@remixmate/cli 0.9.15 → 0.9.16

package/README.md

@@ -296,7 +296,7 @@ remixmate template-registry --list-templates
 ### Quick start
 
 ```
-@skills/gen-image/SKILL.md Generate an image of a panda, 9:16, using gemini 3.1, Chinese-painting style + follow this doc strictly
+@skills/gen-image/SKILL.md Generate an image of a panda, 9:16, using gemini, Chinese-painting style + follow this doc strictly
 @skills/gen-video/SKILL.md Generate a video of a panda running in a bamboo forest, 9:16, 6 seconds, using veo + follow this doc strictly
 @skills/gen-voice/SKILL.md Generate a voiceover introducing panda habits, around 100 words + follow this doc strictly
 @skills/gen-digital-human/SKILL.md Get the digital human list + follow this doc strictly

package/README.zh-CN.md

@@ -232,7 +232,7 @@ remixmate template-registry --list-templates
 ### 快速体验
 
 ```
-@skills/gen-image/SKILL.md 生成一张熊猫的图片，9:16，调用gemini 3.1，国画风 + 严格按该文档执行
+@skills/gen-image/SKILL.md 生成一张熊猫的图片，9:16，调用gemini，国画风 + 严格按该文档执行
 @skills/gen-video/SKILL.md 生成一段熊猫在竹林奔跑的视频，9:16，长度6秒，调用veo + 严格按该文档执行
 @skills/gen-voice/SKILL.md 生成一段语音，介绍熊猫的习性，大概100字左右 + 严格按该文档执行
 @skills/gen-digital-human/SKILL.md 获取数字人列表 + 严格按该文档执行

package/dist/capabilities.d.ts

@@ -19,8 +19,12 @@ export interface ModelConstraints {
     durationDefault?: number;
     refImageMax?: number;
     sizes?: string[];
-    /** aspect-ratio → [width, height] pixel preset (Seedream). */
+    /** aspect-ratio → [width, height] pixel preset (Seedream). Per model: the same
+     *  ratio maps to different pixels on different Seedream variants. */
     sizePresets?: Record<string, [number, number]>;
+    /** total-pixel bounds (width × height); the backend rescales sizes outside them. */
+    pixelMin?: number;
+    pixelMax?: number;
 }
 export interface ModelDescriptor {
     id: string;

package/dist/manifest.json

@@ -1,7 +1,7 @@
 {
   "schemaVersion": 1,
-  "version": "0.9.15",
-  "generatedAt": "2026-08-14T08:23:17.130Z",
+  "version": "0.9.16",
+  "generatedAt": "2026-08-18T05:34:36.073Z",
   "skills": [
     {
       "id": "export-jianying",
@@ -54,7 +54,7 @@
       "tier": "atomic",
       "category": "asset",
       "title": "AI Image Generation",
-      "summary": "AI image generation: produce an image from a text prompt. Supports Seedream and Gemini models, plus image-to-image with reference images.",
+      "summary": "AI image generation: produce an image from a text prompt. Supports the Seedream family (including a high-fidelity 'pro' variant) and Gemini, plus image-to-image with reference images.",
       "triggers": [
         "AI image generation, text-to-image, \"draw me ...\", \"generate an image of ...\"",
         "Image-to-image, reference image, style transfer, image variation",
@@ -247,11 +247,11 @@
       "title": "Web Page Recording",
       "summary": "Drive a headless browser (Playwright Python) to RECORD any URL to a video, then (by default) transcode to mp4, grab a cover frame, upload to VOD and return a playable CDN URL. Modes: fixed-duration recording, condition-triggered stop (element appears / disappears), auto-scroll from top to bottom, custom storyboards, and parameterized templates. Storyboard scenes: highlight / focus / zoom / scroll / virtual-cursor click / type / hover / caption / title-card / arrow / numbered sequence / redact / code-line highlight. For still images (png/jpg) use the web_screenshot tool instead. Use this tool whenever the user wants a video / recording / screencast of a web page: record a page, scroll-through video, page-from-top-to-bottom clip, demo of clicks/typing/hover, storyboard / multi-scene intro video, or a template-based clip.",
       "triggers": [
-        "录屏、网页录制、录制视频、录一段操作、生成 webm、screencast",
-        "滚动录屏、页面从头划到尾的视频",
-        "多场景视频、分镜视频、storyboard、按时间线编排",
-        "演示点击 / 输入 / 悬停（虚拟鼠标 + 涟漪 / 打字机 / 触发 tooltip）",
-        "模板视频一行出片、按顺序编号高亮多个区域并录制"
+        "Screen recording, record a web page, record a video, capture an interaction, produce a webm, screencast",
+        "Scroll recording, a video that pans the page from top to bottom",
+        "Multi-scene video, storyboard video, timeline-sequenced clips",
+        "Animated demos of clicks / typing / hover (virtual cursor + ripple / typewriter / triggering tooltips)",
+        "One-command template clips, numbering and highlighting several regions in sequence and recording it"
       ],
       "entry": {
         "type": "python",
@@ -275,11 +275,11 @@
       "title": "Web Page Screenshot",
       "summary": "Drive a headless browser (Playwright Python) to capture any URL to a local STILL IMAGE (png/jpg): full-page / viewport / element / region screenshots, with device emulation, waiting, hide/mask/redact, and static annotations (highlight / arrow / caption / numbered sequence / redact). Images only — for video / recording / scroll-through / storyboard clips (webm) use the web_record tool instead.",
       "triggers": [
-        "网页截图、网页截屏、整页截图、长截图、full page screenshot",
-        "截某个元素 / 区域、局部截屏、focus 某个区域",
-        "截图前隐藏元素 / 涂盖打码、给静态截图加注释（红框 / 箭头 / 标签）",
-        "高亮某文件的 L5-L20 代码行并截图",
-        "移动端 / 设备模拟截图、带 cookie / 登录态截图"
+        "Web page screenshot, screen capture, full-page screenshot, long screenshot",
+        "Capture a specific element / region, partial screenshot, focus on an area",
+        "Hide or mask elements before capturing, annotate a still screenshot (highlight box / arrow / label)",
+        "Highlight lines L5-L20 of a file and screenshot it",
+        "Mobile / device-emulated screenshot, capture with cookies / a logged-in session"
       ],
       "entry": {
         "type": "python",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@remixmate/cli",
-  "version": "0.9.15",
+  "version": "0.9.16",
   "description": "AI media generation skills for Claude Code / Codex — 12 skills covering image, video, voice, digital human, web screenshot, web recording, script, template registry, rendering, Jianying export, and video deconstruction.",
   "type": "module",
   "main": "dist/index.js",

