Skip to content

Mr-funny/hbg-classical-poem-silk-video / skill/classical-poem-silk-video

classical-poem-silk-video

Verified

Turn 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.

FileKindSize
SKILL.mdskill md6.5 KB
agents/openai.yamlconfig275 B
assets/MaShanZheng-Regular.ttfbinary5.6 MB
assets/OFL.txtmarkdown4.2 KB
references/runtime-contract.mdmarkdown1.9 KB
references/style-and-scene-mapping.mdmarkdown6.2 KB
scripts/check_prerequisites.shexecutablescript1.5 KB
scripts/clean_star_watermark.shexecutablescript861 B
scripts/concat_poem.shexecutablescript1.3 KB
scripts/concat_poem_crossfade.shexecutablescript2.0 KB
scripts/docker_gemini_i2v.pyexecutablescript2.7 KB
scripts/docker_gemini_i2v.shexecutablescript970 B
scripts/final_media_qa.shexecutablescript3.6 KB
scripts/make_scene_ass.pyexecutablescript2.7 KB
scripts/render_scene.shexecutablescript1.8 KB

references/runtime-contract.md

View on GitHub
# Runtime contract

Use this reference when preparing a machine for the skill or diagnosing a missing Docker runtime.

## Host requirements

- Codex with the built-in `image_gen` tool for still-frame generation.
- Docker, FFmpeg, ffprobe, Python 3, and ripgrep.
- The open-source [HBG Gemini Flow Suite](https://github.com/Mr-funny/hbg-gemini-flow-suite), running as a container named `gemini-flow-suite`.
- A workspace bind-mounted read-only at `/workspace` inside the container.
- A writable output mount at `/data/outputs` inside the container and at `outputs/gemini-flow-suite` in the host workspace.

Run `scripts/check_prerequisites.sh` from the active project before generating media.

## Container requirements

The container must provide:

- `/opt/gemini-venv/bin/python` with `gemini_webapi` installed.
- A pre-authorized Gemini cookie file at `/data/auth/gemini/cookies.json`.
- `veo-watermark-remover` when optional white sparkle cleanup is requested.

The skill never reads or prints cookie values. Authorization is a separate one-time user-controlled setup. Actual poem-video generation must use Docker commands and must not open or control the host browser.

## Setup outline

```bash
git clone https://github.com/Mr-funny/hbg-gemini-flow-suite.git
cd hbg-gemini-flow-suite
cp .env.example .env
docker compose up -d --build
./suite auth gemini
```

Follow the runtime repository's README for current authorization and mount configuration. Never commit `.env`, cookies, Chrome profiles, exported Docker volumes, generated media, or provider credentials.

## Optional watermark cleanup

Only remove the provider's white sparkle/diamond overlay when the user requests it and applicable terms permit it. Preserve traditional red seals and intentional painting marks. Skip this step when the cleanup tool is unavailable or inappropriate; report the limitation rather than silently altering another region.
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
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: 198kUpdated Claude CodeCodexVerifiedInstall