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 rojim666/SztuCode --skill buddy-multimodal-generationgit clone --depth 1 https://github.com/rojim666/SztuCodeWrote 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/rojim666/sztucode/buddy-multimodal-generation)<a href="https://agentmods.dev/skills/rojim666/sztucode/buddy-multimodal-generation"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/buddy-multimodal-generation/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/rojim666/sztucode/buddy-multimodal-generation"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/buddy-multimodal-generation.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 | $0.00149 | $0.06221 |
| Opus 5 | $0.00075 | $0.03111 |
| Sonnet 5 | $0.00030 | $0.01244 |
| Haiku 4.5 | $0.00015 | $0.00622 |
Grade A, and why
3D模型与视频特效 scanned grade A with 1 finding 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
使用 `execute_command` 工具执行 `curl` 命令将文件下载到**当前工作目录**： How it starts
The opening of the file, as written. The whole thing — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.
3D模型与视频特效技能
通过云端服务生成多模态内容，包括 3D 模型生成，以及基于模板的图片视频特效。
⚠️ 本技能不处理以下任务（已迁移至内置工具）：
- 文生图 / 图生图 / 图片编辑 / 风格转换 → 使用
ImageGen工具（通过 ToolSearch 发现后用 DeferExecuteTool 调用）- 文生视频 / 图生视频 → 使用
VideoGen工具（通过 ToolSearch 发现后用 DeferExecuteTool 调用）如果用户请求的是上述 4 类任务，必须停止执行本技能，改为引导模型使用对应工具。
能力概览
| 能力 | 命令 | 说明 |
|---|---|---|
| 视频特效 | buddy-cloud.py video-fx |
基于模板的图片转视频特效（支持多图） |
| 3D 模型生成 | buddy-cloud.py 3d |
文生3D / 图生3D（异步轮询） |
所有能力统一使用
connect_cloud_service认证，详见下方认证流程。
1. 视频特效
将静态图片转化为动态视频片段，基于预设特效模板驱动人物或物体产生动作、变身、互动等效果。目前支持 60+ 个模板，覆盖人物互动、变装变身、物理特效、风格转换等多种类型。
调用示例：
# 单图特效
echo -n "<token>" | python3 <SKILL_DIR>/scripts/buddy-cloud.py video-fx --template return2dust --image "https://example.com/photo.jpg" --token-stdin
# 多图特效（双人互动）
echo -n "<token>" | python3 <SKILL_DIR>/scripts/buddy-cloud.py video-fx --template hug --image "https://example.com/face1.jpg" --image "https://example.com/face2.jpg" --token-stdin
示例用法：
- 上传一张人像，应用"万物归尘"让人物化作粒子消散（单图：
--image URL） - 上传两张人脸照片，应用"亲吻"生成双人互动视频（多图：
--image URL1 --image URL2） - 上传一张全身照，应用"变身机甲"将人物改造为未来战士
部分模板一览（template 取值）：
| 类型 | 模板名 | template |
|---|---|---|
| 人物互动 | 拥抱 / 亲吻 / 比心 / 公主抱 / 脸颊贴贴 | hug / kissing / hearting / bridalcarry / cheeks |
| 变装变身 | 变身机甲 / 变身美人鱼 / 埃及变装 / 毕业啦 / 赛博朋克 | futuresoldier / mermaidme / egyptme / graduation / cyber |
| 物理特效 | 万物归尘 / 飞走了 / 被拽走了 / 面对疾风 / 膨胀 | return2dust / balloonfly / dragme / windonface / morphlab |
| 风格转换 | 动漫视频 / 卡通视频 / 3D手办风 / 毛茸茸 | animelive / cartoonlive / 3dfigure / fuzzy |
| 趣味互动 | 吃我一拖鞋 / 倒头就是睡 / 被骷髅抓走了 / 捏脸 | shoehit / napme / atomy / facepinch |
完整模板列表见官方文档。
2. 3D 模型生成
基于腾讯混元大模型，将文本描述或图片生成高精度 3D 模型。支持文生3D、图生3D、多视角生3D、白模（Geometry）、草图生3D。
调用方式
# 文生3D
echo -n "<token>" | python3 <SKILL_DIR>/scripts/buddy-cloud.py 3d "文本描述" --token-stdin
# 图生3D
echo -n "<token>" | python3 <SKILL_DIR>/scripts/buddy-cloud.py 3d --image-url "https://example.com/image.jpg" --token-stdin
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.
- today First seen · 408 lines · 149 tokens per session scan A ce5754fdab6f
3D模型与视频特效 is a skill published in the GitHub repository rojim666/SztuCode (64 stars, last pushed today), licensed MIT. It adds 149 tokens to every session and 6,221 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-12.
Other skills, from other repositories
copperhead
Change or verify a KiCad project through copperhead's gated pipeline. Use whenever a task touches .kicadsch or .kicadpcb files, a schematic, a PCB layout, a netlist, ERC/DRC, a BOM, or hardware design docs — instead of editing those files directly.
roblox-studio
Build and edit in Roblox Studio via the Roblox Studio MCP the RIGHT way - preflight the Studio connection, do the whole build in a few big executeluau scripts (not dozens of tiny calls), make REALISTIC terrain with the Terrain VOXEL api driven by Perlin noise (NEVER stacked Parts or concentric layers - those give ugly…
tura
Work in the Tura agent-runtime repository. Use for Tura architecture, Rust backend, GUI/TUI, prompts, commands, providers, sessions, documentation, tests, packaging, and release work in this directory.
promote
A workflow for sharing useful work from a separate Git worktree, which is another working folder linked to the same Git project, into the shared main branch.
skill-test
Verifies that the skill system is working correctly.
verify
Drive the MCP extension through the real Pi TUI and capture provider-prefix behavior.