package/skills/export-jianying/version.json

@@ -3,5 +3,5 @@
   "repoName": "agent-skill-media-maker",
   "skillId": "554",
   "version": "V3",
-  "skillDescription": "剪映草稿生成技能，将素材URL打包为剪映可导入的草稿ZIP，支持从 RenderPlan 自动转换（调用 ab-api /file/generateJianYing）。\n\n当用户提到以下任何需求时，立即使用本 skill：\n- 导出剪映、剪映草稿、打包剪映、导入剪映\n- 将素材导出为剪映格式、生成剪映工程\n- 把视频/图片/音频打包成剪映草稿\n- 从 RenderPlan 导出剪映草稿\n\n即使用户没有明确说「剪映」，只要他们想要将素材打包为可在剪映中编辑的草稿格式，也要使用本 skill。"
+  "skillDescription": "Jianying (CapCut) draft-generation skill. Packages asset URLs into a draft ZIP that Jianying can import; supports automatic conversion from a RenderPlan (calls ab-api /file/generateJianYing).\n\nUse this skill as soon as the user mentions any of these intents:\n- Export to Jianying, Jianying draft, package for Jianying, import into Jianying\n- Export materials to the Jianying format, generate a Jianying project\n- Bundle video / image / audio into a Jianying draft\n- Export a Jianying draft from a RenderPlan\n\nEven when the user does not say \"Jianying\" explicitly, use this skill whenever they want to package materials into a draft that can be edited in Jianying."
 }

package/skills/gen-digital-human/skill.json

@@ -12,13 +12,19 @@
     "type": "object",
     "properties": {
       "list_avatars": { "type": "boolean", "description": "List available digital-human avatars" },
-      "source": { "type": "string", "enum": ["jimeng", "hifly"], "description": "Filter by source" },
+      "mine": { "type": "boolean", "description": "With list_avatars=true: list the caller's own custom avatars instead of the public catalog. Custom avatars do not appear without this." },
+      "name": { "type": "string", "description": "With list_avatars=true: fuzzy-filter avatars by name" },
+      "source": { "type": "string", "enum": ["jimeng", "hifly"], "description": "Provider: jimeng is image-driven, hifly is video-driven. Usually inferred from the avatar; pass it explicitly when the avatar declares no source." },
       "gender": { "type": "string", "enum": ["male", "female"], "description": "Filter by gender" },
       "avatar_id": { "type": "number", "description": "Avatar id" },
       "text": { "type": "string", "description": "Narration text (TTS mode)" },
       "audio_url": { "type": "string", "description": "Audio URL (audio-driven mode)" },
-      "voice_id": { "type": "string", "description": "Voice id" },
-      "aspect_ratio": { "type": "string", "description": "Aspect ratio" },
+      "voice_id": { "type": "string", "description": "Voice id (TTS mode). Shares the Minimax catalog with gen-voice — call gen_voice with list_voices=true to see available ids rather than inventing one." },
+      "voice_name": { "type": "string", "description": "Voice display name, recorded alongside voice_id for bookkeeping. Does not affect synthesis." },
+      "aspect_ratio": { "type": "string", "description": "Aspect ratio: 9:16 / 16:9 / 3:4 / 1:1. Defaults to the avatar's own ratio." },
+      "prompt": { "type": "string", "description": "Action prompt describing how the avatar should perform, e.g. 'more hand gestures'" },
+      "check_status": { "type": "boolean", "description": "Status-check mode: poll an earlier job instead of starting a new one. Requires generation_id. Use this when a generate call timed out." },
+      "generation_id": { "type": "number", "description": "Job id to poll (required when check_status=true)" },
       "json_output": { "type": "boolean", "description": "Emit a JSON result (generate: { url, generationId }; list: { avatars }; check-status: { status, url }) instead of human-readable output" }
     },
     "required": []

