@remixmate/cli 0.1.0

package/skills/gen-script/skill.json

@@ -0,0 +1,41 @@
+{
+  "name": "gen-script",
+  "toolName": "gen_script",
+  "tier": "orchestration",
+  "title": "Video Script Generation",
+  "description": "Video script generation: turn a topic into a structured Video DSL (JSON) that describes the full video — scene structure, asset requirements, and narrative flow.",
+  "envVars": ["DEFAULT_IMAGE_MODEL", "DEFAULT_VIDEO_MODEL", "STUB_IMAGE_URL", "STUB_VIDEO_URL"],
+  "scriptPath": "scripts/gen_script.py",
+  "parameters": {
+    "type": "object",
+    "properties": {
+      "topic": { "type": "string", "description": "Video topic (required)" },
+      "platform": {
+        "type": "string",
+        "enum": ["douyin", "xiaohongshu", "bilibili", "wechat", "youtube", "generic"],
+        "description": "Target platform"
+      },
+      "duration": { "type": "number", "description": "Target duration in seconds" },
+      "style": { "type": "string", "description": "Style tag" },
+      "ratio": { "type": "string", "description": "Aspect ratio, e.g. 16:9 or 9:16" },
+      "scenes": { "type": "number", "description": "Scene count" },
+      "voice_id": { "type": "string", "description": "Narration voice id. Default depends on the bound template's outputLanguage; query gen_voice with list_voices=true to see available ids." },
+      "template_id": { "type": "string", "description": "Template id (e.g. html-slide). The template owns outputLanguage and may also declare a defaultVoiceId; both flow into the produced DSL." },
+      "headline": { "type": "string", "description": "On-screen headline (recommended 4-12 chars / ~3 words). Stored at meta.headline and pushed into every scene's textLayers[role=headline] so the template can render it as the top big-text. **Must** be set when the user explicitly provided a headline / main title; without it, headline falls back to the long-form topic and overflows the top text layer." },
+      "subheadline": { "type": "string", "description": "On-screen subheadline (project name / slogan / source, e.g. 'Pixelle-Video'). Stored at meta.subheadline and pushed into every scene's textLayers[role=subheadline] so the template can render it as the top small-text. **Must** be set when the user explicitly provided a subtitle / project name. Note: this is the on-screen subheadline, not the CC subtitle (global.subtitle) — they are independent." },
+      "carousel_items": {
+        "type": "array",
+        "items": { "type": "string" },
+        "description": "Media URLs for the template's image/video carousel (e.g. spotlight-card's middle carousel). When provided together with a template_id that has an input-schema.json, these URLs are placed directly into customPayload.carousel.items as existing assets — NO AI image generation is triggered. **Must** pass when the user explicitly provides image/video URLs for carousel-style templates (spotlight-card, etc.). Each element is a full URL string."
+      },
+      "caption_lines": {
+        "type": "array",
+        "items": { "type": "string" },
+        "description": "Bottom typewriter text lines for templates that support a caption/typewriter area (e.g. spotlight-card). Each element is one line of text. Supports **emphasis** syntax (rendered with accent color). **Must** pass when the user explicitly provides bullet-point text / bottom copy for the video."
+      },
+      "stub_image_url": { "type": "string", "description": "Test-mode image stub URL. Only pass when the user explicitly says things like 'just testing / don't actually generate / use a placeholder image / stub URL / save credits' AND provides a concrete URL. With this set, every image AssetRef in the produced DSL is written as source=existing, status=generated, url=<this URL> — 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. Only pass when the user explicitly says things like 'just testing / don't actually generate the video / placeholder clip / save credits' AND provides a concrete URL. With this set, every video AssetRef in the produced DSL is written as source=existing, status=generated, url=<this URL> — 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": ["topic"]
+  }
+}

package/skills/gen-script/version.json

@@ -0,0 +1,7 @@
+{
+  "skillName": "gen-script",
+  "repoName": "agent-skill-media-maker",
+  "skillId": "474",
+  "version": "V8",
+  "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。"
+}

