@remixmate/cli 0.9.15 → 0.9.17

package/skills/gen-image/skill.json

@@ -4,22 +4,81 @@
   "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" },
+  "joinsTake": true,
+  "envVars": [
+    "PRIV_TOKEN",
+    "MM_API_BASE_URL",
+    "AGENT_NAME",
+    "MM_IMAGE_MODEL"
+  ],
+  "entry": {
+    "type": "http",
+    "handler": "gen-image"
+  },
   "parameters": {
     "type": "object",
     "properties": {
-      "prompt": { "type": "string", "description": "Image description (required)" },
-      "model": { "type": "string", "description": "Model id" },
-      "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" },
-      "negative_prompt": { "type": "string", "description": "Negative prompt — content to avoid" },
-      "json_output": { "type": "boolean", "description": "Emit a JSON result ({ urls: [...] }) instead of human-readable output" }
+      "prompt": {
+        "type": "string",
+        "description": "Image description (required)"
+      },
+      "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": "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"]
+    "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

@@ -6,22 +6,86 @@
   "title": "AI Video Generation",
   "description": "AI video generation: produce a short video clip from a text prompt. Supports Seedance and Veo models, plus first/last frame and reference images.",
   "auth": "required",
-  "envVars": ["PRIV_TOKEN", "MM_API_BASE_URL", "AGENT_NAME", "MM_VIDEO_MODEL"],
-  "entry": { "type": "http", "handler": "gen-video" },
+  "joinsTake": true,
+  "envVars": [
+    "PRIV_TOKEN",
+    "MM_API_BASE_URL",
+    "AGENT_NAME",
+    "MM_VIDEO_MODEL"
+  ],
+  "entry": {
+    "type": "http",
+    "handler": "gen-video"
+  },
   "parameters": {
     "type": "object",
     "properties": {
-      "prompt": { "type": "string", "description": "Video description" },
-      "model": { "type": "string", "description": "Model: seedance / veo / veo-fast" },
-      "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)" },
-      "generate_audio": { "type": "boolean", "description": "Generate native audio" },
-      "json_output": { "type": "boolean", "description": "Emit a JSON result ({ url }) instead of human-readable output" }
+      "prompt": {
+        "type": "string",
+        "description": "Video description"
+      },
+      "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": "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"]
+    "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/skill.json

@@ -6,17 +6,43 @@
   "title": "Text-to-Speech (Minimax)",
   "description": "Text-to-speech (TTS): synthesize narration audio from text via the Minimax TTS model. Returns the persisted audio URL — no download needed.",
   "auth": "required",
-  "envVars": ["PRIV_TOKEN", "MM_API_BASE_URL", "AGENT_NAME"],
-  "entry": { "type": "http", "handler": "gen-voice" },
+  "joinsTake": true,
+  "envVars": [
+    "PRIV_TOKEN",
+    "MM_API_BASE_URL",
+    "AGENT_NAME"
+  ],
+  "entry": {
+    "type": "http",
+    "handler": "gen-voice"
+  },
   "parameters": {
     "type": "object",
     "properties": {
-      "text": { "type": "string", "description": "Text to synthesize (required)" },
-      "voice_id": { "type": "string", "description": "Voice id. Default 'Chinese (Mandarin)_Male_Announcer'. When unsure, call with list_voices=true first to see what's available — do not invent ids." },
-      "speed": { "type": "number", "description": "Speech rate, 0.5-2.0" },
-      "list_voices": { "type": "boolean", "description": "List available voices and exit" },
-      "local": { "type": "boolean", "description": "Used together with list_voices=true: print the voice-resolver fallback catalog with language tags (no remote /voice/page call). Output is one '<id>\\t<lang>\\t<name>' line per voice." },
-      "json_output": { "type": "boolean", "description": "Emit a JSON result (url, audio_length_ms, subtitles)" }
+      "text": {
+        "type": "string",
+        "description": "Text to synthesize (required)"
+      },
+      "voice_id": {
+        "type": "string",
+        "description": "Voice id. Default 'Chinese (Mandarin)_Male_Announcer'. When unsure, call with list_voices=true first to see what's available — do not invent ids."
+      },
+      "speed": {
+        "type": "number",
+        "description": "Speech rate, 0.5-2.0"
+      },
+      "list_voices": {
+        "type": "boolean",
+        "description": "List available voices and exit"
+      },
+      "local": {
+        "type": "boolean",
+        "description": "Used together with list_voices=true: print the voice-resolver fallback catalog with language tags (no remote /voice/page call). Output is one '<id>\\t<lang>\\t<name>' line per voice."
+      },
+      "json_output": {
+        "type": "boolean",
+        "description": "Emit a JSON result (url, audio_length_ms, subtitles)"
+      }
     },
     "required": []
   }