package/skills/gen-digital-human/version.json

@@ -3,5 +3,5 @@
   "repoName": "agent-skill-media-maker",
   "skillId": "336",
   "version": "V8",
-  "skillDescription": "数字人口播视频技能，支持查询形象、TTS 口播、音频驱动口播和查询生成状态（调用 ab-api 数字人接口，即梦 / 飞影）。\n\n当用户提到以下任何需求时，立即使用本 skill：\n- 数字人、数字人视频、数字人口播、生成数字人视频\n- 用户提供已有音频 URL（MP3 等）、用外链音频驱动数字人口型\n- AI 主播、虚拟主播、虚拟人物视频、口播视频\n- 让数字人说话、让虚拟人说一段话、让 AI 人物播报\n- 查看/列出数字人形象、有哪些数字人可以用\n- 使用即梦/飞影数字人\n\n即使用户没有明确说「使用 AI」，只要他们想要让一个虚拟人物朗读/播报一段文字并生成视频，也要使用本 skill。"
+  "skillDescription": "Digital-human (talking-head) skill: list available avatars, run TTS-based or audio-driven lip-sync, and check the status of pending jobs. Backed by ab-api's digital-human endpoints (Jimeng / HiFly providers).\n\nUse this skill immediately whenever the user asks for any of:\n- Digital human, talking-head video, AI presenter, virtual host\n- \"Make a talking-head video out of this script / this audio file\"\n- List or browse digital-human avatars\n- Use Jimeng or HiFly to drive an avatar\n\nEven without an explicit \"use AI\", any request that turns text or audio into a synthesized presenter video should route here."
 }

package/skills/gen-image/SKILL.md

@@ -23,21 +23,28 @@ Wraps ab-api's `POST /model/genImg` (the same endpoint the web studio uses), aut
 
 ## Models and sizes
 
-Aligned with the gen-image handler's model presets and the backend `ModelGenImgDTO`:
-
-| LiteLLM `model` | Display name | Provider |
-|-----------------|--------------|----------|
-| `doubao/doubao-seedream-4-5-251128` | Seedream 4.5 | Volcano |
-| `doubao/doubao-seedream-5-0-260128` | Seedream 5.0 Lite | Volcano |
-| `gemini-3-pro-image` | Gemini 3 Pro | Google |
-| `gemini-3.1-flash-image-preview` | Gemini 3.1 Flash | Google |
-
-- **Seedream**: `--size` is an aspect ratio (e.g. `1:1`, `9:16`) or `WxH`; the backend may auto-upscale the 4.5 model to meet a minimum pixel count.
-- **Gemini**: `--size` is a backend-allowed aspect ratio (e.g. `1:1`, `16:9`); add `--resolution`: `1K` / `2K` / `4K` (default `1K`).
+Pass `--model` a short name. The authoritative roster — ids, aliases, per-model limits —
+lives in the backend catalog (`/model/capabilities`), which the CLI fetches at runtime;
+the names below are the stable aliases to use.
+
+| `--model` | What it is | Reference images |
+|-----------|------------|------------------|
+| `seedream` | Default. General-purpose, highest output resolution. | up to 14 |
+| `seedream-pro` | High-fidelity variant: better placement/element control, more faithful text rendering. Costs more per image. | up to 10 |
+| `gemini` | Gemini 3 Pro. | up to 4 |
+
+- **Seedream**: `--size` is an aspect ratio (e.g. `1:1`, `9:16`) or `WxH`. The backend maps the
+  ratio to that model's own pixel preset and rescales out-of-range sizes, so prefer a ratio
+  over explicit pixels.
+- **`seedream-pro`** additionally supports `3:2` / `2:3` / `21:9`, and caps output at ~2K
+  (about 4.6 MP). Asking it for 4K pixels gets scaled down, not rejected — use `seedream`
+  when you need a genuinely larger image.
+- **Gemini**: `--size` is a backend-allowed aspect ratio (e.g. `1:1`, `16:9`); add
+  `--resolution`: `1K` / `2K` / `4K` (default `1K`). `--resolution` is ignored by Seedream.
 
 ## Auth & environment
 
-No skill-local env file — the executing process inherits the system environment. Examples say `python`; on macOS you may need `python3`.
+No skill-local env file — the executing process inherits the system environment.
 
 - **Enterprise OpenClaw**: auth is already injected, **no need** for `PRIV_TOKEN` / `--priv-token`.
 - **Other environments**: configure the token. Without a token, non-interactive runs fail; interactive ones may prompt.
@@ -45,7 +52,7 @@ No skill-local env file — the executing process inherits the system environmen
 | Env var | Description | Default |
 |---------|-------------|---------|
 | `PRIV_TOKEN` | Tianyan token; `--priv-token` overrides | none |
-| `MM_IMAGE_MODEL` | Default model id | `doubao/doubao-seedream-4-5-251128` |
+| `MM_IMAGE_MODEL` | Default model, as a `--model` value | backend default (`seedream`) |
 | `MM_API_BASE_URL` | API root; `--api-base-url` overrides | `https://api.remixmate.com/api` |
 | `AGENT_NAME` | Optional `x-invoke-agent` header | none |
 
@@ -67,17 +74,30 @@ remixmate gen-image \
 ```bash
 remixmate gen-image \
   --prompt "<image description>" \
-  --model gemini-3-pro-image \
+  --model gemini \
   --size "16:9" \
   --resolution "2K"
 ```
 
+```bash
+# High-fidelity: precise placement, legible on-image text
+remixmate gen-image \
+  --prompt "<image description>" \
+  --model seedream-pro \
+  --size "16:9"
+```
+
 ### Image-to-image (reference image)
 
 Reference images accept local file paths, HTTPS URLs, or data URIs. Pass `--reference` multiple times for multiple references.
 
-- **Seedream**: up to **14** reference images, `--image-strength` controls reference influence.
-- **Gemini**: up to **4** reference images.
+- **`seedream`**: up to **14** reference images, `--image-strength` controls reference influence.
+- **`seedream-pro`**: up to **10** reference images. Best choice when the edit has to land in a
+  specific spot — describe the target region in the prompt (e.g. "in the marked area at the
+  bottom left") and it holds position far better than `seedream`.
+- **`gemini`**: up to **4** reference images.
+
+Over-the-limit runs fail fast in the CLI, before spending credits.
 
 ```bash
 # URL reference
@@ -109,7 +129,7 @@ remixmate gen-image \
 | Flag | Description | Default |
 |------|-------------|---------|
 | `-p` / `--prompt` | Description (required) | — |
-| `-m` / `--model` | Model id | see `MM_IMAGE_MODEL` |
+| `-m` / `--model` | `seedream` / `seedream-pro` / `gemini` | see `MM_IMAGE_MODEL` |
 | `-s` / `--size` | Seedream: ratio or WxH; Gemini: ratio | `1:1` |
 | `--resolution` | Gemini only: `1K` / `2K` / `4K` | `1K` |
 | `-n` | Number of images, 1–4 | `1` |
@@ -124,7 +144,9 @@ remixmate gen-image \
 
 ## Credits
 
-Every run charges credits. The CLI prints a footer on stdout when it does:
+Every run charges credits, per image and **per model** — `seedream-pro` costs noticeably more
+per image than `seedream`, so don't reach for it by default. The CLI prints a footer on stdout
+when it charges:
 
 ```
 💳 Charged 31 credits · balance 1,240

package/skills/gen-image/skill.json

@@ -4,7 +4,7 @@
   "tier": "atomic",
   "category": "asset",
   "title": "AI Image Generation",
-  "description": "AI image generation: produce an image from a text prompt. Supports Seedream and Gemini models, plus image-to-image with reference images.",
+  "description": "AI image generation: produce an image from a text prompt. Supports the Seedream family (including a high-fidelity 'pro' variant) and Gemini, plus image-to-image with reference images.",
   "auth": "required",
   "envVars": ["PRIV_TOKEN", "MM_API_BASE_URL", "AGENT_NAME", "MM_IMAGE_MODEL"],
   "entry": { "type": "http", "handler": "gen-image" },
@@ -12,12 +12,20 @@
     "type": "object",
     "properties": {
       "prompt": { "type": "string", "description": "Image description (required)" },
-      "model": { "type": "string", "description": "Model id" },
+      "model": { "type": "string", "description": "Model: 'seedream' (default), 'seedream-pro' (high fidelity, precise placement and on-image text; costs more per image), or 'gemini'" },
       "size": { "type": "string", "description": "Aspect ratio or WxH, e.g. 1:1, 9:16" },
       "resolution": { "type": "string", "enum": ["1K", "2K", "4K"], "description": "Output resolution (Gemini only)" },
       "n": { "type": "number", "description": "Number of images, 1-4" },
-      "reference": { "type": "string", "description": "Reference image path or URL" },
+      "reference": {
+        "type": "array",
+        "items": { "type": "string" },
+        "description": "Reference images for image-to-image: local file path, https URL, or data URI. Pass multiple to blend several references (seedream: max 14, seedream-pro: max 10, gemini: max 4 — over the limit fails before spending credits)."
+      },
+      "image_strength": { "type": "number", "description": "How strongly the reference images influence the result, 0-1 (Seedream family only). Omit to use the backend default." },
+      "guidance_scale": { "type": "number", "description": "Prompt-adherence strength, where supported. Omit to use the backend default." },
       "negative_prompt": { "type": "string", "description": "Negative prompt — content to avoid" },
+      "seed": { "type": "number", "description": "Random seed. Pass the same seed with the same prompt and model to make a run reproducible." },
+      "watermark": { "type": "boolean", "description": "Add a watermark to the output. Only true has an effect; there is no opt-out override of the backend default." },
       "json_output": { "type": "boolean", "description": "Emit a JSON result ({ urls: [...] }) instead of human-readable output" }
     },
     "required": ["prompt"]

