zenstory-ai/video-recap-skills / skills/video-recap
video-recap
Verified把一段或多集视频做成带画框字幕的中文解说成片或纯原声高光短片。用户提供 .mp4 / .mov / .mkv / .webm,要求做影视解说、短剧二创、加旁白配音、跨集混剪或导出剪映草稿时使用;串联完成看片识台词、定主线与留原声、按台词停顿切镜头、写词检查、TTS 配音与混音加字幕。触发词:视频解说、影视解说、视频旁白、生成解说、视频 recap、video recap、voiceover、narration、recap。
scripts/jianying/schema.py
View on GitHub"""Schema constants and skeleton factories for JianYing export.
This module is intentionally data-oriented: it owns draft version metadata and
the full `materials` parallel-array shape.
"""
from jianying.templates import template
# The full 剪映 materials object: ~45 parallel arrays. Only arrays backed by a
# production builder are populated; retaining the full shape preserves compatibility.
MATERIAL_KEYS = ["ai_translates", "audio_balances", "audio_effects", "audio_fades", "audio_track_indexes", "audios", "beats", "canvases", "chromas", "color_curves", "digital_humans", "drafts", "effects", "flowers", "green_screens", "handwrites", "hsl", "images", "log_color_wheels", "loudnesses", "manual_deformations", "masks", "common_mask", "material_animations", "material_colors", "multi_language_refs", "placeholders", "plugin_effects", "primary_color_wheels", "realtime_denoises", "shapes", "smart_crops", "smart_relights", "sound_channel_mappings", "speeds", "stickers", "tail_leaders", "text_templates", "texts", "time_marks", "transitions", "video_effects", "video_trackings", "videos", "vocal_beautifys", "vocal_separations"]
def us(seconds):
"""Seconds (float) -> integer microseconds. The single seconds->µs boundary."""
return int(round(float(seconds) * 1_000_000))
def full_materials(filled):
"""Return a complete JianYing `materials` object with all known arrays."""
out = {k: [] for k in MATERIAL_KEYS}
out.update(filled)
return out
def scrub_platform_identity(project):
"""Remove hardware fingerprints carried by the pinned upstream templates."""
for platform_key in ("last_modified_platform", "platform"):
for identity_key in ("device_id", "hard_disk_id", "mac_address"):
project[platform_key][identity_key] = ""
return project
def draft_content_skeleton(draft_id, width, height, fps, total_us, materials, tracks):
"""Build the root `draft_content.json` / `draft_info.json` skeleton."""
content = template("project")
scrub_platform_identity(content)
content["canvas_config"] = {"width": width, "height": height, "ratio": "original"}
content["duration"] = int(total_us)
content["fps"] = float(fps)
content["id"] = draft_id
content["materials"] = full_materials(materials)
content["tracks"] = tracks
return content
def meta_info(draft_id, total_us):
"""Build the companion `draft_meta_info.json` skeleton."""
meta = template("meta")
meta["draft_id"] = draft_id
meta["draft_timeline_materials_size_"] = 0
meta["tm_duration"] = int(total_us)
return meta
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |