@remixmate/cli 0.1.0

package/skills/template-bind/video_dsl/schema/video-dsl-v1alpha1.json

@@ -0,0 +1,378 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "$id": "video.dsl/v1alpha1",
+  "title": "Video DSL v1alpha1",
+  "description": "声明式视频描述语言，描述最终视频应该长什么样，而非如何调用每个技能。",
+  "type": "object",
+  "required": ["version", "meta", "global", "scenes"],
+  "properties": {
+    "version": {
+      "type": "string",
+      "const": "v1alpha1"
+    },
+    "meta": {
+      "$ref": "#/definitions/Meta"
+    },
+    "global": {
+      "$ref": "#/definitions/GlobalConfig"
+    },
+    "assets": {
+      "type": "array",
+      "items": { "$ref": "#/definitions/AssetRef" },
+      "description": "顶层素材声明池，可被 scene 级 assetBindings 引用"
+    },
+    "scenes": {
+      "type": "array",
+      "items": { "$ref": "#/definitions/Scene" },
+      "minItems": 1,
+      "maxItems": 20
+    },
+    "transitions": {
+      "$ref": "#/definitions/TransitionConfig"
+    },
+    "renderHints": {
+      "$ref": "#/definitions/RenderHints"
+    },
+    "outputs": {
+      "$ref": "#/definitions/OutputConfig"
+    }
+  },
+  "definitions": {
+    "Meta": {
+      "type": "object",
+      "required": ["title"],
+      "properties": {
+        "title": { "type": "string" },
+        "topic": { "type": "string" },
+        "platform": {
+          "type": "string",
+          "enum": ["douyin", "xiaohongshu", "bilibili", "wechat", "youtube", "generic"],
+          "default": "generic"
+        },
+        "targetDuration": {
+          "type": "number",
+          "description": "目标总时长（秒）"
+        },
+        "language": { "type": "string", "default": "zh-CN" },
+        "style": {
+          "type": "string",
+          "description": "整体风格标签，如 科技感、清新、商务、卡通"
+        },
+        "audience": { "type": "string" },
+        "description": { "type": "string" }
+      }
+    },
+    "GlobalConfig": {
+      "type": "object",
+      "properties": {
+        "aspectRatio": {
+          "type": "string",
+          "enum": ["16:9", "9:16", "1:1", "4:3", "3:4", "21:9"],
+          "default": "16:9"
+        },
+        "resolution": {
+          "type": "string",
+          "enum": ["480p", "720p", "1080p", "4k"],
+          "default": "1080p"
+        },
+        "fps": {
+          "type": "integer",
+          "enum": [24, 25, 30, 60],
+          "default": 30
+        },
+        "subtitle": {
+          "type": "object",
+          "properties": {
+            "enabled": { "type": "boolean", "default": true },
+            "style": { "type": "string", "enum": ["bottom", "center", "karaoke"], "default": "bottom" },
+            "fontSize": { "type": "integer" },
+            "fontFamily": { "type": "string" },
+            "color": { "type": "string" }
+          }
+        },
+        "narration": {
+          "type": "object",
+          "properties": {
+            "voiceId": { "type": "string", "description": "Minimax 音色 ID" },
+            "voiceName": { "type": "string" },
+            "speed": { "type": "number", "default": 1.0 }
+          }
+        },
+        "bgm": {
+          "type": "object",
+          "properties": {
+            "enabled": { "type": "boolean", "default": false },
+            "url": { "type": "string" },
+            "volume": { "type": "number", "default": 0.15, "minimum": 0, "maximum": 1 }
+          }
+        }
+      }
+    },
+    "AssetRef": {
+      "type": "object",
+      "required": ["assetId", "type"],
+      "properties": {
+        "assetId": {
+          "type": "string",
+          "description": "全局唯一素材 ID，scene 可通过此 ID 引用"
+        },
+        "type": {
+          "type": "string",
+          "enum": ["image", "video", "audio", "avatar", "subtitle", "bgm"]
+        },
+        "source": {
+          "type": "string",
+          "enum": ["existing", "gen-image", "gen-video", "gen-voice", "gen-digital-human"],
+          "description": "素材来源"
+        },
+        "status": {
+          "type": "string",
+          "enum": ["missing", "planned", "generating", "generated", "approved", "failed"],
+          "default": "planned"
+        },
+        "url": {
+          "type": "string",
+          "description": "已生成/已有素材的 URL"
+        },
+        "localPath": {
+          "type": "string",
+          "description": "本地缓存路径"
+        },
+        "payload": {
+          "type": "object",