package/skills/gen-image/version.json

@@ -3,5 +3,5 @@
   "repoName": "agent-skill-media-maker",
   "skillId": "337",
   "version": "V9",
-  "skillDescription": "AI 生图技能，根据文字描述生成图片，也支持参考图进行图生图（调用 ab-api /model/genImg，支持 Seedream 与 Gemini）。\n\n当用户提到以下任何需求时，立即使用本 skill：\n- AI 生图、AI 画图、文生图、文字生成图片、生成图像、帮我画、生成一张图\n- 图生图、以图生图、参考图、风格迁移、图片变体\n- 使用 doubao / 豆包 / seedream、Gemini 等生成图片\n- 用户提供图片提示词并希望生成图片\n\n即使用户没有明确说「使用 AI」，只要他们想要根据描述生成图片，也要使用本 skill。"
+  "skillDescription": "AI image generation skill: produce an image from a text prompt, or do image-to-image with reference images. Backed by ab-api's `/model/genImg` (Seedream and Gemini families).\n\nUse this skill immediately whenever the user asks for any of:\n- AI image generation, text-to-image, \"draw me ...\", \"generate an image of ...\"\n- Image-to-image, reference image, style transfer, image variation\n- Generate an image with Doubao / Seedream / Gemini\n- Provide a prompt and ask for an image\n\nEven without an explicit \"use AI\", any request that turns a description into an image should route here."
 }

package/skills/gen-script/SKILL.md

@@ -293,26 +293,28 @@ Apply the following principles when producing the DSL:
    "text": "Alibaba's open-source AI video-editing project\nalready has 4.3k stars on GitHub"
    ```
    instead of one continuous paragraph.
-4. **Moderate scene count**: 30-second videos work well with 4–6 scenes, 60-second videos with 6–10.
-5. **Leave room for templates**: pick generic layouts; do not assume a specific template implementation.
-6. **Image model allowlist**: every `type: image` + `source: gen-image` `AssetRef`'s `payload.model` **must** be one of the values in the table below. **Never** use display names, short forms, or made-up ids (e.g. `seedream`, `gemini-flash`, etc.).
+5. **Moderate scene count**: 30-second videos work well with 4–6 scenes, 60-second videos with 6–10.
+6. **Leave room for templates**: pick generic layouts; do not assume a specific template implementation.
+7. **Image model allowlist**: every `type: image` + `source: gen-image` `AssetRef`'s `payload.model` **must** be one of the values in the table below. **Never** use display names, short forms, or made-up ids (e.g. `seedream`, `gemini-flash`, etc.).
 
 ### Allowlist `model` values aligned with gen-image
 
-Mirrors the `gen-image` skill and `GEN_IMG_MODEL_PRESETS` in `gen_image.py`. **Only** the following four values are allowed (copy verbatim, including prefix and version):
+The roster is owned by the backend catalog (`/model/capabilities`), which `gen-image` resolves at
+runtime. A DSL is persisted and replayed later, so write the **full id** — copy verbatim, including
+prefix and version — not a short alias:
 
-| LiteLLM `model` | Display name | Provider |
-|-----------------|--------------|----------|
-| `doubao/doubao-seedream-4-5-251128` | Seedream 4.5 | Volcano |
-| `doubao/doubao-seedream-5-0-260128` | Seedream 5.0 Lite | Volcano |
-| `gemini-3-pro-image` | Gemini 3 Pro | Google |
-| `gemini-3.1-flash-image-preview` | Gemini 3.1 Flash | Google |
+| `payload.model` | Display name | Provider | Notes |
+|-----------------|--------------|----------|-------|
+| `doubao/doubao-seedream-5-0-260128` | Seedream 5.0 Lite | Volcano | Default. Highest output resolution, up to 14 reference images. |
+| `doubao/doubao-seedream-5-0-pro-260628` | Seedream 5.0 Pro | Volcano | High fidelity: precise element placement, faithful on-image text. Up to 10 reference images, caps out around 2K. Costs noticeably more per image. |
+| `gemini-3-pro` | Gemini 3 Pro | Google | Up to 4 reference images. |
 
