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 3dgs-paper-readergit 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/3dgs-paper-reader)<a href="https://agentmods.dev/skills/jaccen/awesome-gaussian-skills/3dgs-paper-reader"><img src="https://agentmods.dev/badge/skills/jaccen/awesome-gaussian-skills/3dgs-paper-reader/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/3dgs-paper-reader"><img src="https://agentmods.dev/badge/skills/jaccen/awesome-gaussian-skills/3dgs-paper-reader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00096 | $0.02887 |
| Opus 5 | $0.00048 | $0.01443 |
| Sonnet 5 | $0.00019 | $0.00577 |
| Haiku 4.5 | $0.00010 | $0.00289 |
Grade A, and why
3dgs-paper-reader 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 6d 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
3DGS Paper Reader
You are a senior 3D computer vision researcher specializing in 3D Gaussian Splatting and neural radiance fields. Your task is to read and analyze research papers in this domain.
Capabilities
- Parse and analyze 3DGS / NeRF / 3D reconstruction papers from arXiv or local files
- Extract structured information: method, innovation, experiments, limitations
- Generate publication-quality summaries with comparison tables
- Identify relationships to prior work and positioning in the research landscape
Workflow
Step 1: Source Acquisition
When the user provides a paper reference, identify the source type:
| Source Format | Action |
|---|---|
| arXiv ID (e.g., "2401.01345") | Fetch from arxiv.org/abs/{ID} |
| arXiv URL | Extract ID and fetch |
| Local PDF path | Read the PDF directly |
| Paper title | Search arXiv and retrieve the most relevant match |
Step 2: Full-Text Analysis
Read the entire paper and extract the following structured information:
- Metadata: Title, authors, venue, year, arXiv ID
- Problem Statement: What specific problem does this paper solve?
- Core Innovation: The single most important contribution (1-2 sentences)
- Method Details:
- Input representation (point cloud / images / video / meshes)
- 3D primitive type (anisotropic Gaussians / 2D Gaussians / surfels / hybrid)
- Key attributes per primitive (μ, Σ, opacity, SH coefficients, ...)
- Rendering formulation (α-blending / differentiable rasterization / ...)
- Loss functions (L1 + SSIM + D-SSIM + perceptual + regularizer)
- Training strategy (adaptive density control / pruning / splitting / ...)
- Special mechanisms (frequency-aware / signed opacity / deformable / ...)
- Experimental Setup:
- Datasets used (Mip-NeRF 360 / Tanks and Temples / Deep Blending / DTU / ...)
- Evaluation metrics (PSNR / SSIM / LPIPS / FPS / memory / #Gaussians)
- Baselines compared against
- Key Results: Quantitative comparison table (method → PSNR → SSIM → LPIPS)
- Limitations: Explicitly stated or inferred limitations
- Relationship to Existing Work: How does this compare to known methods?
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.
- 6d ago Changed 6318fe67bc64
- 12d ago First seen · 202 lines · 96 tokens per session scan A ea26e5063a1f
3dgs-paper-reader is a skill published in the GitHub repository jaccen/Awesome-Gaussian-Skills (150 stars, last pushed 6d ago), licensed Apache-2.0. It adds 96 tokens to every session and 2,887 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
usgs-lidar-dem
Download USGS 3DEP LiDAR DEM data, colorize with satellite imagery, and import into Metashape as laser scan ground truth. Use when extending photogrammetry environments with surrounding terrain.
sky-artifact-prevention
Prevent and remove sky/tunnel mesh artifacts in road corridor photogrammetry. Covers five strategies from Metashape-side prevention (height field, region crop, point cloud classification, source selection) to post-mesh cleanup. The.
photo-import-setup
Set up a new Metashape project from scratch — import photos, load GPS reference, configure sensors (fisheye, rolling shutter, multi-camera), import EXR alpha masks, run image quality analysis, and disable bad frames. The first skill to use on any new capture. Works through the Metashape MCP server.
corridor-alignment-pipeline
Orchestrate incremental alignment of long road corridor captures with automatic drift detection and QA gates. Prevents alignment divergence by checking GPS deviation gradients and continuity between batches. Works through the Metashape MCP server.
metashape-reconstruction
Guide dense reconstruction, mesh building, and texturing in Metashape MCP. Covers depth maps, point cloud, mesh, texture, DEM, and orthomosaic generation with correct GPU/CPU settings and quality parameters. Works through the Metashape MCP server.
metashape-api-lookup
Look up Metashape Python API parameters and enums from local reference files when building or fixing MCP tools. Use when you need to verify parameter names, types, defaults, or enum values for Metashape API calls.