+          "description": "素材生成参数，根据 source 不同内容不同",
+          "properties": {
+            "prompt": { "type": "string" },
+            "negativePrompt": {
+              "type": "string",
+              "description": "负向提示词，描述不希望出现的元素"
+            },
+            "guidanceScale": {
+              "type": "number",
+              "description": "引导系数，控制生成图片对 prompt 的遵循程度"
+            },
+            "model": { "type": "string" },
+            "text": { "type": "string" },
+            "voiceId": { "type": "string" },
+            "avatarId": { "type": ["string", "integer"] },
+            "duration": { "type": "number" },
+            "ratio": { "type": "string" },
+            "resolution": { "type": "string" },
+            "style": { "type": "string" }
+          },
+          "additionalProperties": true
+        },
+        "metadata": {
+          "type": "object",
+          "description": "生成后的元数据",
+          "properties": {
+            "duration": { "type": "number" },
+            "width": { "type": "integer" },
+            "height": { "type": "integer" },
+            "fileSize": { "type": "integer" },
+            "mimeType": { "type": "string" }
+          },
+          "additionalProperties": true
+        }
+      }
+    },
+    "Scene": {
+      "type": "object",
+      "required": ["id", "purpose"],
+      "properties": {
+        "id": { "type": "string" },
+        "purpose": {
+          "type": "string",
+          "enum": ["opening", "intro", "point", "example", "explanation", "transition", "highlight", "cta", "ending"],
+          "description": "场景在叙事中的角色"
+        },
+        "duration": {
+          "type": "number",
+          "description": "该场景时长（秒），可省略由模板决定"
+        },
+        "layout": {
+          "type": "string",
+          "enum": ["full-visual", "split-left-right", "split-top-bottom", "picture-in-picture", "text-overlay", "avatar-with-bg", "kenburns"],
+          "default": "full-visual"
+        },
+        "visuals": {
+          "type": "object",
+          "properties": {
+            "background": {
+              "type": "object",
+              "properties": {
+                "assetRef": { "type": "string", "description": "引用 assets 池中的 assetId" },
+                "color": { "type": "string" },
+                "gradient": { "type": "string" }
+              }
+            },
+            "foreground": {
+              "type": "object",
+              "properties": {
+                "assetRef": { "type": "string" },
+                "position": { "type": "string", "enum": ["center", "left", "right", "top", "bottom"] },
+                "scale": { "type": "number", "default": 1.0 }
+              }
+            },
+            "avatar": {
+              "type": "object",
+              "properties": {
+                "assetRef": { "type": "string" },
+                "position": { "type": "string", "enum": ["center", "left", "right", "bottom-left", "bottom-right"] },
+                "scale": { "type": "number", "default": 1.0 }
+              }
+            }
+          }
+        },
+        "audio": {
+          "type": "object",
+          "properties": {
+            "narration": {
+              "type": "object",
+              "description": "场景旁白。两种写法：(A) 传统：提供 text；(B) 多项卡片场景推荐：提供 intro/items/outro，每个 item 对应一张卡片，编译期会按 \\n 切行送 TTS 并自动生成 highlightMap，避免高亮与音频错位。",
+              "properties": {
+                "text": { "type": "string", "description": "该场景的完整旁白文案（传统写法）" },
+                "intro": { "type": "string", "description": "可选：开场铺垫句（此期间无卡片高亮）" },
+                "items": {
+                  "type": "array",
+                  "items": { "type": "string" },
+                  "description": "每行一个卡片的叙述句。长度必须等于 templateData 里对应数组（concepts/pillars/eras/items）的长度"
+                },
+                "outro": { "type": "string", "description": "可选：收尾句（此期间无卡片高亮）" },
+                "assetRef": { "type": "string", "description": "旁白音频 assetId" }
+              }
+            },
+            "bgm": {
+              "type": "object",
+              "properties": {
+                "assetRef": { "type": "string" },
+                "volume": { "type": "number" }
+              }
+            },
+            "soundEffect": {
+              "type": "object",
+              "properties": {
+                "assetRef": { "type": "string" },