 **Agent behavior (avoid accidentally rewriting `model`)**:
 
-- `gen_script.py` already writes a valid `payload.model` (currently `gemini-3.1-flash-image-preview` by default). When the user only asks to refine narration, change `payload.prompt`, add or remove scenes, etc. and does **not** ask to change the image model, the agent **must keep** each image asset's original `payload.model` — do not replace it under the guise of "polishing the script".
-- **Only when the user explicitly asks to change the image model** (e.g. switches to Seedream or a different Gemini), update the corresponding image `AssetRef`'s `payload.model` to the matching row id from the table. Writing a display name into JSON is wrong.
-- When creating a new image `AssetRef`, pick one of the values above for `payload.model`; default to `gemini-3.1-flash-image-preview` to match the script, or to whichever value the user specified.
+- `gen_script.py` already writes a valid `payload.model` (`doubao/doubao-seedream-5-0-260128` unless `DEFAULT_IMAGE_MODEL` overrides it). When the user only asks to refine narration, change `payload.prompt`, add or remove scenes, etc. and does **not** ask to change the image model, the agent **must keep** each image asset's original `payload.model` — do not replace it under the guise of "polishing the script".
+- **Only when the user explicitly asks to change the image model** (e.g. switches to the Pro variant or to Gemini), update the corresponding image `AssetRef`'s `payload.model` to the matching row id from the table. Writing a display name or an alias into JSON is wrong.
+- When creating a new image `AssetRef`, pick one of the values above for `payload.model`; default to `doubao/doubao-seedream-5-0-260128` to match the script, or to whichever value the user specified.
+- If a run fails with an unknown-model error, the catalog has moved on from this table — check `/model/capabilities` rather than guessing a version string.
 
 ## Error handling
 
@@ -325,11 +327,5 @@ Mirrors the `gen-image` skill and `GEN_IMG_MODEL_PRESETS` in `gen_image.py`. **O
 | File | Purpose |
 |------|---------|
 | `gen_script.py` | Core script — produces the Video DSL JSON from a topic. |
-| `dsl.json` | DSL example produced from the generic template (debug reference). |
-| `script.json` | Intermediate script-generation result (example). |
-| `html_slide.json` | DSL example for the html-slide template. |
-| `knowledge_card_dsl.json` | DSL example for the knowledge-card scene. |
-| `knowledge_card_script.json` | Intermediate knowledge-card script result. |
-| `script_knowledge_card.json` | Full knowledge-card script example. |
-
-These JSON files are reference data for development / debugging; they do not participate in runtime logic. The authoritative DSL examples live under `template-registry/video_dsl/schema/examples/`.
+
+The authoritative DSL examples live under `template-registry/video_dsl/schema/examples/`; list them with `template_registry list_examples=true`.

package/skills/gen-script/version.json

@@ -3,5 +3,5 @@
   "repoName": "agent-skill-media-maker",
   "skillId": "474",
   "version": "V11",
-  "skillDescription": "视频脚本生成技能，将用户主题转化为结构化 Video DSL（JSON），描述视频的完整结构、素材需求与叙事逻辑。\n\n当用户提到以下任何需求时，立即使用本 skill：\n- 帮我写视频脚本、生成视频脚本、视频策划、写分镜脚本\n- 做一个短视频、帮我规划视频内容、生成视频 DSL\n- 把主题转成视频结构、视频内容规划\n\n即使用户没有明确说「生成 DSL」，只要他们想要把一个主题变成视频内容结构，也要使用本 skill。"
+  "skillDescription": "Video-script generation skill. Turns a user-supplied topic into a structured Video DSL (JSON) that describes the full video — scene structure, asset requirements, and narrative flow.\n\nUse this skill as soon as the user mentions any of these intents:\n- Write a video script, generate a video script, plan a video, write storyboards\n- Create a short video, plan video content, generate a Video DSL\n- Turn a topic into a video structure / video content plan\n\nEven when the user does not say \"generate the DSL\", use this skill whenever they want to turn a topic into a structured video plan.\n\n⚠️ Stop-and-confirm gate: after this skill returns a DSL, show the full script and wait for the user's explicit confirmation. Never call `prepare_video_assets` in the same turn."
 }

package/skills/gen-video/SKILL.md

@@ -23,7 +23,9 @@ Wraps ab-api's `POST /model/genVideo` (the same endpoint the web "Lingchuang AI
 
 ## Models
 
-Aligned with the handler's `MODEL_ALIASES` and the frontend `AI_VIDEO_MODELS`:
+The authoritative roster — ids, aliases and per-model limits — lives in the backend catalog
+(`/model/capabilities`), which the CLI fetches at runtime. The table below mirrors it; when the
+two disagree, the catalog wins.
 
 | LiteLLM `model` | Display name | Provider | Duration | Notes |
 |-----------------|--------------|----------|----------|-------|
@@ -33,8 +35,8 @@ Aligned with the handler's `MODEL_ALIASES` and the frontend `AI_VIDEO_MODELS`:
 