package/skills/gen-video/SKILL.md

@@ -0,0 +1,170 @@
+---
+name: gen-video
+description: |
+  AI video generation skill: produce a short clip from a text prompt. Backed by ab-api's `/model/genVideo` (Seedance and Veo families).
+
+  Use this skill immediately whenever the user asks for any of:
+  - Text-to-video, AI-generated clip, "make a short video of ..."
+  - Generate video with Doubao / Seedance / Veo / Google
+  - Image-to-video, first-frame / last-frame, reference-image-to-video
+
+  Even without an explicit "use AI", any request that turns a description into a moving clip should route here.
+triggers:
+  - Text-to-video, AI-generated clip, "make a short video of ..."
+  - Generate video with Doubao / Seedance / Veo / Google
+  - Image-to-video, first-frame / last-frame, reference-image-to-video
+---
+
+# AI Video Generation Skill
+
+Wraps ab-api's `POST /model/genVideo` (the same endpoint the web "Lingchuang AI Video" tool uses), authenticated with the **Tianyan privateToken**, routed through LiteLLM to **Seedance** or **Veo**.
+
+## Models
+
+Aligned with `gen_video.py`'s `GEN_VIDEO_MODEL_PRESETS` and the frontend `AI_VIDEO_MODELS`:
+
+| LiteLLM `model` | Display name | Provider | Duration | Notes |
+|-----------------|--------------|----------|----------|-------|
+| `doubao-seedance-1-5-pro-251215` | Seedance 1.5 Pro | Volcano | 4–12s | Audio support, first/last frame, fixed camera, adaptive ratio |
+| `veo-3.1-generate-001` | Veo 3.1 | Google | 4 / 6 / 8s | Native audio, first/last frame, reference images, negative prompt, up to 4K |
+| `veo-3.1-fast-generate-001` | Veo 3.1 Fast | Google | 4 / 6 / 8s | Faster Veo 3.1 variant for quick iteration |
+
+**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
+
+### Per-model parameter ranges
+
+| | Seedance 1.5 Pro | Veo 3.1 / Veo 3.1 Fast |
+|--|--|--|
+| **Aspect ratio** | `adaptive` `16:9` `4:3` `1:1` `3:4` `9:16` `21:9` | `16:9` `9:16` |
+| **Resolution** | `480p` `720p` `1080p` | `720p` `1080p` `4k` |
+| **Duration** | 4–12 seconds (continuous integers) | 4 / 6 / 8 seconds |
+| **First / last frame** | yes | yes |
+| **Reference images** | not supported (use first/last frame) | yes, up to 3 |
+| **Generated audio** | yes | yes (native audio) |
+| **Fixed camera** | yes | — |
+| **Negative prompt** | — | yes |
+
+## Auth & environment
+
+No skill-local env file — the executing process inherits the system environment. Examples below say `python`; on macOS you may need `python3`.
+
+- **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.
+
+| Env var | Description | Default |
+|---------|-------------|---------|
+| `PRIV_TOKEN` | Tianyan token; `--priv-token` overrides | none |
+| `MM_VIDEO_MODEL` | Default model id | `doubao-seedance-1-5-pro-251215` |
+| `MM_API_BASE_URL` | API root | see `gen_video.py` default |
+| `AGENT_NAME` | Optional `x-invoke-agent` header | none |
+
+## Operations
+
+1. **Script path**: read the system-injected `Base directory for this skill: <path>` as `<SkillDir>` and always use `<SkillDir>/scripts/gen_video.py`. Do not hardcode paths.
+2. **Prompt**: include camera language ("aerial shot", "slow motion", "push-in") and dynamic descriptions for better results. Chinese or English both work.
+3. By default only the URL is printed; pass `--download` (and optional `--output`) to save locally.