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/skill.json

@@ -6,19 +6,53 @@
   "title": "Video Asset Preparation",
   "description": "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. This is Phase 1 of the two-phase video pipeline; Phase 3 (Remotion render) lives in render_video.",
   "auth": "required",
-  "envVars": ["PRIV_TOKEN", "MM_API_BASE_URL", "MM_BACKEND_API_URL", "AGENT_NAME", "REMOTION_RENDER_API_URL", "REMOTION_RENDER_MODE", "REMOTION_OUTPUT_DIR", "ASSET_CACHE_DIR"],
+  "createsTake": true,
+  "envVars": [
+    "PRIV_TOKEN",
+    "MM_API_BASE_URL",
+    "MM_BACKEND_API_URL",
+    "AGENT_NAME",
+    "REMOTION_RENDER_API_URL",
+    "REMOTION_RENDER_MODE",
+    "REMOTION_OUTPUT_DIR",
+    "ASSET_CACHE_DIR"
+  ],
   "scriptPath": "scripts/prepare_video_assets.py",
   "parameters": {
     "type": "object",
     "properties": {
-      "dsl_json": { "type": "string", "description": "DSL JSON as an inline string (preferred — no disk write needed; required for multi-user concurrent flows). Pass the full DSL JSON, or — when a gen_script skeleton is cached in the session — a minimal JSON with only scenes[].audio.narration.text overrides (the agent layer merges narration onto the cached skeleton)." },
-      "dsl": { "type": "string", "description": "DSL file path (legacy fallback; prefer dsl_json inline)." },
-      "template_id": { "type": "string", "description": "Template id. When provided, the script invokes template-registry internally; no separate binding step is needed." },
-      "binding_json": { "type": "string", "description": "TemplateBinding JSON as an inline string (alternative to template_id; no file needed)." },
-      "binding": { "type": "string", "description": "TemplateBinding file path (optional; auto-generated when template_id is provided)." },
-      "save_job": { "type": "boolean", "description": "Persist the RenderPlan to the database (default true). On success the stdout contains '📦 render job jobId: N'. Auto-degrades to false when PRIV_TOKEN is missing, falling back to file mode. Pass false to opt out explicitly." },
-      "stub_image_url": { "type": "string", "description": "Test-mode image stub URL (renderer-side short-circuit). Only pass when the user explicitly says things like 'just testing / don't actually generate / use a placeholder image / save credits' AND provides a concrete URL. With this set, every image+source=gen-image AssetRef is short-circuited to that URL with no gen-image call. Do not pass otherwise; if the user expressed the intent without a URL, ask for one — do not invent one." },
-      "stub_video_url": { "type": "string", "description": "Test-mode video stub URL (renderer-side short-circuit). Only pass when the user explicitly says things like 'just testing / don't actually generate the video / use a placeholder clip / save credits' AND provides a concrete URL. With this set, every video+source=gen-video AssetRef is short-circuited to that URL with no gen-video call. Do not pass otherwise; if the user expressed the intent without a URL, ask for one — do not invent one." }
+      "dsl_json": {
+        "type": "string",
+        "description": "DSL JSON as an inline string (preferred — no disk write needed; required for multi-user concurrent flows). Pass the full DSL JSON, or — when a gen_script skeleton is cached in the session — a minimal JSON with only scenes[].audio.narration.text overrides (the agent layer merges narration onto the cached skeleton)."
+      },
+      "dsl": {
+        "type": "string",
+        "description": "DSL file path (legacy fallback; prefer dsl_json inline)."
+      },
+      "template_id": {
+        "type": "string",
+        "description": "Template id. When provided, the script invokes template-registry internally; no separate binding step is needed."
+      },
+      "binding_json": {
+        "type": "string",
+        "description": "TemplateBinding JSON as an inline string (alternative to template_id; no file needed)."
+      },
+      "binding": {
+        "type": "string",
+        "description": "TemplateBinding file path (optional; auto-generated when template_id is provided)."
+      },
+      "save_job": {
+        "type": "boolean",
+        "description": "Persist the RenderPlan to the database (default true). On success the stdout contains '📦 render job jobId: N'. Auto-degrades to false when PRIV_TOKEN is missing, falling back to file mode. Pass false to opt out explicitly."
+      },
+      "stub_image_url": {
+        "type": "string",
+        "description": "Test-mode image stub URL (renderer-side short-circuit). Only pass when the user explicitly says things like 'just testing / don't actually generate / use a placeholder image / save credits' AND provides a concrete URL. With this set, every image+source=gen-image AssetRef is short-circuited to that URL with no gen-image call. Do not pass otherwise; if the user expressed the intent without a URL, ask for one — do not invent one."
+      },
+      "stub_video_url": {
+        "type": "string",
+        "description": "Test-mode video stub URL (renderer-side short-circuit). Only pass when the user explicitly says things like 'just testing / don't actually generate the video / use a placeholder clip / save credits' AND provides a concrete URL. With this set, every video+source=gen-video AssetRef is short-circuited to that URL with no gen-video call. Do not pass otherwise; if the user expressed the intent without a URL, ask for one — do not invent one."
+      }
     },
     "required": []
   }

