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 jaccen/Awesome-Gaussian-Skills --skill agent-routergit clone --depth 1 https://github.com/jaccen/Awesome-Gaussian-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/jaccen/awesome-gaussian-skills/agent-router)<a href="https://agentmods.dev/skills/jaccen/awesome-gaussian-skills/agent-router"><img src="https://agentmods.dev/badge/skills/jaccen/awesome-gaussian-skills/agent-router/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/jaccen/awesome-gaussian-skills/agent-router"><img src="https://agentmods.dev/badge/skills/jaccen/awesome-gaussian-skills/agent-router.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 | $0.00213 | $0.03513 |
| Opus 5.5 | $0.00085 | $0.01405 |
| Sonnet 5.5 | $0.00043 | $0.00703 |
| Haiku 4.5 | $0.00021 | $0.00351 |
Grade A, and why
awesome-gaussian-skills 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 yesterday.
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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Awesome Gaussian Skills — 总路由
概述
本技能是 Awesome-Gaussian-Skills 工具包的总入口与调度器。当前基线（2026-10-14 快照）：
- 方法知识库：
data/methods.json955 条方法，其中 848 条带 arXiv ID，覆盖 26 个类目；每条含 arXiv ID、venue、年份、类目、核心创新点、代码链接 - 18 个子技能：覆盖 3DGS 科研与工程全流程（读论文 → 方法对比 → 实验设计 → 代码审查 → 训练调试 → 可视化 → 论文写作 → 专利 → 本体 → 超级智能体 → MCP 渲染）
- 科研专家团（
research-expert-team）：九个角色覆盖选题评估到 rebuttal，并自带「本体与知识表示 / 超级智能体 / AIGC 内容生成」三个前沿方向的方法选型表 - 知识库快照：本技能包内含 30 个参考文件（方法全库、九簇深度笔记、写作能力库、验证引用、世界模型、具身智能、期刊分区、基准与数据集等）
- 配套资源：在线交互式方法检索器、开源书籍《Spatial & Embodied Intelligence》、benchmark 数据
本技能的职责是：判断任务类型 → 路由到正确的子技能、专家角色或知识库文件，并强制执行引用准确性纪律。
数据源与路径
| 资源 | 位置 |
|---|---|
| 本地仓库（作者维护，每日更新） | C:\Users\Lenovo\Desktop\Project\Awesome-Gaussian-Skills |
| 单一事实源（方法库） | 仓库内 data/methods.json（改任何计数前先看它） |
| 类目清单 | 仓库内 data/categories.json（26 个 canonical 类目 + 各类计数） |
| GitHub 仓库 | https://github.com/jaccen/Awesome-Gaussian-Skills |
| 在线方法检索器 | https://jaccen.github.io/Awesome-Gaussian-Skills/ |
| 在线书籍（空间与具身智能） | https://jaccen.github.io/Awesome-Gaussian-Skills/spatial-embodied-intelligence.html |
子技能安装状态（WorkBuddy 用户技能目录）：18 个全部已安装，路由表里不再有"未安装"项。
任务路由表
按任务意图路由到对应子技能（均已作为独立 WorkBuddy 技能加载；若其未触发，手动调用 Skill 工具）：
| 任务意图 | 路由到 |
|---|---|
| 科研全流程：评估 idea、挖创新点、模拟审稿、润色、消除 AI 痕迹、投稿格式、实验设计与分析 | research-expert-team（九角色专家团） |
| 读/总结 3DGS、NeRF 论文；从 arXiv PDF 提取方法架构 | 3dgs-paper-reader |
| 对比两个或多个 3DGS 方法；找某场景最优方法 | 3dgs-method-compare |
| 设计实验：数据集、基线、指标、消融矩阵 | 3dgs-experiment-planner |
| 审查 3DGS/CUDA 实现代码；渲染伪影排查 | 3dgs-code-reviewer（104 个已知 bug 模式） |
| 训练崩溃：NaN、OOM、发散、floaters、稠密化失败 | 3dgs-training-debugger（60+ 运行时模式） |
| 论文配图：雷达图、对比表、方法时间线 | 3dgs-visualizer |
| NeRF 方法迁移到 3DGS；NeRF-3DGS 混合架构 | nerf-to-3dgs-migrator |
| CAD ↔ Mesh ↔ 3DGS 转换、表面提取、逆向 CAD | cad-mesh-3dgs |
| 部署到生产：行业选型、GIS/BIM/ROS2/引擎集成 | 3dgs-engineering-guide |
| 压缩、剪枝、量化到端侧部署 | 3dgs-compression-deploy |
| 关节物体推理、部件结构、数字孪生 | 3dgs-articulated-reasoner |
| 空间智能体：感知-规划-动作闭环、空间记忆 | 3dgs-spatial-agent |
| 计算机图形/3D 视觉学术论文写作与投稿格式 | cg-paper-writing |
| 中国专利/软著材料生成 | patent-software-ip |
| MCP 协议 3DGS 渲染管线 | 3dgs-mcp-renderer |
| 本体建模、知识表示、场景图与符号接地 | ontology |
| 超级智能体架构、多智能体编排、Agentic AI | super-agent |
What ships with it
1 file 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.
- yesterday First seen · 153 lines · 213 tokens per session scan A 8b20c2ecdbd2
awesome-gaussian-skills is a skill published in the GitHub repository jaccen/Awesome-Gaussian-Skills (162 stars, last pushed today), licensed Apache-2.0. It adds 213 tokens to every session and 3,513 once invoked, about $0.0009 per session on Opus 5.5. 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 2026-10-16.
Other skills, from other repositories
fba-simulator
Run Flux Balance Analysis (FBA) and related constraint-based simulations using COBRApy. Covers standard FBA, parsimonious FBA (pFBA), Flux Variability Analysis (FVA), loopless FBA, gene/reaction knockouts, and carbon source swapping. Outputs flux distributions and CSV files.
flux-analyzer
Analyse FBA flux distributions to extract biological insights. Covers gene essentiality, phenotypic phase planes, flux sampling, pathway-level aggregation, secretion product prediction, and production of publication- quality figures.
gsmm-validator
Validate a COBRApy genome-scale metabolic model for mass/charge balance, stoichiometric consistency, biomass producibility, dead-end metabolites, thermodynamic loops, and GPR rule formatting. Outputs a structured validation report with errors and warnings.
gsmm-builder
Build or load a genome-scale metabolic model (GSMM) using COBRApy. Covers loading from BIGG, constructing minimal models from scratch, setting medium constraints, and exporting validated .json model files.
stat-result-validator
Validate statistical research outputs for formulation quality, method-to- problem alignment, theory presence, experimental evidence, fair comparison, artifact completeness, and final-claim consistency.
statistical-experimental-evaluation
Design and run statistical experiments that test the formal problem, proposed methods, theoretical predictions, baselines, and ablations.