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 phanghonghao/THU-Awesome-Skills --skill ai-gengit clone --depth 1 https://github.com/phanghonghao/THU-Awesome-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/phanghonghao/thu-awesome-skills/ai-gen)<a href="https://agentmods.dev/skills/phanghonghao/thu-awesome-skills/ai-gen"><img src="https://agentmods.dev/badge/skills/phanghonghao/thu-awesome-skills/ai-gen/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/phanghonghao/thu-awesome-skills/ai-gen"><img src="https://agentmods.dev/badge/skills/phanghonghao/thu-awesome-skills/ai-gen.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00083 | $0.01555 |
| Opus 5 | $0.00042 | $0.00777 |
| Sonnet 5 | $0.00017 | $0.00311 |
| Haiku 4.5 | $0.00008 | $0.00155 |
Grade A, and why
ai-gen 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 11d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI-Gen Skill - AI 生图/生视频 (多模型组合版)
通过 paratera API 进行文生图和文生视频生成。支持三个模型预设（豆包/GLM/MiniMax），可跨系列组合补齐能力。
可用预设
| 预设 | Provider | 文生图 | 文生视频 | 说明 |
|---|---|---|---|---|
| 豆包 (默认) | doubao |
GLM-CogView3-Flash | Doubao-Seedance-1.0-Pro | 豆包图挂了，用 GLM 补 |
| GLM | glm |
GLM-CogView3-Flash | Doubao-Seedance-1.0-Pro | GLM 无视频，用豆包补 |
| MiniMax | minimax |
GLM-CogView3-Flash | MiniMax-T2V-01-Directo | MiniMax 无图，用 GLM 补 |
三个预设的图片都是 GLM（唯一可用的图片模型），区别在视频模型。
完整工作流程
Step 1: 获取输入
询问用户提供 .MD 文件路径或直接描述生成需求：
请提供要生成的 .MD 文件路径，或直接描述你想生成的图片/视频内容。
Step 2: 读取并分析文件
如果用户提供了 .MD 文件：
- 使用 Read 工具读取文件内容
- 分析文件中的场景描述、段落标题、关键画面
- 将内容拆分为可独立生成的场景/描述项
如果用户直接描述需求：
- 分析用户描述
- 将其拆分为合理的生成任务
Step 3: 选择模型预设
使用 AskUserQuestion 让用户选择预设：
问题: "请选择模型预设："
Header: "模型预设"
选项:
a. 豆包 (Doubao) — 视频: Doubao-Seedance-1.0-Pro (推荐)
b. GLM — 视频: Doubao-Seedance-1.0-Pro (同豆包视频)
c. MiniMax — 视频: MiniMax-T2V-01-Directo
图片统一使用 GLM-CogView3-Flash（无需选择）。
Step 4: 制定生成计划
将分析结果整理为结构化的生成计划表格，展示给用户：
## 生成计划 (预设: 豆包)
| # | 类型 | Prompt | 参数 |
|---|------|--------|------|
| 1 | 文生图 | A cute robot waving in a futuristic city | size=1024x1024 |
| 2 | 文生视频 | A robot walking through a neon-lit corridor | ratio=16:9 |
| ... | ... | ... | ... |
共计 N 项生成任务。
对每一项标注：
- 类型: 文生图 (image) 或 文生视频 (video)
- Prompt: 英文提示词（如果原文是中文，翻译为英文，因为模型对英文 prompt 效果更好）
- 参数: size / ratio / dur 等可选参数
Step 5: 用户确认
展示计划后，询问用户确认：
以上生成计划是否满意？可以：
- 直接确认执行
- 修改某一项的 prompt / 参数
- 删除某些项
- 添加新项
Step 6: 执行生成
用户确认后，按计划逐项调用 generate.py 执行生成。
对于每项任务，使用 Bash 工具执行：
文生图:
python "<LOCAL_USER>/.claude/skills/ai-gen/generate.py" --mode image --prompt "..." --provider <provider> --output "ai_gen_output/001_image.png"
文生视频:
python "<LOCAL_USER>/.claude/skills/ai-gen/generate.py" --mode video --prompt "..." --provider <provider> --output "ai_gen_output/002_video.mp4"
注意：
- 文生图是同步调用，约 10-30 秒返回
- 文生视频是异步调用（提交→轮询→下载），可能需要 2-5 分钟
- 多个文生图任务可以并行执行
- 文生视频建议串行以避免 API 限流
- API Key 池会自动轮换，无需手动指定 key
What ships with it
3 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.
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.
- 11d ago First seen · 167 lines · 83 tokens per session scan A ffd639d45445
ai-gen is a skill published in the GitHub repository phanghonghao/THU-Awesome-Skills (8 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 1,555 once invoked, about $0.0004 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).
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.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.