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/skill.json

@@ -6,18 +6,53 @@
   "title": "Remotion Video Renderer",
   "description": "Loads a persisted RenderPlan by job_id and drives the Remotion engine to produce the final video. Assets must already be generated via prepare_video_assets — this skill never resolves or regenerates assets.",
   "auth": "required",
-  "envVars": ["PRIV_TOKEN", "MM_API_BASE_URL", "MM_BACKEND_API_URL", "AGENT_NAME", "REMOTION_RENDER_API_URL", "REMOTION_RENDER_MODE", "REMOTION_OUTPUT_DIR", "ASSET_CACHE_DIR"],
+  "createsTake": true,
+  "envVars": [
+    "PRIV_TOKEN",
+    "MM_API_BASE_URL",
+    "MM_BACKEND_API_URL",
+    "AGENT_NAME",
+    "REMOTION_RENDER_API_URL",
+    "REMOTION_RENDER_MODE",
+    "REMOTION_OUTPUT_DIR",
+    "ASSET_CACHE_DIR"
+  ],
   "scriptPath": "scripts/render_video.py",
   "parameters": {
     "type": "object",
     "properties": {
-      "job_id": { "type": "number", "minimum": 1, "description": "Render job id (positive integer, e.g. 8). This is the integer N parsed from prepare_video_assets's stdout line '📦 render job jobId: N' (also tolerated: legacy zh '📦 渲染任务 jobId: N'). Never pass 0, a placeholder string, or descriptive text." },
-      "save_job": { "type": "boolean", "description": "Persist the render Manifest back to the database under the same jobId (default true). Auto-degrades to false when PRIV_TOKEN is missing. Pass false to opt out explicitly." },
-      "upload_title": { "type": "string", "description": "Upload title for the resulting video file. Defaults to the local output filename." },
-      "no_upload": { "type": "boolean", "description": "Skip the upload step. Only effective for local rendering; remote rendering uploads server-side." },
-      "renderer": { "type": "string", "enum": ["local", "remote"], "description": "Render mode: local runs the Remotion CLI on this host; remote calls the standalone remotion-renderer service. Defaults to REMOTION_RENDER_MODE." },
-      "render_plan": { "type": "string", "description": "Existing RenderPlan file path. Local / single-user fallback used only when job_id is unavailable; prefer job_id." }
+      "job_id": {
+        "type": "number",
+        "minimum": 1,
+        "description": "Render job id (positive integer, e.g. 8). This is the integer N parsed from prepare_video_assets's stdout line '📦 render job jobId: N' (also tolerated: legacy zh '📦 渲染任务 jobId: N'). Never pass 0, a placeholder string, or descriptive text."
+      },
+      "save_job": {
+        "type": "boolean",
+        "description": "Persist the render Manifest back to the database under the same jobId (default true). Auto-degrades to false when PRIV_TOKEN is missing. Pass false to opt out explicitly."
+      },
+      "upload_title": {
+        "type": "string",
