konradre/video-production-skills / skills/video-finish-qc
video-finish-qc
VerifiedRuns the FINISH of a whole spot from its EDL — part of every video job; a builder's render before it is PRE-FINISH — and the QC of the delivered master: the per-shot upscale tier (after approval and a cost line), the per-shot normalise, the hero pass, the three-stage finish (graded cut, master, deliverable), the finals run, and the one-pass QC (duration, loudness, true peak, cuts, take-cut leaks, VO placement, the finish against the previous version). Use when approved keepers must be upscaled, shots normalised, a hero pass is due, a spot must be rendered from its EDL, finals are requested, or a delivered file must be verified or sent. Triggers — "upscale the keepers", "run the hero pass", "normalise the shots", "apply the ads look", "has it been finished", "render the spot", "finish it", "final renders", "QC the deliverable", "rogue frames", "is the loudness right", "send me the 1080p", "starlight on the wides". Not for the per-clip ordering doctrine — use video-finish. Not for the cut or the beat gate — use video-edit-edl. Not for voicing or sourcing the sound — use spot-audio-assembly. Not for LUFS mastering of a standalone mix — use mastering-audio.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 32.3 KB |
| references/FAQ.md | markdown | 3.4 KB |
| references/PIPELINE.md | markdown | 13.7 KB |
| references/QC.md | markdown | 26.4 KB |
| scripts/aac_packet_clock.pyexecutable | script | 7.8 KB |
| scripts/decoded_checks.py | script | 65.1 KB |
| scripts/final_renders.shexecutable | script | 1.9 KB |
| scripts/finish_clip.pyexecutable | script | 11.9 KB |
| scripts/finish_spot.pyexecutable | script | 41.0 KB |
| scripts/hero_distinct.pyexecutable | script | 2.1 KB |
| scripts/hero_pass.shexecutable | script | 3.8 KB |
| scripts/look_sheet.py | script | 9.7 KB |
| scripts/matrix_check.pyexecutable | script | 23.6 KB |
| scripts/normalise_shots.pyexecutable | script | 18.9 KB |
| scripts/phone_texture_probe.py | script | 7.0 KB |
| scripts/qc_deliverable.pyexecutable | script | 61.8 KB |
| scripts/upscale_fal_topaz.pyexecutable | script | 8.5 KB |
| scripts/upscale_local.shexecutable | script | 3.4 KB |
scripts/upscale_local.sh
View on GitHub#!/usr/bin/env bash
# upscale_local.sh — the local reconstructive upscale (Topaz Rhea ×4 by default) on OPERATOR-APPROVED takes only, one after
# another, through the topaz_upscale tool; writes <out-dir>/<stem>__<model>x<scale>.mp4 and prints RHEA-OK/RHEA-FAILED per
# take and the sentinel UPSCALE-LOCAL-END. A log without the sentinel is a failure whatever the file sizes say.
# RHEA-OK needs the TOOL's verdict (exit 0 + TOPAZ-UPSCALE-OK) and the file; the line names the encoder and pixel format, and
# an 8-bit result (the ladder's h264 rung) is flagged — a file on disk once passed as OK after the tool had failed (2026-10-28).
# The tool's full output goes to <out-dir>/<stem>__<model>x<scale>.log; the script exits 1 when any take failed.
# Every take must trace to the operator's recorded pick (video-production/scripts/pick_gate.py) — else PICK-GATE-REFUSED, exit 3.
# Run it DETACHED (video-production/scripts/detach.py) with every path absolute — a Bash-backgrounded run has a 10-minute cap and a
# truncated mezzanine silently shortens the deliverable. Poll the log on demand; never follow it.
#
# upscale_local.sh --root <project> [--model rhea-1] [--scale 4] [--out-dir edit/upscale-out] [--tool <topaz_upscale.py>] takes/A.mp4 takes/B.mp4 …
# --tool defaults to $TOPAZ_UPSCALE_PY or the repository's tools/topaz-upscale/topaz_upscale.py (resolved from this script's real path)
set -u
ROOT="."; MODEL="rhea-1"; SCALE="4"; OUT="edit/upscale-out"; TOOL="${TOPAZ_UPSCALE_PY:-$(dirname "$(readlink -f "$0")")/../../../tools/topaz-upscale/topaz_upscale.py}"; TAKES=()
while [ $# -gt 0 ]; do case "$1" in
--root) ROOT="$2"; shift 2;; --model) MODEL="$2"; shift 2;; --scale) SCALE="$2"; shift 2;; --out-dir) OUT="$2"; shift 2;; --tool) TOOL="$2"; shift 2;;
-h|--help) sed -n '2,10p' "$0"; exit 0;; *) TAKES+=("$1"); shift;; esac; done
[ ${#TAKES[@]} -gt 0 ] || { echo "no takes given"; exit 2; }; [ -f "$TOOL" ] || { echo "upscale tool not found: $TOOL (set --tool or TOPAZ_UPSCALE_PY)"; exit 2; }
ROOT=$(cd "$ROOT" && pwd)
GATE="$(cd "$(dirname "$0")" && pwd)/../../video-production/scripts/pick_gate.py" # the pick, checked in code before any work
python3 "$GATE" check --root "$ROOT" "${TAKES[@]}" || { echo "[$(date +%H:%M:%S)] PICK-GATE-REFUSED — record the operator's pick first (pick_gate.py record / derive)"; exit 3; }
mkdir -p "$ROOT/$OUT"; FAILS=0
for T in "${TAKES[@]}"; do
stem=$(basename "$T" .mp4); echo "[$(date +%H:%M:%S)] UPSCALE $stem ($MODEL x$SCALE)"
UP="$ROOT/$OUT/${stem}__${MODEL}x${SCALE}.mp4"; TLOG="${UP%.mp4}.log"
python3 "$TOOL" --in "$ROOT/$T" --model "$MODEL" --scale "$SCALE" --out-dir "$ROOT/$OUT" > "$TLOG" 2>&1; RC=$?
tail -3 "$TLOG"
ENC=$(sed -n 's/.*"encoder": "\([^"]*\)".*/\1/p' "$TLOG" | tail -1)
if [ $RC -eq 0 ] && [ "$(tail -1 "$TLOG")" = "TOPAZ-UPSCALE-OK" ] && [ -s "$UP" ]; then
PIX=$(ffprobe -v error -select_streams v:0 -show_entries stream=pix_fmt -of csv=p=0 "$UP" 2>/dev/null)
case "$PIX" in *10le|*10be|p010*) B="";; '') B=" ⚠ pixel format unknown (ffprobe failed) — check the file by hand";; *) B=" ⚠ 8-BIT ($PIX) — the 10-bit rung failed; read $TLOG";; esac
echo "[$(date +%H:%M:%S)] RHEA-OK $stem ← $(basename "$UP") (${ENC:-?}, ${PIX:-?})$B"
else
FAILS=$((FAILS + 1)); echo "[$(date +%H:%M:%S)] RHEA-FAILED $stem (tool exit $RC, $(tail -1 "$TLOG")) — read $TLOG"
fi
done
echo "[$(date +%H:%M:%S)] UPSCALE-LOCAL-END"
[ $FAILS -eq 0 ]
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 |