 **Model shortcuts** (`--model` / `-m` accepts these directly):
 - `seedance` / `seedance-1.5` / `seedance-1.5-pro` → Seedance 1.5 Pro
-- `veo` / `veo-3.1` → Veo 3.1
-- `veo-fast` / `veo-3.1-fast` → Veo 3.1 Fast
+- `veo` / `veo-3.1` / `veo-3.1-generate` → Veo 3.1
+- `veo-fast` / `veo-3.1-fast` / `veo-3.1-fast-generate` → Veo 3.1 Fast
 
 ### Per-model parameter ranges
 

package/skills/gen-video/skill.json

@@ -12,14 +12,22 @@
     "type": "object",
     "properties": {
       "prompt": { "type": "string", "description": "Video description" },
-      "model": { "type": "string", "description": "Model: seedance / veo / veo-fast" },
+      "model": { "type": "string", "description": "Model: 'seedance' (default; 4-12s, adaptive/21:9 ratios, fixed camera), 'veo' (4/6/8s, native audio, up to 4k, reference images), or 'veo-fast' (faster Veo variant for iteration)" },
       "duration": { "type": "number", "description": "Duration in seconds" },
       "ratio": { "type": "string", "description": "Aspect ratio" },
       "resolution": { "type": "string", "description": "Resolution" },
       "first_frame": { "type": "string", "description": "First-frame image path or URL" },
       "last_frame": { "type": "string", "description": "Last-frame image path or URL" },
-      "reference": { "type": "string", "description": "Reference image (Veo only)" },
+      "reference": {
+        "type": "array",
+        "items": { "type": "string" },
+        "description": "Reference images: local file path, https URL, or data URI. Veo only, max 3 — Seedance rejects them, use first_frame / last_frame instead."
+      },
       "generate_audio": { "type": "boolean", "description": "Generate native audio" },
+      "camera_fixed": { "type": "boolean", "description": "Lock the camera in place (Seedance)" },
+      "negative_prompt": { "type": "string", "description": "Content to steer away from (Veo)" },
+      "seed": { "type": "number", "description": "Random seed. Pass the same seed with the same prompt and model to make a run reproducible." },
+      "person_generation": { "type": "string", "enum": ["allow_all", "dont_allow"], "description": "Whether the model may render people (Veo). Omit to use the backend default." },
       "json_output": { "type": "boolean", "description": "Emit a JSON result ({ url }) instead of human-readable output" }
     },
     "required": ["prompt"]

package/skills/gen-video/version.json

@@ -3,5 +3,5 @@
   "repoName": "agent-skill-media-maker",
   "skillId": "339",
   "version": "V8",
-  "skillDescription": "AI 生视频技能，根据文字描述生成素材视频（调用 ab-api /model/genVideo，支持 Seedance 与 Veo）。\n\n当用户提到以下任何需求时，立即使用本 skill：\n- AI 生视频、文生视频、文字生成视频、生成一段视频、AI 制作视频\n- 使用 doubao / 豆包 / seedance、Veo、Google 等生成视频\n- 用户提供视频提示词并希望生成视频\n- 图生视频、首帧生成视频、参考图生成视频\n\n即使用户没有明确说「使用 AI」，只要他们想要根据描述生成视频，也要使用本 skill。"
+  "skillDescription": "AI video generation skill: produce a short clip from a text prompt. Backed by ab-api's `/model/genVideo` (Seedance and Veo families).\n\nUse this skill immediately whenever the user asks for any of:\n- Text-to-video, AI-generated clip, \"make a short video of ...\"\n- Generate video with Doubao / Seedance / Veo / Google\n- Image-to-video, first-frame / last-frame, reference-image-to-video\n\nEven without an explicit \"use AI\", any request that turns a description into a moving clip should route here."
 }

package/skills/gen-voice/SKILL.md

@@ -21,7 +21,7 @@ Wraps ab-api's unified `POST /tool/tts` with `provider: "minimax"` (the same end
 
 ## Auth & environment
 
-There is no skill-local env file — the executing process inherits the system environment. Examples below say `python`; on macOS you may need `python3`.
+There is no skill-local env file — the executing process inherits the system environment.
 
 - **Enterprise OpenClaw**: auth is already injected, **no need** to set `PRIV_TOKEN` / `--priv-token`.
 - **Other environments**: configure the token. See the Tianyan privateToken doc internally. Without a token, non-interactive runs fail; interactive runs prompt.

package/skills/gen-voice/version.json

@@ -3,5 +3,5 @@
   "repoName": "agent-skill-media-maker",
   "skillId": "338",
   "version": "V7",
-  "skillDescription": "语音合成（TTS）技能，将文字转为语音音频（调用 ab-api 统一 /tool/tts，provider=minimax，基于 Minimax TTS）。\n\n当用户提到以下任何需求时，立即使用本 skill：\n- AI 配音、语音合成、文字转语音、TTS、文本转音频、生成语音\n- 使用 minimax 语音合成\n- 用户想要将一段文字朗读出来、生成音频\n\n即使用户没有明确说「使用 AI」，只要他们想要将文字转为语音，也要使用本 skill。"
+  "skillDescription": "Text-to-speech (TTS) skill: synthesize narration audio from text via ab-api's unified `/tool/tts` endpoint with `provider: \"minimax\"` (Minimax TTS).\n\nUse this skill immediately whenever the user asks for any of:\n- AI voice-over, TTS, text-to-speech, generate narration audio\n- Use Minimax for speech synthesis\n- Read a piece of text aloud / produce an audio file from text\n\nEven when the user does not explicitly say \"AI\", any request that turns text into speech should route here."
 }

