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/pyproject.toml

@@ -0,0 +1,25 @@
+[project]
+name = "funasr-script"
+version = "0.1.0"
+description = "Small local FunASR transcription scripts for extracting a video audio track and writing JSON transcripts."
+readme = "README.md"
+requires-python = ">=3.13"
+dependencies = [
+    "funasr>=1.3.14",
+    "soundfile>=0.13.1",
+    "torch>=2.13.0",
+    "torchaudio>=2.11.0",
+]
+
+[project.scripts]
+funasr-script = "funasr_nano:main"
+funasr-nano = "funasr_nano:main"
+funasr-fast = "funasr_fast:main"
+funasr-regular = "funasr_regular:main"
+
+[build-system]
+requires = ["setuptools>=69"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools]
+py-modules = ["funasr_common", "funasr_regular", "funasr_fast", "funasr_nano", "main"]