+                "trigger": { "type": "string", "enum": ["scene-start", "scene-end", "midpoint"] }
+              }
+            }
+          }
+        },
+        "textLayers": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "required": ["role", "content"],
+            "properties": {
+              "role": {
+                "type": "string",
+                "enum": ["headline", "subheadline", "caption", "badge", "callout"],
+                "description": "文本图层的语义角色：headline=画面主标题（大字），subheadline=画面副标题/项目名/标语（小字，与 headline 配对），caption=注释/角标，badge=徽标，callout=指示/标注。注意 subtitle（CC 字幕，逐句出字）由 global.subtitle 与 render-plan.subtitleSegments 单独承载，不在 textLayers.role 这里。"
+              },
+              "content": { "type": "string" },
+              "position": { "type": "string" },
+              "animation": { "type": "string", "enum": ["fade-in", "slide-up", "typewriter", "none"], "default": "fade-in" }
+            }
+          }
+        },
+        "animationHints": {
+          "type": "object",
+          "properties": {
+            "entrance": { "type": "string", "enum": ["fade", "slide-left", "slide-right", "slide-up", "zoom-in", "none"], "default": "fade" },
+            "exit": { "type": "string", "enum": ["fade", "slide-left", "slide-right", "slide-down", "zoom-out", "none"], "default": "fade" },
+            "motion": { "type": "string", "enum": ["static", "kenburns-in", "kenburns-out", "pan-left", "pan-right", "float"], "default": "static" }
+          }
+        },
+        "assetBindings": {
+          "type": "array",
+          "items": { "type": "string" },
+          "description": "该场景引用的 assetId 列表"
+        },
+        "templateData": {
+          "type": "object",
+          "additionalProperties": true,
+          "description": "模板专属数据，结构由所绑定模板的 slotMapping 定义。如 knowledge-slides 的 slides 等"
+        }
+      }
+    },
+    "TransitionConfig": {
+      "type": "object",
+      "properties": {
+        "default": {
+          "type": "string",
+          "enum": ["cut", "fade", "dissolve", "slide-left", "slide-right", "wipe", "zoom", "flip", "flip-corner"],
+          "default": "fade"
+        },
+        "duration": {
+          "type": "number",
+          "default": 0.5,
+          "description": "转场时长（秒）"
+        },
+        "overrides": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "properties": {
+              "from": { "type": "string" },
+              "to": { "type": "string" },
+              "type": { "type": "string" },
+              "duration": { "type": "number" }
+            }
+          }
+        }
+      }
+    },
+    "RenderHints": {
+      "type": "object",
+      "properties": {
+        "templatePreference": {
+          "type": "array",
+          "items": { "type": "string" },
+          "description": "偏好的模板 ID 列表"
+        },
+        "brandColors": {
+          "type": "array",
+          "items": { "type": "string" },
+          "description": "品牌色 HEX 值"
+        },
+        "pace": {
+          "type": "string",
+          "enum": ["slow", "normal", "fast"],
+          "default": "normal"
+        },
+        "shotDensity": {
+          "type": "string",
+          "enum": ["sparse", "normal", "dense"],
+          "default": "normal"
+        }
+      }
+    },
+    "OutputConfig": {
+      "type": "object",
+      "properties": {
+        "remotion": {
+          "type": "object",
+          "properties": {
+            "enabled": { "type": "boolean", "default": true },
+            "codec": { "type": "string", "enum": ["h264", "h265", "vp8", "vp9"], "default": "h264" },
+            "crf": { "type": "integer", "default": 18 }
+          }
+        },
+        "jianyingDraft": {
+          "type": "object",
+          "description": "剪映草稿导出（预留）",
+          "properties": {
+            "enabled": { "type": "boolean", "default": false }
+          }
+        },
+        "cloudEditingProject": {
+          "type": "object",
+          "description": "云剪辑工程导出（预留）",
+          "properties": {
+            "enabled": { "type": "boolean", "default": false }
+          }
+        }
+      }
+    }
+  }
+}

package/skills/video-parser/SKILL.md

@@ -0,0 +1,238 @@
+---
+name: video-parser
+description: |
+  Video deconstruction skill. Splits a video into reusable content assets — audio, ASR transcript, scene segments, keyframe images.
+
+  Use this skill as soon as the user mentions any of these intents:
+  - Deconstruct / split / analyze / parse a video
+  - Extract keyframes, extract the script from a video, transcribe a video
+  - Pull content assets or raw material out of a video
+
+  Even 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.
+triggers:
+  - Deconstruct / split / analyze / parse a video
+  - Extract keyframes, extract the script from a video, transcribe a video
+  - Pull content assets or raw material out of a video
+---
+
+# Video Deconstruction Skill
+
+Splits a video into reusable content assets — audio, ASR transcript (with per-word timestamps), scene cuts, keyframe images. Emits a structured asset-manifest JSON.
+
+## Dependencies
+
+- **ffmpeg**: must be installed locally (`brew install ffmpeg`) — used for audio extraction, scene-change detection, and keyframe capture.
+- **Python 3**: standard library only, no third-party dependencies.
+
+## Authentication & environment
+
+There is no dedicated env file; the **process environment** variables of the caller apply. Examples use `python`; on macOS without that alias use `python3`.
+
+- **Enterprise OpenClaw**: auth is injected, **no** `PRIV_TOKEN` / `--priv-token` needed.
+- **Other environments**: configure a token — obtain a `PRIV_TOKEN` from your ab-api service. Non-interactive invocations may fail when the token is missing; interactive runs prompt for one.
+
+| Env var | Description | Default |
+|---------|-------------|---------|
+| `PRIV_TOKEN` | Tianyan token; overridable with `--priv-token`. | (none) |
+| `MM_API_BASE_URL` | API root URL. | `http://localhost:3001/api` |
+| `AGENT_NAME` | Optional, sent as the `x-invoke-agent` request header. | (none) |
+
+## Steps
+
+1. **Script path**: read the system-injected `Base directory for this skill: <path>` as `<SkillDir>`. Every command below uses `<SkillDir>/scripts/deconstruct_video.py`; never hard-code paths.
+2. **Confirm ffmpeg**: run `ffmpeg -version` to confirm it is installed locally.
+3. **Pick the input**: either a direct video URL or a local file path (one of the two).
+4. **Run the deconstruction**: invoke the script and wait for it to finish.
+5. **Inspect the result**: check `deconstruction.json`, `audio.mp3`, and the `keyframes/` directory in the output folder.
+
+### Deconstruct from a URL
+
+```bash
+python3 <SkillDir>/scripts/deconstruct_video.py \
+  --url "https://example.com/video.mp4" \
+  --output-dir ./output_deconstructed
+```
+
+### Deconstruct from a local file
+
+```bash
+python3 <SkillDir>/scripts/deconstruct_video.py \
+  --local /path/to/video.mp4 \
+  --output-dir ./output_deconstructed
+```
+
+### Custom scene-change threshold
+
+```bash
+python3 <SkillDir>/scripts/deconstruct_video.py \
+  --url "https://example.com/video.mp4" \
+  --scene-threshold 0.4
+```
+
+Lower values are more sensitive (more cuts), higher values are looser (fewer cuts). Default is 0.3.
+
+### Audio + ASR only (skip keyframes)
+
+```bash
+python3 <SkillDir>/scripts/deconstruct_video.py \
+  --url "https://example.com/video.mp4" \
+  --skip-keyframes
+```
+
+### Keyframes only (skip ASR)
+
+```bash
+python3 <SkillDir>/scripts/deconstruct_video.py \
+  --url "https://example.com/video.mp4" \
+  --skip-asr
+```
+
+### JSON pipeline mode
+
+```bash
+python3 <SkillDir>/scripts/deconstruct_video.py \
+  --url "https://example.com/video.mp4" \
+  --json-output
+```
+
+Prints only the final `deconstruction.json` payload to stdout — no progress lines — suitable for piping.
+
+See every option: `python3 <SkillDir>/scripts/deconstruct_video.py --help`.
+
+## Common CLI flags
+
+| Flag | Description | Default |
+|------|-------------|---------|
+| `--url` | Remote video URL (mutually exclusive with `--local`). | — |
+| `--local` | Local video path (mutually exclusive with `--url`). | — |
+| `-o` / `--output-dir` | Output directory. | `./deconstructed_<timestamp>` |
+| `--scene-threshold` | Scene-change threshold 0.0–1.0. | `0.3` |
+| `--private-token` | Override `privateToken`. | env var |
+| `--json-output` | Pipeline mode — JSON-only stdout. | off |
+| `--skip-asr` | Skip the ASR step. | off |
+| `--skip-keyframes` | Skip the keyframe-extraction step. | off |
+
+## Output layout
+
+The script writes the following under `--output-dir`:
+
+```
+<output-dir>/
+├── audio.mp3              # Extracted audio file
+├── deconstruction.json    # Asset-manifest JSON
+└── keyframes/             # Keyframe images
+    ├── frame_001.jpg
+    ├── frame_002.jpg
+    └── ...
+```
+
+### `deconstruction.json` shape
+
+```json
+{
+  "source": {
+    "url": "original URL (if any)",
+    "localPath": "local video path",
+    "durationMs": 12345
+  },
+  "audio": {
+    "localPath": "output_dir/audio.mp3",
+    "url": "uploaded OSS URL"
+  },
+  "asr": {
+    "text": "full recognized transcript",
+    "duration": 3816,
+    "utterances": [
+      {
+        "text": "per-utterance text",
+        "startTime": 0,
+        "endTime": 1000,
+        "words": [...]
+      }
+    ]
+  },
+  "scenes": [
+    {
+      "index": 0,
+      "startTimeSec": 0.0,
+      "endTimeSec": 3.5,
+      "keyframe": "keyframes/frame_001.jpg"
+    }
+  ],
+  "keyframes": [
+    {
+      "index": 0,
+      "timestampSec": 0.0,
+      "localPath": "keyframes/frame_001.jpg"
+    }
+  ]
+}
+```
+
+## Deconstruction → structural analysis
+
+Reads the deconstruction artifacts and extracts hook, narrative structure, copy pacing, scene composition, etc., emitting a structured analysis report. Script path: `<SkillDir>/scripts/analyze_video.py`.
+
+The analysis report can be used to:
+- Feed an AI to write a new script with the same structure.
+- Guide a human re-creator to replicate the video's rhythm.
+- Inform downstream template development.
+
+### Basic usage
+
+```bash
+python3 <SkillDir>/scripts/analyze_video.py \
+  -i ./output/deconstructed_xxx/deconstruction.json
+```
+
+### Specify the output directory
+
+```bash
+python3 <SkillDir>/scripts/analyze_video.py \
+  -i ./output/deconstructed_xxx/ \
+  -o ./reports/
+```
+
+### Pipeline mode
+
+```bash
+python3 <SkillDir>/scripts/analyze_video.py \
+  -i ./output/deconstructed_xxx/ \
+  --json-output
+```
+
+Prints only the `analysis.json` payload to stdout, no progress text, suitable for piping.
+
+### analyze_video.py flags
+
+| Flag | Description | Default |
+|------|-------------|---------|
+| `-i` / `--input` | Path to `deconstruction.json` or its parent directory. | required |
+| `-o` / `--output-dir` | Output directory. | same as input |
+| `--json-output` | Pipeline mode (JSON-only stdout). | off |
+
+### Output files
+
+`analysis.json`: the structured analysis report. Covers the following dimensions:
+
+| Field | Description |
+|-------|-------------|
+| `source` | Original video information (URL, duration). |
+| `overview` | Language, scene count, copy length, asset types. |
+| `hook` | Opening-hook text, duration, strategy classification. |
+| `narrativeStructure` | Per-scene narrative structure (role, duration share, text density). |
+| `pacing` | Pacing analysis (scene-duration distribution, rhythm type). |
+| `textStructure` | Copy structure (speaking rate, silent gaps, keywords). |
+| `audioPattern` | Audio pattern (speech vs. silence ratio). |
+| `cta` | CTA detection (closing copy, whether an explicit CTA exists). |
+| `assets` | Asset manifest (audio, keyframes). |
+
+## Error handling
+
+- **ffmpeg not installed**: the script detects this and prompts `brew install ffmpeg`.
+- **401 / token missing** (non-OpenClaw): check or set the token via the Feishu link above.
+- **Business `code != 0`**: read the `msg` printed on stderr.
+- **Video download failed**: confirm the URL is a direct video link (page links such as Douyin / Xiaohongshu are not supported).
+- **ASR timeout**: large files can take a while; the script defaults to a 300-second timeout.
+- **No scene change detected**: too-high threshold can yield zero cuts — try lowering `--scene-threshold`.
+- **Network**: check connectivity and `MM_API_BASE_URL`.