Mr-funny/hbg-classical-poem-silk-video / skill/classical-poem-silk-video
classical-poem-silk-video
VerifiedTurn Chinese classical poems and ci into coherent vertical Chinese-art videos with poem-driven scene grouping, GPT ImageGen stills, Docker-only Gemini I2V, retained model-generated ambience, Gemini sparkle-watermark cleanup, brush-calligraphy captions revealed character by character, optional local BGM mixing, stitching, and final-frame QA. Supports verse-driven variation across ink landscape, gongbi bird-and-flower, colored figure-and-horse painting, blue-green landscape, xuan paper, silk, and related Chinese visual languages. Use when users ask for 古诗词动态视频、诗词逐句或两句一景、国风视频、毛笔字逐字出现、整首诗拼接成片,or want the established 月落乌啼霜满天 workflow applied to another poem.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.5 KB |
| agents/openai.yaml | config | 275 B |
| assets/MaShanZheng-Regular.ttf | binary | 5.6 MB |
| assets/OFL.txt | markdown | 4.2 KB |
| references/runtime-contract.md | markdown | 1.9 KB |
| references/style-and-scene-mapping.md | markdown | 6.2 KB |
| scripts/check_prerequisites.shexecutable | script | 1.5 KB |
| scripts/clean_star_watermark.shexecutable | script | 861 B |
| scripts/concat_poem.shexecutable | script | 1.3 KB |
| scripts/concat_poem_crossfade.shexecutable | script | 2.0 KB |
| scripts/docker_gemini_i2v.pyexecutable | script | 2.7 KB |
| scripts/docker_gemini_i2v.shexecutable | script | 970 B |
| scripts/final_media_qa.shexecutable | script | 3.6 KB |
| scripts/make_scene_ass.pyexecutable | script | 2.7 KB |
| scripts/render_scene.shexecutable | script | 1.8 KB |
scripts/final_media_qa.sh
View on GitHub#!/usr/bin/env bash
set -euo pipefail
if [ "$#" -lt 2 ] || [ "$#" -gt 3 ]; then
echo "Usage: $0 <final-video.mp4> <qa-output-dir> [timestamps.tsv]" >&2
exit 2
fi
video="$1"
qa_dir="$2"
timestamps_file="${3:-}"
test -f "$video" || { echo "Video not found: $video" >&2; exit 2; }
mkdir -p "$qa_dir/frames"
ffprobe -v error -show_streams -show_format -of json "$video" > "$qa_dir/ffprobe.json"
ffmpeg -hide_banner -nostats -i "$video" -vf 'blackdetect=d=0.15:pix_th=0.10' -an -f null - 2> "$qa_dir/blackdetect.log" || true
ffmpeg -hide_banner -nostats -i "$video" -map 0:a:0 -af 'silencedetect=n=-45dB:d=1.0' -f null - 2> "$qa_dir/silencedetect.log" || true
ffmpeg -hide_banner -nostats -i "$video" -map 0:a:0 -af volumedetect -f null - 2> "$qa_dir/volumedetect.log" || true
duration="$(ffprobe -v error -show_entries format=duration -of default=nw=1:nk=1 "$video")"
for item in '0.10:p10' '0.25:p25' '0.50:p50' '0.75:p75' '0.90:p90'; do
ratio="${item%%:*}"
label="${item##*:}"
timestamp="$(awk -v d="$duration" -v r="$ratio" 'BEGIN { printf "%.3f", d * r }')"
ffmpeg -hide_banner -loglevel error -y -ss "$timestamp" -i "$video" -frames:v 1 "$qa_dir/frames/$label.png"
done
last_timestamp="$(awk -v d="$duration" 'BEGIN { printf "%.3f", (d > 0.08 ? d - 0.08 : 0) }')"
ffmpeg -hide_banner -loglevel error -y -ss "$last_timestamp" -i "$video" -frames:v 1 "$qa_dir/frames/last.png"
if [ -n "$timestamps_file" ]; then
test -f "$timestamps_file" || { echo "Timestamp file not found: $timestamps_file" >&2; exit 2; }
while IFS=$'\t' read -r timestamp label; do
[ -n "${timestamp:-}" ] || continue
case "$timestamp" in \#*) continue ;; esac
safe_label="$(printf '%s' "${label:-frame}" | tr -cs 'A-Za-z0-9._-' '-')"
ffmpeg -hide_banner -loglevel error -y -ss "$timestamp" -i "$video" -frames:v 1 "$qa_dir/frames/$safe_label.png"
done < "$timestamps_file"
fi
ffmpeg -hide_banner -loglevel error -y \
-i "$qa_dir/frames/p10.png" -i "$qa_dir/frames/p25.png" \
-i "$qa_dir/frames/p50.png" -i "$qa_dir/frames/p75.png" \
-i "$qa_dir/frames/p90.png" -i "$qa_dir/frames/last.png" \
-filter_complex '[0:v]scale=270:480[a];[1:v]scale=270:480[b];[2:v]scale=270:480[c];[3:v]scale=270:480[d];[4:v]scale=270:480[e];[5:v]scale=270:480[f];[a][b][c]hstack=3[top];[d][e][f]hstack=3[bottom];[top][bottom]vstack=2[out]' \
-map '[out]' -frames:v 1 "$qa_dir/contact-sheet.png"
python3 - "$qa_dir/ffprobe.json" <<'PY'
import json
import math
import sys
payload = json.load(open(sys.argv[1], encoding="utf-8"))
streams = payload.get("streams", [])
video = next((s for s in streams if s.get("codec_type") == "video"), None)
audio = next((s for s in streams if s.get("codec_type") == "audio"), None)
errors = []
if not video:
errors.append("missing video stream")
else:
if video.get("codec_name") != "h264":
errors.append(f"video codec is {video.get('codec_name')}, expected h264")
if (video.get("width"), video.get("height")) != (1080, 1920):
errors.append(f"video size is {video.get('width')}x{video.get('height')}, expected 1080x1920")
rate = video.get("avg_frame_rate") or video.get("r_frame_rate") or "0/1"
numerator, denominator = (float(part) for part in rate.split("/", 1))
fps = numerator / denominator if denominator else 0.0
if not math.isclose(fps, 30.0, abs_tol=0.05):
errors.append(f"frame rate is {fps:.3f}, expected 30")
if not audio:
errors.append("missing audio stream")
elif audio.get("codec_name") != "aac":
errors.append(f"audio codec is {audio.get('codec_name')}, expected aac")
if errors:
raise SystemExit("; ".join(errors))
print("media contract passed: H.264/AAC, 1080x1920, 30 fps")
PY
printf 'QA artifacts: %s\n' "$qa_dir"
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |