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/understanding_cache.py
View on GitHub"""Own understanding-stage cache keys, provenance, and statuses."""
import json
from pathlib import Path
from asr_timing_evidence import (
EVIDENCE_FILENAME,
_identity as _artifact_identity,
validate_asr_timing_evidence,
)
from extract import FRAME_TIME_CONVENTION_VERSION
from lib import (
CONFIG,
file_identity,
offline_ignored_settings,
)
from vlm import vlm_prompt_payload
def _artifact_meta_path(artifact_path):
artifact_path = Path(artifact_path)
return artifact_path.with_name(f"{artifact_path.name}.meta.json")
def _load_json(path):
return json.loads(Path(path).read_text(encoding="utf-8"))
def _video_input(video_path):
"""The source video as a cache input: resolved path plus {size, mtime_ns}, so two
different files written in the same timestamp tick never share a stage output."""
return {"path": str(Path(video_path).resolve()), **file_identity(video_path)}
def _without_settings(meta, keys):
settings = meta.get("settings")
if not keys or not isinstance(settings, dict):
return meta
return {**meta, "settings": {k: v for k, v in settings.items() if k not in keys}}
def _stage_cache_valid(artifact_path, expected_meta, *, ignore_settings=()):
"""A stage output is reusable when it exists, is non-empty, its sidecar equals the
expected inputs/settings dict, and the output itself is the one the sidecar recorded.
`ignore_settings` names `settings` keys left out of the comparison on both sides (an
endpoint URL that only reflects which credential is set, or a retired legacy key)."""
artifact_path = Path(artifact_path)
if not artifact_path.exists() or artifact_path.stat().st_size == 0:
return False
meta_path = _artifact_meta_path(artifact_path)
if not meta_path.exists():
return False
try:
meta = _load_json(meta_path)
except (OSError, ValueError, TypeError):
return False
if not isinstance(meta, dict) or meta.get("artifact") != file_identity(artifact_path):
return False
expected = dict(expected_meta)
expected["artifact"] = meta["artifact"]
return _without_settings(meta, ignore_settings) == _without_settings(
expected, ignore_settings
)
def _write_stage_meta(artifact_path, meta):
meta_path = _artifact_meta_path(artifact_path)
payload = dict(meta)
payload["artifact"] = _artifact_identity(artifact_path)
meta_path.write_text(
json.dumps(payload, ensure_ascii=False, indent=2), encoding="utf-8"
)
def _remove_stage_meta(artifact_path):
_artifact_meta_path(artifact_path).unlink(missing_ok=True)
def _scene_cache_payload(video_path):
return {
"schema_version": 1,
"stage": "scenes",
"inputs": {"video": _video_input(video_path)},
"settings": {
"scene_threshold": CONFIG.get("scene_threshold"),
"scene_junk_filter": CONFIG.get("scene_junk_filter"),
"scene_junk_dark_luma": CONFIG.get("scene_junk_dark_luma"),
"scene_junk_bright_luma": CONFIG.get("scene_junk_bright_luma"),
"scene_junk_pixel_ratio": CONFIG.get("scene_junk_pixel_ratio"),
},
}
def _asr_cache_payload(video_path, *, skip_asr=False):
return {
"schema_version": 2,
"stage": "asr",
"inputs": {"video": _video_input(video_path)},
"settings": {
"skip_asr": bool(skip_asr),
"mimo_asr_api_url": CONFIG.get("mimo_asr_api_url"),
"mimo_asr_model": CONFIG.get("mimo_asr_model"),
"mimo_asr_language": CONFIG.get("mimo_asr_language"),
"mimo_asr_base64_max_mb": CONFIG.get("mimo_asr_base64_max_mb"),
"asr_segment_seconds": CONFIG.get("asr_segment_seconds"),
},
}
def _asr_cache_state(artifact_path, expected_meta, video_path):
"""Classify an ASR cache without upgrading stale evidence into new authority."""
