Commit Graph
7 Commits
Author SHA1 Message Date
nite 5e844d17ec feat: emphasize non-mandatory workflow, support transcription-only use case
SKILL.md:
- Workflow header: explicit statement that every step is optional
  Example: transcription-only → Steps 1,2,4,5 and stop
- When to Use: add standalone transcription as valid use case
- Don't use for: remove 'pure audio-only transcription' exclusion
- Verification checklist: each item tagged with which step it belongs to
  and whether it can be skipped (e.g. Step 3/8 skip for transcription-only)
2026-07-14 12:21:51 +08:00
nite e56723a68f feat: multi-track transcription support
SKILL.md:
- Step 2: user can provide multiple track indexes (e.g. mic + Discord)
- Step 4: transcribe each track separately, cross-reference all transcripts
- Step 5: get-transcription supports --track filter

manage_index.py:
- get-transcription: optional --track flag to filter by track index
- Without --track, returns all transcription records (was: latest only)
2026-07-14 12:19:42 +08:00
nite 8fbb7f176e feat: preserve multi-track audio in clip extraction
SKILL.md:
- Step 6: two clip modes — video-only (frame extraction) vs all-streams (editor use)
- Pitfall #10: warn about dropping audio tracks with default -map 0:v:0
- Note on keyframe accuracy vs frame-exact re-encode

extract_frames.py:
- New --all-streams flag on clip subcommand
- -map 0 preserves video + all audio tracks + subtitles
- Default remains -map 0:v:0 for fast frame extraction
2026-07-14 12:16:17 +08:00
nite 5f9e96de19 refine: README simplification + Fun-ASR-Nano as explicit default
README (EN + ZH):
- npx skills add: use HTTPS URL instead of SSH
- Remove 'First use' uv sync section (agent handles setup, not user)
- Remove 'Stock Material Search' section (workflow detail, belongs in SKILL.md)
- Keep README focused on overview + workflow, not implementation details
- Fun-ASR-Nano marked as default in Features

SKILL.md:
- Step 4: explicitly state Fun-ASR-Nano as recommended default model
2026-07-14 12:05:49 +08:00
nite b60931913b feat: add stock material search section + npx skills add install
- SKILL.md: new 'Finding stock materials' section (on-demand, not mandatory)
  - 5 material sources: 爱给网, B站素材酷, Tenor, GIPHY, Klipy
  - Language-based priority (Chinese users → 爱给网 + B站素材酷)
  - Semantic search term expansion guidance
  - B站素材酷: bcut-resource-search userscript or direct API
  - Anti-bot fallback: browser-based tools
- README.md + README.zh.md: add 'npx skills add' install method
  - Compatible with open agent skills ecosystem (73+ frameworks)
  - git clone as fallback option
  - New 'Stock Material Search' section
2026-07-14 12:00:39 +08:00
nite f8ecbadf1d docs: add bilingual README (English + Chinese) 2026-07-14 11:09:15 +08:00
nite a565382a52 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.
2026-07-14 11:07:57 +08:00