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/assembly_contract.py

View on GitHub
"""Assembly manifest/QC persistence and delivery contract helpers."""

import json
import math
import wave
from pathlib import Path

from lib import CONFIG
from assemble_constants import ASSEMBLY_MANIFEST, ASSEMBLY_QC
from loudness import _loudness_mode
from artifacts import _source_video_identity, _timeline_provenance_status


def _assembly_manifest_payload(input_video, tts_segments, work_dir, output_path,
                               tts_meta_path=None, final_output=None, *, settings_payload,
                               audio_mode="narration"):
    """Slim render record. The orchestrator reads `final_output` to report the result;
    `source_video` is set only when cut mode passed --source-video. QC results live in
    assembly_qc.json (`qc_path`), not here."""
    input_video = Path(input_video)
    output_path = Path(output_path)
    source_video_identity = _source_video_identity()
    qc_path = Path(work_dir) / ASSEMBLY_QC
    settings = settings_payload(work_dir, audio_mode=audio_mode)
    payload = {
        "schema_version": 2,
        "input_video": str(input_video.resolve()),
        "source_video": source_video_identity["path"] if source_video_identity else None,
        "source_video_identity": source_video_identity,
        "tts_meta": str(Path(tts_meta_path).resolve()) if tts_meta_path else None,
        "tts_segments": len(tts_segments),
        "audio_mode": audio_mode,
        "selected_audio_stream_index": 0,
        "assembly_settings": settings,
        "output_path": str(output_path.resolve()),
        "qc_path": str(qc_path.resolve()),
        "audio_segments": [
            {
                "index": seg["index"],
                # The loudness measurements are None whenever voiceover skipped normalization.
                "narration": seg["narration"],
                "spoken_text": seg["spoken_text"],
                "truncated": seg["truncated"],
                "truncate_reason": seg["truncate_reason"],
                "fit_status": seg["fit_status"],
                "blocking": seg["blocking"],
                "audio_duration": seg["audio_duration"],
                "placed_audio_duration": seg["placed_audio_duration"],
                "placed_audio_path": seg.get("placed_audio_path"),
                "actual_place_start": seg.get("actual_place_start"),
                "actual_place_end": seg.get("actual_place_end"),
                "source_duck_end": seg.get("source_duck_end"),
                "source_restore_at": seg.get("source_restore_at"),
                "source_handoff_status": seg.get("source_handoff_status"),
                "source_entry_status": seg.get("source_entry_status"),
                "written_start": seg.get("written_start"),
                "global_narration_speed": seg["global_narration_speed"],
                "segment_tempo_factor": seg["segment_tempo_factor"],
                "effective_tempo": seg["effective_tempo"],
                "rms_dbfs_before": seg.get("rms_dbfs_before"),
                "rms_dbfs_after": seg.get("rms_dbfs_after"),
                "peak_after": seg.get("peak_after"),
            }
            for seg in tts_segments
        ],
    }
    if final_output is not None:
        payload["final_output"] = str(Path(final_output).resolve())
    provenance = _timeline_provenance_status(work_dir)
    if provenance:
        payload["timeline_provenance"] = provenance
    return payload


def _write_assembly_manifest(work_dir, manifest):
    path = Path(work_dir) / ASSEMBLY_MANIFEST
    path.write_text(json.dumps(manifest, ensure_ascii=False, indent=2), encoding="utf-8")
    return path


def _placed_audio_matches_timeline(seg):
    """True when the persisted per-beat WAV is exactly what the serialized timeline window plays."""
    placed_path = Path(seg["placed_audio_path"])
    if not placed_path.exists():
        return False
    try:
        with wave.open(str(placed_path), "rb") as placed_wav:
            placed_duration = placed_wav.getnframes() / placed_wav.getframerate()
            tolerance = 1.0 / placed_wav.getframerate()
    except wave.Error:
        return False
    timeline_start = math.floor(float(seg["actual_place_start"]) * 10_000 + 1e-9) / 10_000
    timeline_end = math.ceil(float(seg["actual_place_end"]) * 10_000 - 1e-9) / 10_000
    serialized_span = timeline_end - timeline_start
    return (
        abs(placed_duration - seg["placed_audio_duration"]) <= tolerance + 1e-9
        and serialized_span + 1e-9 >= placed_duration
    )


def _build_assembly_qc(tts_segments, video_duration, *, audio_operations, render_delivery,
                       output_path=None, source_has_audio=None, loudness_mode=None,
                       loudnorm_measurement=None, loudnorm_final_pass=None,
                       visual_qc=None, audio_mode="narration"):
    """Machine-readable assembly release gate.

