Skip to content

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。

FileKindSize
SKILL.mdskill md18.4 KB
assets/dashboard/app.jsscript16.2 KB
assets/dashboard/index.htmlother867 B
assets/dashboard/styles.cssother22.6 KB
assets/dashboard/tokens.cssother8.9 KB
assets/dashboard/views.jsscript31.4 KB
references/audio-modes.mdmarkdown3.6 KB
references/config-playbook.mdmarkdown8.1 KB
references/creative-editing-playbook.mdmarkdown12.3 KB
references/data-schema.mdmarkdown34.6 KB
references/index-tts.mdmarkdown2.1 KB
references/jianying/LICENSE.duo-videoother1.0 KB
references/jianying/SOURCE.mdmarkdown703 B
references/jianying/empty_draft_meta_info.jsonconfig1.7 KB
references/jianying/empty_jy_material_video.jsonconfig1.8 KB
references/jianying/empty_jy_meta_material_value.jsonconfig358 B
references/jianying/empty_jy_project_info.jsonconfig3.6 KB
references/jianying/empty_jy_segment.jsonconfig1.3 KB
references/jianying/empty_jy_text_styles.jsonconfig440 B
references/jianying/empty_yj_material_audio.jsonconfig865 B
references/jianying/empty_yj_material_text.jsonconfig2.4 KB
references/packaging.mdmarkdown6.8 KB
references/promotional-copy.mdmarkdown4.1 KB
references/prompt-templates.mdmarkdown2.0 KB
references/research-guide.mdmarkdown2.7 KB
references/resource-library.mdmarkdown12.1 KB
references/shot-review.mdmarkdown4.8 KB
scripts/agent_text.pyscript2.7 KB
scripts/artifacts.pyscript972 B
scripts/asr.pyscript12.5 KB
scripts/asr_timing_evidence.pyscript4.2 KB
scripts/assemble.pyscript31.0 KB
scripts/assemble_constants.pyscript894 B
scripts/assembly_contract.pyscript10.3 KB
scripts/assembly_settings.pyscript3.8 KB
scripts/audio_automation.pyscript6.6 KB
scripts/audio_mix.pyscript18.5 KB
scripts/briefing/__init__.pyscript101 B
scripts/briefing/builder.pyscript31.1 KB
scripts/briefing/context.pyscript6.1 KB
scripts/briefing/timeline.pyscript23.0 KB
scripts/codec_peak.pyscript5.1 KB
scripts/cut.pyscript148 B
scripts/cut_cli.pyscript12.4 KB
scripts/cut_contract.pyscript13.3 KB
scripts/cut_qc.pyscript1.9 KB
scripts/cut_render.pyscript13.2 KB
scripts/dashboard/__init__.pyscript159 B
scripts/dashboard/data.pyscript24.6 KB
scripts/dashboard/io.pyscript7.1 KB
scripts/dashboard/runs.pyscript21.8 KB
scripts/dashboard/templates.pyscript9.6 KB
scripts/dashboard_server.pyscript9.3 KB
scripts/detect.pyscript22.2 KB
scripts/doctor.pyexecutablescript12.9 KB
scripts/entry_suggestion.pyscript4.6 KB
