Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add binggandata/bggg-skills --skill bggg-tiktok-cutgit clone --depth 1 https://github.com/binggandata/bggg-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/binggandata/bggg-skills/bggg-tiktok-cut)<a href="https://agentmods.dev/skills/binggandata/bggg-skills/bggg-tiktok-cut"><img src="https://agentmods.dev/badge/skills/binggandata/bggg-skills/bggg-tiktok-cut/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/binggandata/bggg-skills/bggg-tiktok-cut"><img src="https://agentmods.dev/badge/skills/binggandata/bggg-skills/bggg-tiktok-cut.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00134 | $0.01699 |
| Opus 5 | $0.00067 | $0.00849 |
| Sonnet 5 | $0.00027 | $0.00340 |
| Haiku 4.5 | $0.00013 | $0.00170 |
Grade A, and why
bggg-tiktok-cut scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BGGG TikTok Cut
把 AI 生成的视频剪成 TikTok 可发布的 9:16 成片。Codex 负责判断故事、节奏、画面瑕疵和字幕文案;脚本负责可重复的 FFmpeg 渲染。
快速流程
- 定位输入:确认视频文件、素材文件夹、BGM、字幕/SRT、产品卖点或脚本。用户没有给完整参数时,先按 TikTok 默认值推进:1080x1920、30fps、15-45 秒、前 1-3 秒强 hook、大字字幕、轻 BGM。
- 建项目:把本次产物收进一个项目目录,避免散落在工作区。
python3 <skill-dir>/scripts/init_project.py "<project-dir>" --name "<name>" --inputs "<video1>" "<video2>" - 探测素材:生成 media inventory 和抽帧,用抽帧判断 AI 视频的坏帧、主体位置、适合 cover 还是 blur-bg。
python3 <skill-dir>/scripts/probe_media.py "<project-dir>/raw" --out "<project-dir>/metadata/media_inventory.json" --frames-dir "<project-dir>/diagnostics/frames" - 需要语音时转写:有口播/旁白时生成 JSON/SRT;无语音的 AI 视频可直接根据脚本写 captions/overlays。
python3 <skill-dir>/scripts/transcribe.py "<project-dir>/raw/source.mp4" --out-dir "<project-dir>/transcripts" --model small --language auto - 写剪辑计划:编辑
plans/edit_plan.template.json,或先生成 starter plan 再修改。python3 <skill-dir>/scripts/make_plan.py "<project-dir>" --title "<hook>" --target-seconds 30 - 渲染:
python3 <skill-dir>/scripts/render_tiktok_cut.py "<project-dir>/plans/edit_plan.json" - 自检:用
ffprobe验证输出尺寸、时长、音频;抽查开头、字幕密集处、结尾。如果字幕被 TikTok UI 安全区遮挡、画面主体被裁掉、音频爆音或 BGM 过响,改 plan 后重渲染。
剪辑判断
- AI 视频优先看画面连续性:删掉变形手、漂移 logo、字幕穿帮、闪帧、明显循环卡顿和主体出框的片段。
- 前 3 秒要给理由:用画面强动作、结果预览、反差句、价格/痛点/卖点 overlay 之一开场。不要用慢慢铺垫。
- 竖屏重构图默认
blur-bg:横屏或宽画幅 AI 视频用模糊背景保留完整主体;主体稳定且足够大时用cover;需要展示全图时用contain。 - 字幕安全区:字幕默认放在中下区域,避开 TikTok 底部描述区和右侧操作栏。价格、优惠、CTA 放顶部或中部 badge。
- BGM 是辅助:有口播时 BGM 轻铺,默认 0.08-0.14;无口播的视觉向视频可提高到 0.18-0.28,但避免压过关键音效。
- 批量剪辑:每条视频单独建项目或在同一项目中保存多个
plans/*.json,输出命名带产品/角度/序号。
Edit Plan
渲染脚本读取 JSON plan。需要详细字段时读 references/edit-plan-schema.md。
最小可用示例:
{
"version": 1,
"project": {
"title": "TikTok cut",
"platform": "tiktok",
"target": {"width": 1080, "height": 1920, "fps": 30}
},
"settings": {
"fit": "blur-bg",
"grade": "punch",
"caption_style": "tiktok-bold",
"voice_volume": 1.0,
"output_name": "final_tiktok.mp4"
},
"clips": [
{"source": "raw/clip.mp4", "start": 0.0, "end": 6.2, "fit": "blur-bg", "label": "HOOK"}
],
"captions": [
{"start": 0.0, "end": 2.4, "text": "第一眼就要看到结果", "style": "hook"}
],
"overlays": [
{"start": 0.0, "end": 2.4, "text": "AI 视频二创", "style": "hook"}
],
"bgm": {"path": "assets/bgm/music.mp3", "volume": 0.12},
"export": {"crf": 20, "preset": "fast"}
}
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .gitignore 59 B
- evals/evals.json 1.9 KB
- projects/.gitkeep 0 B
- README_EN.md 1.6 KB
- README.md 1.5 KB
- references/edit-plan-schema.md 2.8 KB
- references/source-projects.md 2.0 KB
- references/tiktok-editing-playbook.md 2.9 KB
- scripts/init_project.py 5.5 KB runs code
- scripts/make_plan.py 3.4 KB runs code
- scripts/media_common.py 4.8 KB runs code
- scripts/probe_media.py 2.9 KB runs code
- scripts/render_tiktok_cut.py 20 KB runs code
- scripts/transcribe.py 4.8 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 109 lines · 134 tokens per session scan A 703b5e3a31be
bggg-tiktok-cut is a skill published in the GitHub repository binggandata/bggg-skills (594 stars, last pushed 1mo ago), licensed MIT. It adds 134 tokens to every session and 1,699 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…