+        "description": "Upload title for the resulting video file. Defaults to the local output filename."
+      },
+      "no_upload": {
+        "type": "boolean",
+        "description": "Skip the upload step. Only effective for local rendering; remote rendering uploads server-side."
+      },
+      "renderer": {
+        "type": "string",
+        "enum": [
+          "local",
+          "remote"
+        ],
+        "description": "Render mode: local runs the Remotion CLI on this host; remote calls the standalone remotion-renderer service. Defaults to REMOTION_RENDER_MODE."
+      },
+      "render_plan": {
+        "type": "string",
+        "description": "Existing RenderPlan file path. Local / single-user fallback used only when job_id is unavailable; prefer job_id."
+      }
     },
-    "required": ["job_id"]
+    "required": [
+      "job_id"
+    ]
   }
 }

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/skill.json

@@ -6,17 +6,39 @@
   "title": "Video Deconstruction",
   "description": "Video deconstruction: split a video into reusable assets (audio extraction, ASR transcript, keyframe extraction, scene segmentation).",
   "auth": "required",
-  "envVars": ["RENDER_API_URL", "PRIV_TOKEN", "CONVERSATION_ID"],
+  "joinsTake": true,
+  "envVars": [
+    "RENDER_API_URL",
+    "PRIV_TOKEN",
+    "CONVERSATION_ID"
+  ],
   "scriptPath": "scripts/parse_via_render.py",
   "parameters": {
     "type": "object",
     "properties": {
-      "url": { "type": "string", "description": "Direct remote video URL (required). Share/page links are not supported." },
-      "scene_threshold": { "type": "number", "description": "Scene-cut detection threshold 0.0-1.0 (default 0.3)" },
-      "skip_asr": { "type": "boolean", "description": "Skip the ASR step" },
-      "skip_keyframes": { "type": "boolean", "description": "Skip the keyframe-extraction step" },
-      "json_output": { "type": "boolean", "description": "Pipeline mode — emit JSON only on stdout" }
+      "url": {
+        "type": "string",
+        "description": "Direct remote video URL (required). Share/page links are not supported."
+      },
+      "scene_threshold": {
+        "type": "number",
+        "description": "Scene-cut detection threshold 0.0-1.0 (default 0.3)"
+      },
+      "skip_asr": {
+        "type": "boolean",
+        "description": "Skip the ASR step"
+      },
+      "skip_keyframes": {
+        "type": "boolean",
+        "description": "Skip the keyframe-extraction step"
+      },
+      "json_output": {
+        "type": "boolean",
+        "description": "Pipeline mode — emit JSON only on stdout"
+      }
     },
-    "required": ["url"]
+    "required": [
+      "url"
+    ]
   }
 }

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."
 }