Cmux Debugging Guide
manaflow-ai/cmux
Covers debug logging, the Debug menu, profiling rules and runtime pitfalls for working on the cmux macOS terminal app.
Agent skill
When Debugging ML Training Use ML Training Debugger
Debug ML training issues and optimize performance including loss divergence, overfitting, and slow convergence
Install When Debugging ML Training Use ML Training Debugger
$ npx skills add aiskillstore/marketplace --skill when-debugging-ml-training-use-ml-training-debugger -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install aiskillstore/marketplace when-debugging-ml-training-use-ml-training-debugger --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/aiskillstore/marketplace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/dnyoussef/when-debugging-ml-training-use-ml-training-debugger .claude/skills/when-debugging-ml-training-use-ml-training-debugger && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "when-debugging-ml-training-use-ml-training-debugger" agent skill from https://github.com/aiskillstore/marketplace/tree/main/skills/dnyoussef/when-debugging-ml-training-use-ml-training-debugger into .claude/skills/when-debugging-ml-training-use-ml-training-debugger/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "when-debugging-ml-training-use-ml-training-debugger", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/aiskillstore/marketplace/tree/main/skills/dnyoussef/when-debugging-ml-training-use-ml-training-debuggerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add aiskillstore/marketplace --skill when-debugging-ml-training-use-ml-training-debugger -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install aiskillstore/marketplace when-debugging-ml-training-use-ml-training-debugger --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aiskillstore/marketplace.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/dnyoussef/when-debugging-ml-training-use-ml-training-debugger .agents/skills/when-debugging-ml-training-use-ml-training-debugger && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "when-debugging-ml-training-use-ml-training-debugger" agent skill from https://github.com/aiskillstore/marketplace/tree/main/skills/dnyoussef/when-debugging-ml-training-use-ml-training-debugger into .agents/skills/when-debugging-ml-training-use-ml-training-debugger/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "when-debugging-ml-training-use-ml-training-debugger", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add aiskillstore/marketplace --skill when-debugging-ml-training-use-ml-training-debugger -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install aiskillstore/marketplace when-debugging-ml-training-use-ml-training-debugger --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aiskillstore/marketplace.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/dnyoussef/when-debugging-ml-training-use-ml-training-debugger .cursor/skills/when-debugging-ml-training-use-ml-training-debugger && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "when-debugging-ml-training-use-ml-training-debugger" agent skill from https://github.com/aiskillstore/marketplace/tree/main/skills/dnyoussef/when-debugging-ml-training-use-ml-training-debugger into .cursor/skills/when-debugging-ml-training-use-ml-training-debugger/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "when-debugging-ml-training-use-ml-training-debugger", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/aiskillstore/marketplace.git --path skills/dnyoussef/when-debugging-ml-training-use-ml-training-debugger--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add aiskillstore/marketplace --skill when-debugging-ml-training-use-ml-training-debugger -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install aiskillstore/marketplace when-debugging-ml-training-use-ml-training-debugger --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aiskillstore/marketplace.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/dnyoussef/when-debugging-ml-training-use-ml-training-debugger .gemini/skills/when-debugging-ml-training-use-ml-training-debugger && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "when-debugging-ml-training-use-ml-training-debugger" agent skill from https://github.com/aiskillstore/marketplace/tree/main/skills/dnyoussef/when-debugging-ml-training-use-ml-training-debugger into .gemini/skills/when-debugging-ml-training-use-ml-training-debugger/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "when-debugging-ml-training-use-ml-training-debugger", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install aiskillstore/marketplace when-debugging-ml-training-use-ml-training-debuggerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add aiskillstore/marketplace --skill when-debugging-ml-training-use-ml-training-debugger -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/aiskillstore/marketplace.