artifact_path = Path(artifact_path)
ignored = offline_ignored_settings(CONFIG.get("mimo_asr_api_key"), "mimo_asr_api_url")
if not _stage_cache_valid(artifact_path, expected_meta, ignore_settings=ignored):
return "MISS"
evidence_path = artifact_path.parent / EVIDENCE_FILENAME
if validate_asr_timing_evidence(evidence_path, video_path, artifact_path):
evidence = _load_json(evidence_path)
# An all-empty transcription is an unexplained outcome, not proven silence; treating it
# as fresh would make one bad run a permanent cache hit. A key-less placeholder is
# retried too, so setting the key later transcribes for real.
if evidence.get("status") in {
"UNAVAILABLE_NO_DURATION", "EMPTY_UNKNOWN", "UNAVAILABLE_NO_KEY"
}:
return "MISS"
return "FRESH"
return "MISS"
def _silence_cache_payload(video_path, asr_json):
return {
"schema_version": 1,
"stage": "silence",
"inputs": {
"video": _video_input(video_path),
"asr_result": _artifact_identity(asr_json),
},
"asr_meta": _load_json(_artifact_meta_path(asr_json))
if _artifact_meta_path(asr_json).exists()
else None,
"settings": {
"silence_noise_threshold": CONFIG.get("silence_noise_threshold"),
"silence_min_duration": CONFIG.get("silence_min_duration"),
"quiet_window_min": CONFIG.get("quiet_window_min"),
"silence_merge_gap": CONFIG.get("silence_merge_gap"),
"source_boundary_noise_threshold": CONFIG.get(
"source_boundary_noise_threshold"
),
"source_boundary_min_pause": CONFIG.get("source_boundary_min_pause"),
"source_boundary_max_alignment_error": CONFIG.get(
"source_boundary_max_alignment_error"
),
},
}
def _vlm_cache_payload(video_path, work_dir, scenes_json, frames):
return {
"schema_version": 1,
"stage": "vlm",
"inputs": {
"video": _video_input(video_path),
"scenes": _artifact_identity(scenes_json),
"background_research": _artifact_identity(
Path(work_dir) / "background_research.json"
),
},
"frames": _frame_cache_payload(video_path, CONFIG.get("fps"), frames),
"prompt": vlm_prompt_payload(),
"settings": {
"fps": CONFIG.get("fps"),
"vlm_model": CONFIG.get("vlm_model"),
"api_url": CONFIG.get("api_url"),
"mimo_disable_thinking": CONFIG.get("mimo_disable_thinking", True),
"mimo_media_resolution": CONFIG.get("mimo_media_resolution"),
},
}
def _frames_manifest_path(work_dir):
return Path(work_dir) / "frames" / "frames_manifest.json"
def _frame_cache_payload(video_path, fps, frames):
frame_names = [Path(frame).name for frame in frames]
return {
# v2: frame number→time is (n-1)/fps, not n/fps. Bumping invalidates frames/VLM
# artifacts produced under the old off-by-one so they are recomputed, not reused.
"schema_version": FRAME_TIME_CONVENTION_VERSION,
"inputs": {"video": _video_input(video_path)},
"fps": float(fps),
"frame_count": len(frames),
"frames": frame_names,
}
def _write_frames_manifest(work_dir, video_path, fps, frames):
manifest_path = _frames_manifest_path(work_dir)
manifest_path.parent.mkdir(parents=True, exist_ok=True)
manifest_path.write_text(
json.dumps(
_frame_cache_payload(video_path, fps, frames), ensure_ascii=False, indent=2
),
encoding="utf-8",
)
def _frames_cache_valid(video_path, work_dir, fps):
frames_dir = Path(work_dir) / "frames"
frames = sorted(frames_dir.glob("frame_*.jpg"))
if not frames:
return False
manifest_path = _frames_manifest_path(work_dir)
if not manifest_path.exists():
return False
try:
manifest = json.loads(manifest_path.read_text(encoding="utf-8"))
expected = _frame_cache_payload(video_path, fps, frames)
except (OSError, ValueError, TypeError):
return False
return manifest == expected
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 |