Skill collection
jaccen/Awesome-Gaussian-Skills agent skills
- skills
- 13
- GitHub stars
- 161
GitHub description: “图形学与3DGS、空间智能持续更新论文；AI Agent Skills for 3D Gaussian Splatting, NeRF & Computer Graphics Research. 800+ methods, 25categories, 12skills. OpenClaw / Claude Code compatible.”
- Stars
- 161 (13 forks)
- Licence
- Apache-2.0
- Last push
- Oct 2026
- Created
- Apr 2026
- 3d-gaussian-splatting
- 3d-reconstruction
- ai-agent
- claude-code
- computer-graphics
- neural-rendering
- openclaw
- 3dgs
- ai-skills
- cvpr
- gaussian-splatting
- nerf
- novel-view-synthesis
- point-cloud
- research-tools
- siggraph
Install all skills
npx skills add jaccen/Awesome-Gaussian-SkillsAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in jaccen/Awesome-Gaussian-Skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Review 3DGS implementation code for correctness, performance bugs, and best practices. | jaccen/ | 161 | — | ~2.9k | Automated safety check: Pass | Apache-2.0 | today |
| 2 | Generate CN patent docs (claims, specification, abstract) and software copyright materials from AI/big-data project code or docs. | jaccen/ | 161 | — | ~4.3k | Automated safety check: Pass | Apache-2.0 | today |
| 3 | 3DGS Articulated Object Reasoning & Digital Twin Agent. An agent skill from jaccen/Awesome-Gaussian-Skills. | jaccen/ | 161 | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | today |
| 4 | 3DGS compression-to-deployment pipeline: quantization (scalar/VQ/mixed-precision), pruning (coreset/adaptive/variational/merge/Bayesian), progressive streaming & LoD, Web/WebGPU/mobile deployment… | jaccen/ | 161 | — | ~5.5k | Automated safety check: Pass | Apache-2.0 | today |
| 5 | MCP protocol integration with 3DGS rendering pipeline: Agent-controlled Three.js/WebGPU rendering, voice-driven scene reconstruction, real-time parameter manipulation, light tracing backend. | jaccen/ | 161 | — | ~6.9k | Automated safety check: Pass | Apache-2.0 | today |
| 6 | Read and summarize 3DGS research papers. An agent skill from jaccen/Awesome-Gaussian-Skills. | jaccen/ | 161 | — | ~2.7k | Automated safety check: Pass | Apache-2.0 | today |
| 7 | 3DGS/CAD/Mesh domain-specific spatial intelligence agent: scene-level reasoning, CAD-in-the-loop parametric extraction, multi-modal 3D interaction, geometry-opacity decoupling, reflective material… | jaccen/ | 161 | — | ~4.5k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 8 | Diagnose and fix 3DGS training-time failures: NaN losses, OOM crashes, divergent optimization, floater artifacts, densification failures, hyperparameter sensitivity. | jaccen/ | 161 | — | ~7k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 9 | Generate publication-quality visualizations for 3DGS research: radar charts, comparison tables, method timelines. | jaccen/ | 161 | — | ~4.1k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 10 | Bridge CAD, Mesh, and 3DGS representations via the SLAT unified encode-decode framework. | jaccen/ | 161 | — | ~5.8k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 11 | Migrate NeRF-based methods to 3DGS via the SLAT unified encode-decode framework. | jaccen/ | 161 | — | ~4k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 12 | Academic paper writing for 3D vision, computer graphics, CAD, and 3D understanding. | jaccen/ | 161 | — | ~4.4k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 13 | Design rigorous experiments for 3DGS research papers. An agent skill from jaccen/Awesome-Gaussian-Skills. | jaccen/ | 161 | — | ~5.6k | Automated safety check: Pass | Apache-2.0 | yesterday |
Questions, answered from the data.
What is the best skill in jaccen/Awesome-Gaussian-Skills?
3dgs Code Reviewer from jaccen/Awesome-Gaussian-Skills ranks first of the 13 skills in jaccen/Awesome-Gaussian-Skills listed here, with the highest score: its repository has 161 GitHub stars, its SKILL.md loads about 2.9k tokens and it passes the automated safety check with no findings. Next come Patent Software Ip and 3dgs Articulated Reasoner.
Are the skills in jaccen/Awesome-Gaussian-Skills official?
None yet. All 13 skills in jaccen/Awesome-Gaussian-Skills listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from jaccen/Awesome-Gaussian-Skills?
Run npx skills add jaccen/Awesome-Gaussian-Skills in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.