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 ztaihang/agent-skills --skill hyperframes-shortsgit clone --depth 1 https://github.com/ztaihang/agent-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/ztaihang/agent-skills/hyperframes-shorts)<a href="https://agentmods.dev/skills/ztaihang/agent-skills/hyperframes-shorts"><img src="https://agentmods.dev/badge/skills/ztaihang/agent-skills/hyperframes-shorts.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00112 | $0.22501 |
| Opus 5 | $0.00056 | $0.11250 |
| Sonnet 5 | $0.00022 | $0.04500 |
| Haiku 4.5 | $0.00011 | $0.02250 |
Grade A, and why
hyperframes-shorts 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 7d 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 — 1,311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
使用说明
本 Skill 用于在用户指定的项目路径下构建 HyperFrames 短视频工程。修改视频内容请改项目目录内的文件；若要贡献或修改 skill 源码，见仓库 CONTRIBUTING.md。
HyperFrames 0.7 能力对齐（Agent 必读）
新版 HyperFrames 能力很多；中文口播短视频不必全用。下表说明本 Skill 与官方 0.7 的关系。
图例：✅ 必用 · ⭐ 推荐升级 · ⚪ 可选 · 🚫 不用
领域 Skill 对照
| 官方能力 | 本 Skill | 说明 |
|---|---|---|
hyperframes-core — HTML 合约、clip/track |
✅ 必用 | 写 index.html 前读 determinism-rules.md 要点 |
hyperframes-animation — GSAP mt |
✅ 必用 | L1–L3 主路径 |
hyperframes-animation — CSS keyframe L0 |
✅ 必用 | adapters/css-animations.md |
hyperframes-animation — 转场 catalog |
⭐ 推荐 | 见下方「L4 转场分级」；写 HTML 前读 transitions/catalog.md 对应条目 |
hyperframes-animation — atomic rules / blueprints |
⭐ P1 | L2/L3 查 rules-index.md；复杂镜查 blueprints |
hyperframes-animation — Lottie / Three.js / TypeGPU |
🚫 默认不用 | 口播解说 seek 成本高；用户明确要求 3D/shader 镜才启用 |
hyperframes-creative — visual-styles / house-style |
✅ 必用 | 写 design.md |
hyperframes-cli — lint / validate / inspect |
✅ 必用 | npm run check |
hyperframes-cli — snapshot |
✅ P0 | ≥4 镜 交付前 npx hyperframes snapshot --frames 9 |
hyperframes-creative — design-adherence |
✅ P0 | HTML 写完后对照 design.md |
hyperframes-creative — video-composition |
✅ P0 | 写 HTML 前必读 |
hyperframes-creative — data-in-motion |
✅ P0 | 有数据镜时必读 |
hyperframes-creative — design-picker |
⭐ P1 | 用户未指定风格时 offer |
hyperframes-creative — beat-direction |
⭐ P1 | 口播 >90s 或 ≥6 镜 |
hyperframes-animation — atomic rules |
⭐ P1 | L2/L3 查 rules-index |
media-use — SFX resolve |
⚪ P2 | HeyGen 已登录时替代 FFmpeg 滴声 |
hyperframes-registry — add 组件 |
⚪ P2 | 数据图表镜可选 |
*.motion.json sidecar |
⚪ P2 | ≥5 镜复杂动效 |
hyperframes-cli — Lambda 云渲染 |
⚪ 可选 | 仅用户要求长片/4K 云导出 |
hyperframes-media — 官方 TTS/BGM |
🚫 不用 | 见下方「TTS 路线对比」；中文坚持用 Edge TTS |
| 11 条官方 workflow | 🚫 不用 | 本 Skill 是 /faceless-explainer 的中文增强替代 |
L4 转场分级（对接 0.7 catalog）
What ships with it
28 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.
- agents/openai.yaml 351 B
- examples/brand-outro.example.md 217 B
- examples/outro-rules.md 5.5 KB
- examples/prompt-template.md 7.2 KB
- examples/prompt-with-brand-outro.example.md 672 B
- LICENSE 1.1 KB
- README.md 4.8 KB
- templates/anti-slop-motion-scheme.md 11 KB
- templates/assets/brand.json.example 425 B
- templates/audio/lines.json.example 1.2 KB
- templates/delivery-pitfalls.md 9.7 KB
- templates/design.md.example 3.6 KB
- templates/hyperframes-zh-checklist.md 8.3 KB
- templates/README.md 3.3 KB
- templates/requirements-align.txt 198 B
- templates/scene-density-guide.md 3.7 KB
- templates/scripts/align-subtitles.py 14 KB runs code
- templates/scripts/apply-audio-schedule.mjs 15 KB runs code
- templates/scripts/apply-brand.mjs 3.6 KB runs code
- templates/scripts/fallback-alignments.py 21 KB runs code
- templates/scripts/generate-tts.py 24 KB runs code
- templates/scripts/realign-line.py 3.2 KB runs code
- templates/scripts/run-align.py 4.8 KB runs code
- templates/scripts/verify-delivery-checklist.py 17 KB runs code
- templates/scripts/verify-index-encoding.py 2.0 KB runs code
- templates/style-history.json.example 301 B
- templates/subtitle-tts-guide.md 15 KB
- templates/visual-style-guide.md 7.5 KB
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.
- 7d ago First seen · 1,311 lines · 112 tokens per session scan A 9f8927008323
hyperframes-shorts is a skill published in the GitHub repository ztaihang/agent-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 112 tokens to every session and 22,501 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.