FRAME`, `$REFERENCE_TYPE`, `$REFERENCE_PATHS`.
 
-**If no images are attached**, ask the user if they'd like to use reference images or frames. Use `AskUserQuestion`:
+**If no images are attached**, ask the user if they'd like to use reference images or frames. Use an interactive choice prompt:
 
 > **Would you like to use reference images or start/end frames?**
 > You can provide an image to use as a starting frame, ending frame, or visual reference for the video.
@@ -93,7 +99,7 @@ Store as `$START_FRAME`, `$END_FRAME`, `$REFERENCE_TYPE`, `$REFERENCE_PATHS`.
 - **Yes** — "I have images I'd like to use"
 - **No** — "Continue without reference images"
 
-If **Yes**, respond with this message (plain text, not AskUserQuestion):
+If **Yes**, respond with this message (plain text, not an interactive choice prompt):
 
 > **Attach your reference image(s) to the chat.**
 > Copy the message below, paste it in the input box, attach your images, and send:
@@ -109,7 +115,7 @@ If **No**, continue to Phase 3.
 
 ## Phase 3 — Motion Control (Motion 2.0 / Fast only)
 
-Use `AskUserQuestion`:
+Use an interactive choice prompt:
 
 > **What camera movement do you want?**
 
@@ -136,7 +142,7 @@ Store as `$MOTION_CONTROL`.
 
 ## Phase 4 — Motion Elements (Motion 2.0 / Fast only)
 
-Use `AskUserQuestion`:
+Use an interactive choice prompt:
 
 > **Want to add a creative style overlay?**
 > Motion Elements add artistic filters to the entire video — like shooting through a specific visual lens.
@@ -158,7 +164,7 @@ Store as `$MOTION_ELEMENT`.
 
 Style stacking lets you layer up to 3 styles: one Vibe + one Lighting + one Color Theme.
 
-Use `AskUserQuestion`:
+Use an interactive choice prompt:
 
 > **Style Stacking — Layer up to 3 styles for the perfect look.**
 > Pick one from each category, or skip any.
@@ -194,7 +200,7 @@ Store as `$STYLE_VIBE`, `$STYLE_LIGHTING`, `$STYLE_COLOR`.
 
 ## Phase 6 — Technical Settings
 
-Use `AskUserQuestion`:
+Use an interactive choice prompt:
 
 > **Technical settings:**
 
@@ -217,7 +223,7 @@ Store all as: `$DIMENSIONS`, `$PROMPT_ENHANCE`, `$NUM_GENERATIONS`, `$NEGATIVE_P
 
 You've gathered all the technical settings. Now get the user's **detailed creative vision** before engineering the prompt.
 
-**Do NOT use AskUserQuestion here** — this requires free-text input. Output a natural chat message summarizing the config and asking for the detailed description:
+**Do NOT use an interactive choice prompt here** — this requires free-text input. Output a natural chat message summarizing the config and asking for the detailed description:
 
 > **Here's your setup:**
 > - **Model:** $MODEL
@@ -272,13 +278,13 @@ Using `$CREATIVE_BRIEF` from Phase 6.5, the motion control from Phase 3, and all
 > ```
 > [If negative prompt: **Negative:** `[negative prompt]`]
 
-Then use `AskUserQuestion` for review:
+Then use an interactive choice prompt for review:
 > **How does this prompt look?**
 - **Looks good — generate** — "Use this prompt as-is and proceed to generation"
 - **Tweak it** — "I want to adjust the prompt before generating"
 - **Rewrite it** — "Start the prompt from scratch with different direction"
 
-If **Tweak it**: ask what they want changed (plain text, not AskUserQuestion), apply changes, show the updated prompt, and ask again.
+If **Tweak it**: ask what they want changed (plain text, not an interactive choice prompt), apply changes, show the updated prompt, and ask again.
 If **Rewrite it**: ask for new direction (plain text), re-engineer from scratch, show the new prompt, and ask again.
 
 ### Build negative prompt (if enabled)