+4. **Async job**: video generation is async; the script polls until completion (typically 1–3 minutes).
+
+### Seedance text-to-video (default model)
+
+```bash
+python3 <SkillDir>/scripts/gen_video.py \
+  --prompt "<video description>" \
+  --duration 5 \
+  --ratio "16:9"
+```
+
+### Seedance first/last frame + audio
+
+```bash
+python3 <SkillDir>/scripts/gen_video.py \
+  --prompt "<transition description>" \
+  --first-frame ./start.png \
+  --last-frame ./end.png \
+  --duration 8 \
+  --generate-audio
+```
+
+### Veo 3.1 high-resolution
+
+```bash
+python3 <SkillDir>/scripts/gen_video.py \
+  --model veo \
+  --prompt "<video description>" \
+  --duration 8 \
+  --ratio "16:9" \
+  --resolution 4k
+```
+
+### Veo 3.1 Fast for rapid iteration
+
+```bash
+python3 <SkillDir>/scripts/gen_video.py \
+  --model veo-fast \
+  --prompt "<video description>" \
+  --duration 6
+```
+
+### Veo with reference images
+
+```bash
+python3 <SkillDir>/scripts/gen_video.py \
+  --model veo \
+  --prompt "<video description>" \
+  --reference ./ref1.png \
+  --reference ./ref2.png \
+  --duration 8
+```
+
+### Download to disk
+
+```bash
+python3 <SkillDir>/scripts/gen_video.py \
+  --prompt "<video description>" \
+  --download \
+  --output "output_video.mp4"
+```
+
+5. **Surface results**: without `--download`, print the video URL; with `--download`, mention the local path.
+
+For the full flag list: `python3 <SkillDir>/scripts/gen_video.py --help`.
+
+## Common CLI flags
+
+| Flag | Description | Default |
+|------|-------------|---------|
+| `-p` / `--prompt` | Video description (combinable with first/last frame or references) | — |
+| `-m` / `--model` | Model id or shortcut (`seedance` / `veo` / `veo-fast`) | see `MM_VIDEO_MODEL` |
+| `-d` / `--duration` | Duration in seconds. Defaults to 5 (Seedance) or 8 (Veo) when omitted | per model |
+| `-r` / `--ratio` | Aspect ratio (default `16:9`). Seedance also accepts `adaptive` | `16:9` |
+| `--resolution` | Resolution. Veo accepts `4k` | `720p` |
+| `--first-frame` | First-frame image: local path, https URL, or data URI | none |
+| `--last-frame` | Last-frame image | none |
+| `--reference` | Reference image (repeatable; Veo only, max 3) | none |
+| `--generate-audio` | Generate native audio | off |
+| `--camera-fixed` | Fixed camera (mainly Seedance) | off |
+| `--negative-prompt` | Negative prompt (mainly Veo) | none |
+| `--seed` | Random seed | none |
+| `--person-generation` | Person policy: `allow_all` / `dont_allow` (Veo) | none |
+| `--download` | Download the video to disk | off |
+| `-o` / `--output` | Download path (only effective with `--download`) | `generated_video.mp4` |
+| `--poll-interval` | Polling interval (seconds) | `10` |
+| `--max-wait` | Max wait time (seconds) | `300` |
+| `--private-token` | Override token | see above |
+
+## Prompt tips
+
+- Include camera language: "aerial shot", "slow motion", "push-in", "close-up".
+- Describe motion explicitly.
+- Example: `"At sunrise, an aerial drone shot of a futuristic city, golden light on glass facades, mist swirling, 4K ultra-clear"`.
+
+## Error handling
+
+- **401** / **token missing** (non-OpenClaw): set `PRIV_TOKEN`.
+- **Business `code != 0`**: read `msg` on stderr.
+- **429**: rate-limited; retry later.
+- **Generation timeout**: increase `--max-wait` or retry later.
+- **Network**: verify connectivity and `MM_API_BASE_URL`.