scripts/export_jianying.pyscript5.6 KB
scripts/extract.pyscript2.5 KB
scripts/final_qc.pyscript19.0 KB
scripts/frame_grid.pyscript10.6 KB
scripts/jianying/__init__.pyscript49 B
scripts/jianying/builders.pyscript11.3 KB
scripts/jianying/model.pyscript2.7 KB
scripts/jianying/optional.pyscript1012 B
scripts/jianying/schema.pyscript2.5 KB
scripts/jianying/templates.pyscript1.0 KB
scripts/jianying/timeline_contract.pyscript5.8 KB
scripts/jianying/tracks.pyscript2.0 KB
scripts/jianying/writer.pyscript7.8 KB
scripts/lib.pyscript29.6 KB
scripts/library.pyscript31.1 KB
scripts/lint_summary.pyscript5.0 KB
scripts/loudness.pyscript14.7 KB
scripts/materials.pyscript22.1 KB
scripts/media.pyscript18.8 KB
scripts/narration_audio.pyscript13.5 KB
scripts/narration_lint.pyscript24.1 KB
scripts/narrative_selection.pyscript8.9 KB
scripts/packaging.pyscript6.1 KB
scripts/packaging_fonts.pyscript12.0 KB
scripts/packaging_plates.pyscript31.2 KB
scripts/packaging_studio.pyscript34.1 KB
scripts/providers/__init__.pyscript72 B
scripts/providers/fish_audio.pyscript3.1 KB
scripts/providers/index_tts.pyscript8.8 KB
scripts/recap.pyscript183 B
scripts/recap_cli.pyscript6.9 KB
scripts/recap_inspect.pyscript16.5 KB
scripts/recap_runner.pyscript22.0 KB
scripts/recap_runtime.pyscript11.8 KB
scripts/recap_source.pyscript1.8 KB
scripts/recap_stage_qc.pyscript2.7 KB
scripts/recap_timeline.pyscript7.7 KB
scripts/render_preflight.pyscript1.7 KB
scripts/resources/__init__.pyscript200 B
scripts/resources/lock.pyscript6.8 KB
scripts/resources/project_binding.pyscript16.1 KB
scripts/sentence_boundaries.pyscript28.8 KB
scripts/sentence_gate.pyscript8.6 KB
scripts/sfx_mix.pyscript14.6 KB
scripts/shot_review.pyscript18.9 KB
scripts/source_subtitles.pyscript7.2 KB
scripts/speech_ownership.pyscript9.3 KB
scripts/storyboard.pyscript21.8 KB
scripts/subtitles/__init__.pyscript56 B
scripts/subtitles/core.pyscript19.0 KB
scripts/subtitles/render.pyscript8.0 KB
scripts/timeline.pyscript8.2 KB
scripts/timeline_emit.pyscript5.4 KB
scripts/tts_audio.pyscript9.6 KB
scripts/tts_cache.pyscript4.5 KB
scripts/understand.pyscript171 B
scripts/understanding_brief.pyscript6.3 KB
scripts/understanding_cache.pyscript8.0 KB
scripts/understanding_runner.pyscript9.8 KB
scripts/understanding_storyboard.pyscript11.9 KB
scripts/validate.pyscript5.7 KB
scripts/visual_render.pyscript10.1 KB
scripts/vlm.pyscript16.4 KB
scripts/voiceover.pyscript28.0 KB

