feat: video-edit-planner skill — transcribe, extract frames, plan edits

A conversational video-editing planning assistant. Provides tools for:
- Audio transcription via bundled funasr-script (Fun-ASR-Nano / SenseVoice)
- On-demand clip extraction and frame sampling (ffmpeg, hardware-accelerated)
- SQLite index to track all artifacts and avoid duplicate processing
- Vision analysis guidance with binary-search-style frame sampling
- Iterative Markdown-table edit plan output

Agent-agnostic: no platform-specific tool names, works with any agent runtime.
Dependencies checked at guidance level with OS package manager install hints.

scripts/transcription/funasr_nano.py

@@ -0,0 +1,30 @@
+from __future__ import annotations
+
+import argparse
+
+from funasr_common import NANO_MODEL_CONFIG, add_common_args, run_pipeline
+
+
+def build_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(
+        prog="funasr-nano",
+        description="提取指定音轨并用 Fun-ASR-Nano-2512 转录。",
+    )
+    add_common_args(parser)
+    return parser
+
+
+def main() -> None:
+    args = build_parser().parse_args()
+    run_pipeline(
+        args,
+        model_name="fun-asr-nano",
+        config=NANO_MODEL_CONFIG,
+        suffix="fun-asr-nano",
+        use_itn=True,
+        sensevoice=False,
+    )
+
+
+if __name__ == "__main__":
+    main()