3dgs-training-debugger

3dgs-training-debugger is a skill for Claude Code from jaccen/Awesome-Gaussian-Skills. It costs 140 tokens per session (7,102 once invoked), scanned A, original, Apache-2.0.

A troubleshooting guide for training 3D Gaussian Splatting models, which render scenes from collections of small 3D shapes.

In plain words
What is it for?
Use it to investigate out-of-memory errors, invalid numerical results, slow or failed convergence, unwanted floating shapes, blurry renders, densification problems, multi-GPU setups, and checkpoint issues.
Why use it?
It helps find the causes of crashes, memory errors, unstable training, poor results, and visual defects instead of changing settings at random.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Good fit Use it to investigate out-of-memory errors, invalid numerical results, slow or failed convergence, unwanted floating shapes, blurry renders, densification problems, multi-GPU setups, and checkpoint issues.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jaccen/awesome-gaussian-skills/3dgs-training-debugger
Install

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.

Any agent
npx skills add jaccen/Awesome-Gaussian-Skills --skill 3dgs-training-debugger
Clone the repo
git clone --depth 1 https://github.com/jaccen/Awesome-Gaussian-Skills

Made for: Claude Code.

Wrote 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.

agentmods badge for 3dgs-training-debugger

README.md
[![agentmods](https://agentmods.dev/badge/skills/jaccen/awesome-gaussian-skills/3dgs-training-debugger/github.svg)](https://agentmods.dev/skills/jaccen/awesome-gaussian-skills/3dgs-training-debugger)
Your own site
<a href="https://agentmods.dev/skills/jaccen/awesome-gaussian-skills/3dgs-training-debugger"><img src="https://agentmods.dev/badge/skills/jaccen/awesome-gaussian-skills/3dgs-training-debugger/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.

agentmods 80×15 button for 3dgs-training-debugger

Your own site · 80×15
<a href="https://agentmods.dev/skills/jaccen/awesome-gaussian-skills/3dgs-training-debugger"><img src="https://agentmods.dev/badge/skills/jaccen/awesome-gaussian-skills/3dgs-training-debugger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 140 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,102 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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 content
    Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00140 $0.07102
Opus 5 $0.00070 $0.03551
Sonnet 5 $0.00028 $0.01420
Haiku 4.5 $0.00014 $0.00710

Measured 11d ago against content hash ef8800f92553, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

3dgs-training-debugger 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.

skills/3dgs-training-debugger/SKILL.md · 460 lines

How it starts

The opening of the file, as written. The whole thing — 460 lines — stays where its author put it; the contents beside it link to each section on GitHub.

3DGS Training Debugger

You are a senior 3DGS engineer who has trained hundreds of Gaussian Splatting models across vanilla 3DGS, deformable GS, feed-forward GS, SLAM-GS, and physics-based GS pipelines. Diagnose and fix training-time failures systematically.

Capabilities

  • Diagnose training crashes (OOM, NaN/Inf loss, CUDA errors) with root-cause analysis
  • Identify convergence failures (stalls, divergence, premature plateau)
  • Debug densification failures (over/under-triggering, positional gradient issues)
  • Diagnose visual artifacts from training logs (floaters, blur, ghosting, holes)
  • Recommend hyperparameter adjustments with expected impact
  • Guide distributed/multi-GPU training setup and debugging
  • Troubleshoot checkpoint save/resume issues
  • Address novel method stability (deformable GS, MoE-GS, physics-based GS, feed-forward GS)
  • Detect 50+ runtime failure patterns (see references/runtime-bug-patterns.md)

Relationship to Other Skills

This skill covers the runtime training phase — what happens AFTER code is written and BEFORE evaluation. It complements:

  • 3dgs-code-reviewer: Static code analysis (pre-training). Use code-reviewer first to catch implementation bugs, then use this skill to debug runtime issues.
  • 3dgs-experiment-planner: Experiment design (pre-training). Design experiments, then use this skill when training fails.
  • 3dgs-engineering-guide: Production deployment (post-training). This skill handles getting training TO completion.

Section 1: Training Monitoring Checklist

1.1 What to Monitor During Training

Metric Expected Behavior Alert Threshold Log Frequency
L1 loss Decreasing, minor oscillation Increase > 20% over 500 iters Every 50 iters
SSIM loss Decreasing smoothly Stagnant for 1000+ iters Every 100 iters
Total loss Decreasing, plateau ~70-80% of training NaN, Inf, or sudden spike Every 50 iters
PSNR (eval) Increasing, plateau near end Drop > 2dB between evals Every 1000 iters
Gaussian count Growth phase (0-15k), then stable Explosive growth (>10x) or vanishing Every 500 iters
VRAM usage Stable with minor fluctuation during ADC > 90% of total VRAM Every 100 iters
Gradient norms Stable, < 1.0 typically > 10.0 or exactly 0.0 Every 100 iters
Learning rate Following schedule (warmup → cosine decay) Unexpected reset or spike Every 500 iters
Active Gaussians Growth then pruning equilibrium All pruned (count → 0) Every ADC cycle
ADC trigger count Periodic (every ~100 iters) Never triggers or triggers every iter Every ADC cycle

Read the full file on GitHub · 460 lines

Files

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.

Changes

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.

  1. 11d ago First seen · 460 lines · 140 tokens per session scan A ef8800f92553

Subscribe to this mod's changes

3dgs-training-debugger is a skill published in the GitHub repository jaccen/Awesome-Gaussian-Skills (150 stars, last pushed 6d ago), licensed Apache-2.0. It adds 140 tokens to every session and 7,102 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens