@remixmate/cli 0.1.0 → 0.1.1

package/skills/video-parser/SKILL.md

@@ -17,222 +17,109 @@ triggers:
 
 # 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.
+Splits a video into reusable content assets — audio, ASR transcript (with per-word timestamps), scene cuts, keyframe images — and returns 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.
+The skill entry (`scripts/parse_via_render.py`) runs the deconstruction **through the ab-render HTTP service** (`POST /parse` → poll `POST /parseStatus`). It needs **no local ffmpeg** — the heavy lifting happens server-side and the manifest (with cloud-hosted asset URLs) comes back as JSON on stdout.
 
 ## 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`.
+No skill-local env file — the executing process inherits the system environment.
 
-- **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.
+- **Enterprise OpenClaw**: auth + service address are injected; nothing to configure.
+- **Other environments**: set `RENDER_API_URL` (the ab-render service) and `PRIV_TOKEN`. Without them the run fails fast with an actionable message.
 
 | 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) |
+| `RENDER_API_URL` | ab-render service base URL (e.g. `http://localhost:3000`). Required. | (none) |
+| `PRIV_TOKEN` | Tianyan token, sent as `X-Priv-Token`. | (none) |
+| `CONVERSATION_ID` | Optional, sent as `x-conversation-id` for file association. | (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.
+1. **Script path**: read the system-injected `Base directory for this skill: <path>` as `<SkillDir>`. The entry is always `<SkillDir>/scripts/parse_via_render.py`; never hard-code paths.
+2. **Provide a direct video URL** (`--url`). Page links (Douyin / Xiaohongshu share pages) are not supported — pass a direct video file URL.
+3. **Run and wait**: the script submits the task and polls until it finishes (up to ~10 minutes), printing progress lines.
+4. **Consume the result**: a JSON asset-manifest is printed to stdout (audio / ASR / scenes / keyframes, with cloud URLs). Save or pipe it as needed.
 
-### Deconstruct from a URL
+### Deconstruct a video
 
 ```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
+python3 <SkillDir>/scripts/parse_via_render.py \
+  --url "https://example.com/video.mp4"
 ```
 
 ### Custom scene-change threshold
 
 ```bash
-python3 <SkillDir>/scripts/deconstruct_video.py \
+python3 <SkillDir>/scripts/parse_via_render.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.
+Lower values are more sensitive (more cuts), higher values looser (fewer cuts). Default `0.3`.
 
-### Audio + ASR only (skip keyframes)
+### Skip ASR or keyframes
 
 ```bash
-python3 <SkillDir>/scripts/deconstruct_video.py \
-  --url "https://example.com/video.mp4" \
-  --skip-keyframes
-```
-
-### Keyframes only (skip ASR)
+# audio + scenes only (skip keyframes)
+python3 <SkillDir>/scripts/parse_via_render.py --url "https://example.com/video.mp4" --skip-keyframes
 
-```bash
-python3 <SkillDir>/scripts/deconstruct_video.py \
-  --url "https://example.com/video.mp4" \
-  --skip-asr
+# keyframes + scenes only (skip ASR)
+python3 <SkillDir>/scripts/parse_via_render.py --url "https://example.com/video.mp4" --skip-asr
 ```
 
 ### JSON pipeline mode
 
 ```bash
-python3 <SkillDir>/scripts/deconstruct_video.py \
+python3 <SkillDir>/scripts/parse_via_render.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`.
+Prints only the final manifest JSON to stdout — no progress lines — suitable for piping into downstream tools.
 
 ## 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 |
+| `--url` | Direct remote video URL (required). | — |
+| `--scene-threshold` | Scene-change sensitivity 0.0–1.0. | `0.3` |
 | `--skip-asr` | Skip the ASR step. | off |
 | `--skip-keyframes` | Skip the keyframe-extraction step. | off |
+| `--json-output` | Pipeline mode — JSON-only stdout. | 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
-    └── ...
-```
+## Result manifest shape
 
-### `deconstruction.json` shape
+`parse_via_render.py` prints the service's `result` payload — a structured manifest whose top-level fields are:
 
 ```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"
-    }
-  ]
+  "source":   { "url": "original URL", "durationMs": 12345 },
+  "audio":    { "url": "cloud audio URL" },
+  "asr":      { "text": "full transcript", "utterances": [ { "text": "...", "startTime": 0, "endTime": 1000, "words": [] } ] },
+  "scenes":   [ { "index": 0, "startTimeSec": 0.0, "endTimeSec": 3.5, "keyframe": "cloud keyframe URL" } ],
+  "keyframes":[ { "index": 0, "timestampSec": 0.0, "url": "cloud keyframe URL" } ]
 }
 ```
 
-## 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.
+(Exact fields are defined by the ab-render service; treat the above as representative.)
 
-### Basic usage
+## Optional local tools (not the skill entry)
 
-```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/
-```
+Two extra scripts ship alongside the entry for local / offline use. They are **not** invoked by the `video_parser` tool and are **not** the skill entry — call them directly with `python3` only when you specifically need local processing:
 
-### Pipeline mode
+- **`scripts/deconstruct_video.py`** — a fully local deconstruction alternative that **requires ffmpeg** (`brew install ffmpeg`) and writes `audio.mp3` + `keyframes/` + `deconstruction.json` to an `--output-dir`. Use when there is no ab-render service available. Flags: `--url` / `--local`, `-o/--output-dir`, `--scene-threshold`, `--skip-asr`, `--skip-keyframes`, `--json-output`.
+- **`scripts/analyze_video.py`** — a second stage that reads a `deconstruction.json` (or the manifest above saved to disk) and emits a structural-analysis report (hook, narrative structure, pacing, CTA, …). Flags: `-i/--input`, `-o/--output-dir`, `--json-output`.
 
-```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). |
+  ```bash
+  python3 <SkillDir>/scripts/analyze_video.py -i ./deconstruction.json
+  ```
 
 ## 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.
+- **`RENDER_API_URL` not configured**: the script exits with a clear message; set the ab-render service URL.
+- **401 / token missing** (non-OpenClaw): set `PRIV_TOKEN`.
 - **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`.
+- **Video download failed**: confirm the URL is a direct video link (share/page links are not supported).
+- **Timeout**: very long videos may exceed the ~10-minute poll window; retry or pre-trim.
+- **No scene change detected**: a too-high threshold yields zero cuts — lower `--scene-threshold`.

package/skills/video-parser/skill.json

@@ -4,18 +4,17 @@
   "tier": "tool",
   "title": "Video Deconstruction",
   "description": "Video deconstruction: split a video into reusable assets (audio extraction, ASR transcript, keyframe extraction, scene segmentation).",
-  "envVars": ["PRIV_TOKEN", "MM_API_BASE_URL", "AGENT_NAME", "RENDER_API_URL"],
+  "envVars": ["RENDER_API_URL", "PRIV_TOKEN", "CONVERSATION_ID"],
   "scriptPath": "scripts/parse_via_render.py",
   "parameters": {
     "type": "object",
     "properties": {
-      "url": { "type": "string", "description": "Remote video URL (or use local)" },
-      "local": { "type": "string", "description": "Local video path (or use url)" },
+      "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": []
+    "required": ["url"]
   }
 }

package/skills/video-parser/version.json

@@ -2,6 +2,6 @@
   "skillName": "video-parser",
   "repoName": "agent-skill-media-maker",
   "skillId": "553",
-  "version": "V1",
+  "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。"
 }