scripts/codec_peak.py

View on GitHub
"""Delivered true peak: measure the encoded file and correct an AAC overshoot over TP.

The loudness stage keeps the PCM mix under its true-peak target, but the lossy AAC encode
adds overshoot (0.3-1.4 dB at 192 kb/s on real renders, most on heavily limited mixes), so
the delivered file can sit over TP while the stage reported -1.1 dBTP. The first render
aims `loudness.CODEC_PEAK_HEADROOM_DB` under TP; `deliver_under_true_peak` then decodes
the delivered audio, and while its true peak is still over TP lowers the pre-encode target
by the measured overshoot plus CODEC_PEAK_MARGIN_DB and re-encodes only the audio (the
video stream is copied from the render), at most CODEC_PEAK_MAX_CORRECTIONS times.
"""

import os
from pathlib import Path

import assemble_constants as constants
import lib
from lib import CONFIG, filter_file_args, log
from loudness import (
    _loudnorm_first_pass_filter, _loudnorm_summary_value, _parse_loudnorm_json,
)

CODEC_PEAK_MARGIN_DB = 0.1
CODEC_PEAK_MAX_CORRECTIONS = 4


def delivered_loudness(path):
    """Integrated loudness and true peak of the file's first audio stream, or None.

    The true peak is the higher of loudnorm's and ebur128's readings of the decoded audio:
    the two oversampling detectors disagree by up to about 1 dB on dense transients.
    """
    result = lib.run_cmd([
        "ffmpeg", "-hide_banner", "-nostats", "-i", str(path), "-map", "0:a:0",
        "-af", f"ebur128=peak=true:framelog=quiet,{_loudnorm_first_pass_filter()}",
        "-f", "null", "-",
    ])
    text = f"{result.stdout or ''}\n{result.stderr or ''}"
    measured = _parse_loudnorm_json(text) if result.returncode == 0 else None
    ebur128_peak = _loudnorm_summary_value(text.split("Summary:")[-1], "Peak")
    try:
        integrated, true_peak = float(measured["input_i"]), float(measured["input_tp"])
    except (KeyError, TypeError, ValueError):
        log(f"  ⚠️ 成片真峰值测量失败: {path}")
        return None
    if ebur128_peak is not None:
        true_peak = max(true_peak, ebur128_peak)
    return {"integrated": integrated, "true_peak": true_peak}


def deliver_under_true_peak(output_path, peak_target, reencode_audio):
    """Re-encode the delivered audio until its true peak is under TP; returns (record, state).

    `reencode_audio(peak_target)` renders the audio again for the lower pre-encode target
    into `output_path` and returns its state; `state` is the last one (None when no
    correction ran). `record` holds the delivered `integrated` / `true_peak` (None when
    unmeasured), the final `peak_target_dbtp` and the number of `corrections`.
    """
    true_peak = float(CONFIG["target_true_peak"])
    delivered = delivered_loudness(output_path)
    state = None
    corrections = 0
    while (delivered is not None and delivered["true_peak"] > true_peak
           and corrections < CODEC_PEAK_MAX_CORRECTIONS):
        overshoot = delivered["true_peak"] - true_peak
        peak_target = round(peak_target - overshoot - CODEC_PEAK_MARGIN_DB, 2)
        log(f"  成片 AAC 真峰值 {delivered['true_peak']} dBTP 超过 {true_peak},"
            f"编码前目标降到 {peak_target} dBTP 后重编码音频")
        state = reencode_audio(peak_target)
        corrections += 1
        delivered = delivered_loudness(output_path)
    return {
        "integrated": delivered["integrated"] if delivered else None,
        "true_peak": delivered["true_peak"] if delivered else None,
        "peak_target_dbtp": peak_target,
        "corrections": corrections,
    }, state


def reencode_audio_track(output_path, inputs, filter_complex, audio_map, video_duration,
                         work_dir):
    """Replace `output_path`'s audio with `audio_map` rendered from `inputs`, copying its video.

    `inputs` are the render's own input arguments, so `filter_complex` keeps its indices;
    the rendered file is appended as the last input. Returns ffmpeg's stderr.
    """
    output_path = Path(output_path)
    video_index = inputs.count("-i")
    candidate = output_path.with_name(f".{output_path.stem}.audio-reencode{output_path.suffix}")
    script = None
    if len(filter_complex.encode("utf-8")) > constants.FILTER_SCRIPT_THRESHOLD_BYTES:
        script = Path(work_dir) / ".filter_complex_reencode.txt"
        script.write_text(filter_complex, encoding="utf-8")
        filter_args = filter_file_args("filter_complex", script)
    else:
        filter_args = ["-filter_complex", filter_complex]
    cmd = [
        "ffmpeg", "-y", *inputs, "-i", str(output_path), *filter_args,
        "-map", f"{video_index}:v:0", "-map", audio_map, "-c:v", "copy",
        "-map_metadata", "-1", "-map_chapters", "-1",
        "-c:a", "aac", "-b:a", "192k", "-ar", "48000", "-movflags", "+faststart",
        "-t", str(video_duration), str(candidate),
    ]
    try:
        result = lib.run_cmd(cmd)
        if result.returncode != 0:
            raise RuntimeError(f"成片音频重编码失败: {result.stderr}")
        os.replace(candidate, output_path)
    finally:
        candidate.unlink(missing_ok=True)
        if script is not None:
            script.unlink(missing_ok=True)
    return result.stderr
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: 198kUpdated Claude CodeCodexVerifiedInstall
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: 196kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
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: 196kUpdated Claude CodeCodexVerifiedInstall