    Only visual_qc.json's verdict and blocking codes are carried here; its facts stay in
    visual_qc.json. Delivery/render facts live here, never in visual_qc.json.
    """
    hard_max = CONFIG["narration_cumulative_tempo_hard_max"]
    segments = tts_segments
    no_safe = [
        s["index"] for s in segments
        if s["fit_status"] == "no_safe_fit"
        or s["truncate_reason"] in {"no_safe_boundary", "no_room"}
        or s["blocking"]
    ]
    skipped = [s["index"] for s in segments if s["fit_status"] == "skipped"]
    tempo_exceeded = []
    truncated = []
    handoff_failed = []
    timeline_audio_failed = []
    max_effective = 0.0
    for s in segments:
        eff = float(s["effective_tempo"])
        max_effective = max(max_effective, eff)
        if eff > hard_max + 1e-6:
            tempo_exceeded.append(s["index"])
        if s["truncated"] or s["truncate_reason"] == "tail_trim_tolerance":
            truncated.append(s["index"])
        if s.get("source_handoff_blocking", False):
            handoff_failed.append(s["index"])
        if s["placed_audio_duration"] > 0 and not _placed_audio_matches_timeline(s):
            timeline_audio_failed.append(s["index"])

    placed = [s["placed_audio_duration"] for s in segments]
    # Information only: how long original audio stays ducked after each narration run ends.
    duck_holds = [
        float(s["source_restore_at"]) - float(s["actual_place_end"])
        for s in segments
        if s.get("source_restore_at") is not None and s.get("actual_place_end") is not None
    ]
    blocking_codes = []
    if audio_mode == "narration" and not segments:
        blocking_codes.append("missing_narration")
    if skipped:
        blocking_codes.append("skipped_segments")
    if no_safe:
        blocking_codes.append("no_safe_fit")
    if tempo_exceeded:
        blocking_codes.append("effective_tempo_exceeded")
    if truncated:
        blocking_codes.append("truncated_speech")
    if handoff_failed:
        blocking_codes.append("unsafe_source_handoff")
    if timeline_audio_failed:
        blocking_codes.append("timeline_audio_mismatch")
    if placed and max(placed) <= 0.0 and not no_safe:
        blocking_codes.append("empty_narration")
    delivered_peak = ((loudnorm_final_pass or {}).get("delivered") or {}).get("true_peak")
    if delivered_peak is not None and delivered_peak > float(CONFIG["target_true_peak"]):
        # The encoded file, not the PCM mix, is what must stay under TP (codec_peak.py).
        blocking_codes.append("delivered_true_peak_over_target")
    visual_verdict = (
        {"verdict": visual_qc["verdict"], "blocking_codes": list(visual_qc["blocking_codes"])}
        if visual_qc is not None
        else {"verdict": "NOT_RUN", "blocking_codes": []}
    )
    if visual_qc is not None and visual_qc["blocking"]:
        blocking_codes.append("visual_qc_failed")
    if source_has_audio is False:
        # Not blocking: assemble can synthesize a silent original track.
        source_audio = "synthetic_silence"
    elif source_has_audio is True:
        source_audio = "present"
    else:
        source_audio = "unknown"

    output = {}
    if output_path is not None:
        output_path = Path(output_path)
        output = {
            "path": str(output_path),
            "exists": output_path.exists(),
            "bytes": output_path.stat().st_size if output_path.exists() else 0,
        }
        if output_path.exists() and output["bytes"] <= 0:
            blocking_codes.append("empty_output")

    return {
        "schema_version": 1,
        "artifact": ASSEMBLY_QC,
        "verdict": "FAIL" if blocking_codes else "PASS",
        "blocking": bool(blocking_codes),
        "blocking_codes": blocking_codes,
        "duration": round(float(video_duration), 4),
        "audio_mode": audio_mode,
        "audio_operations": audio_operations,
        "source_audio": source_audio,
        "loudness_mode": loudness_mode or _loudness_mode(loudnorm_measurement),
        "loudnorm_measurement": loudnorm_measurement,
        "loudnorm_final_pass": loudnorm_final_pass,
        "visual_qc": visual_verdict,
        "delivery_qc": {
            "video_encode_passes": render_delivery["video_encode_passes"],
            "reencode_reason": render_delivery["reencode_reason"],
            "audio_sample_rate": render_delivery["audio_sample_rate"],
            "final_compat_notes": render_delivery["final_compat_notes"],
            "color_tags": render_delivery.get("color_tags"),
        },
        "summary": {
            "segments": len(segments),
            "placed_segments": sum(1 for x in placed if x > 0.0),
            "skipped_segments": skipped,
            "no_safe_fit_segments": no_safe,
            "tempo_exceeded_segments": tempo_exceeded,
            "max_effective_tempo": round(max_effective, 4),
            "truncated_segments": truncated,
            "unsafe_source_handoff_segments": handoff_failed,
            "timeline_audio_mismatch_segments": timeline_audio_failed,
            "max_source_duck_hold_seconds": (
                round(max(0.0, max(duck_holds)), 4) if duck_holds else None
            ),
        },
        "output": output,
    }


def _write_assembly_qc(work_dir, qc):
    path = Path(work_dir) / ASSEMBLY_QC
    path.write_text(json.dumps(qc, ensure_ascii=False, indent=2), encoding="utf-8")
    return path


def _resolve_final_output(base, stem):
    """The recap output is the stable human alias recap_<stem>.mp4, overwritten in place
    on every run so the iterate-on-narration loop always refreshes the same file."""
    return Path(base) / f"recap_{stem}.mp4"
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