package/skills/prepare-video-assets/version.json

@@ -3,5 +3,5 @@
   "repoName": "agent-skill-media-maker",
   "skillId": "476",
   "version": "V1",
-  "skillDescription": "Asset-preparation skill (Phase 1 of the two-phase video pipeline). Resolves and generates every asset (image / audio / video) referenced by a Video DSL, persists a RenderPlan to the database, and returns a job_id for the subsequent render_video call."
+  "skillDescription": "Asset-preparation skill: resolves and generates every asset (image / audio / video) referenced by a Video DSL, persists a RenderPlan to the database, and returns a `job_id` for the subsequent `render_video` call.\n\nUse this skill as soon as the user mentions any of these intents:\n- Generate / prepare video assets, resolve assets, render-ready\n- \"Make me a video about X\" (the agent calls gen_script → prepare_video_assets → render_video)\n- Regenerate one asset (image / audio) for a specific scene\n\nNext step: after the user confirms the resolved assets, call `render_video` with the `job_id` returned by this skill.\n\n⚠️ Stop-and-confirm gate: this skill runs only after the user has confirmed the script, and after it returns you must show the resolved assets and wait for the user's explicit confirmation. Never call `render_video` in the same turn."
 }

package/skills/render-video/version.json

@@ -3,5 +3,5 @@
   "repoName": "agent-skill-media-maker",
   "skillId": "473",
   "version": "V19",
-  "skillDescription": "Final-render skill (Phase 3 of the two-phase video pipeline). Loads a persisted RenderPlan by job_id and drives Remotion to produce the final video. Assets must already be generated via prepare_video_assets."
+  "skillDescription": "Final-render skill: loads a persisted RenderPlan by `job_id` and drives the Remotion engine to produce the final video.\n\nUse this skill as soon as the user mentions any of these intents (after assets are already prepared):\n- Render the video, composite the video, export the video\n- Turn the prepared assets into the final clip\n- Render with Remotion\n\nPrerequisite: assets must already be generated via `prepare_video_assets`. This skill never resolves or regenerates assets — pass it a `job_id` from a previous `prepare_video_assets` call.\n\n⚠️ Stop-and-confirm gate: never call this skill until the user has explicitly confirmed the assets prepared by `prepare_video_assets`. If those assets were prepared in the current turn and the user has not replied since, stop and ask instead of rendering."
 }

package/skills/template-registry/version.json

@@ -3,5 +3,5 @@
   "repoName": "agent-skill-media-maker",
   "skillId": "475",
   "version": "V13",
-  "skillDescription": "视频模板仓库（列表查询）。存储所有视频模板定义，对外只暴露「列出可用模板」一个能力；DSL→TemplateBinding 的绑定逻辑已内嵌进 prepare-video-assets，不再作为独立步骤暴露。同时是跨 skill 共享 Python 库（registry_loader / match_template / template_paths / video_dsl 等）的存放位置。\n\n当用户提到以下任何需求时，立即使用本 skill：\n- 查看可用模板、列出所有模板"
+  "skillDescription": "Video-template registry skill. Stores every video-template definition and lists the available templates (templateId / name / aspect ratio / style tags).\n\nUse this skill as soon as the user mentions any of these intents:\n- View available templates / list every template\n\nNote: DSL→TemplateBinding is no longer a separate exposed step — once prepare_video_assets receives a template_id it builds the binding internally."
 }

package/skills/video-parser/version.json

@@ -3,5 +3,5 @@
   "repoName": "agent-skill-media-maker",
   "skillId": "553",
   "version": "V2",
-  "skillDescription": "视频解构技能，将视频拆解为可复用的内容资产（音频、ASR 文本、关键帧、场景分段）。\n\n当用户提到以下任何需求时，立即使用本 skill：\n- 视频解构、视频拆解、视频分析、解析视频\n- 提取关键帧、提取视频文案、视频转文字\n- 视频内容资产、视频素材提取\n\n即使用户没有明确说「解构」，只要他们想要从视频中提取文案、关键帧或结构化信息，也要使用本 skill。"
+  "skillDescription": "Video deconstruction skill. Splits a video into reusable content assets — audio, ASR transcript, scene segments, keyframe images.\n\nUse this skill as soon as the user mentions any of these intents:\n- Deconstruct / split / analyze / parse a video\n- Extract keyframes, extract the script from a video, transcribe a video\n- Pull content assets or raw material out of a video\n\nEven when the user does not say \"deconstruct\" explicitly, use this skill whenever they want to extract script text, keyframes, or structured information from a video."
 }