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/dnyoussef/when-debugging-ml-training-use-ml-training-debugger .github/skills/when-debugging-ml-training-use-ml-training-debugger && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "when-debugging-ml-training-use-ml-training-debugger" agent skill from https://github.com/aiskillstore/marketplace/tree/main/skills/dnyoussef/when-debugging-ml-training-use-ml-training-debugger into .github/skills/when-debugging-ml-training-use-ml-training-debugger/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "when-debugging-ml-training-use-ml-training-debugger", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add aiskillstore/marketplace --skill when-debugging-ml-training-use-ml-training-debugger -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install aiskillstore/marketplace when-debugging-ml-training-use-ml-training-debugger --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/aiskillstore/marketplace.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/dnyoussef/when-debugging-ml-training-use-ml-training-debugger .opencode/skills/when-debugging-ml-training-use-ml-training-debugger && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "when-debugging-ml-training-use-ml-training-debugger" agent skill from https://github.com/aiskillstore/marketplace/tree/main/skills/dnyoussef/when-debugging-ml-training-use-ml-training-debugger into .opencode/skills/when-debugging-ml-training-use-ml-training-debugger/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "when-debugging-ml-training-use-ml-training-debugger", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
when-debugging-ml-training-use-ml-training-debugger- GitHub stars
- 430
- Used in
- 1 other repo
- Token cost
- ~4.1k tokens
- SKILL.md length
- 291 words
- Files
- 5
- Skills in repo
- 1,108
- Repo updated
- First seen
- Licence
- None found
At a glance
Debug ML training issues and optimize performance including loss divergence, overfitting, and slow convergence
- Works in 5 steps: Diagnose Issue (8 min) → Analyze Root Cause (10 min) → Apply Fix (15 min) → …
- Tasks that involve Debugging
- SKILL.md covers Overview, When to Use, Phase 1: Diagnose Issue (8 min) and Phase 2: Analyze Root Cause…, plus 5 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
When Debugging ML Training Use ML Training Debugger is an agent skill from aiskillstore/marketplace. Debug ML training issues and optimize performance including loss divergence, overfitting, and slow convergence
Its SKILL.md is about 4.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `PROCESS.md`, `README.md` and `skill-report.json`).
It sits in Development, covering Debugging and Performance optimization. The repository describes itself as: Security-audited skills for Claude, Codex & Claude Code. One-click install, quality verified.
When your agent uses it
- Tasks that involve Debugging
- Tasks that involve Performance optimization
Example prompts
- “/when-debugging-ml-training-use-ml-training-debugger”
Requirements
- Python 3
Workflow steps
5 steps, taken from the step headings in SKILL.md.
- Diagnose Issue (8 min)
- Analyze Root Cause (10 min)
- Apply Fix (15 min)
- Validate Fix (12 min)
- Optimize Performance (5 min)
What it can do on your machine
Read from SKILL.md and the folder at commit ad8daf7. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are python and markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
When Debugging ML Training Use ML Training Debugger loads about 4.1k tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 291 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 291 words (~4,082 tokens).
“Systematic debugging workflow for ML training issues including loss divergence, overfitting, slow convergence, gradient problems, and performance optimization.”
- name
- when-debugging-ml-training-use-ml-training-debugger
- version
- 1.0.0
- category
- machine-learning
- tags
- debugging, ml, training, optimization, troubleshooting
- agents
- ml-developer, performance-analyzer, coder
- difficulty
- advanced
- estimated_duration
- 30-60min
- success_criteria
- Issue diagnosed correctly, Root cause identified, Fix applied successfully, Training convergence restored
- validation_method
- training_validation
- dependencies
- claude-flow@alpha, tensorflow/pytorch, tensorboard (for visualization)
- outputs
- Diagnostic report, Fixed model/training code, Performance comparison, Optimization recommendations
Files
SKILL.md and 4 other files in skills/dnyoussef/when-debugging-ml-training-use-ml-training-debugger of aiskillstore/marketplace.
- SKILL.md
- PROCESS.md
- README.md
- process-diagram.gv
- skill-report.json
Open the folder on GitHubat commit ad8daf7
Used in 1 other repository
We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in aiskillstore/marketplace, which our catalogue first saw on October 7, 2026.
Compare with similar skills
When Debugging ML Training Use ML Training Debugger next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| When Debugging ML Training Use ML Training Debugger this skillaiskillstore/marketplace | 430 | 1 repos | ~4.1k | Automated safety check: Pass | None | |
| Cmux Debugging Guidemanaflow-ai/cmux | 28k | 1 repos | ~1.1k | Automated safety check: Pass | Custom licence | |
| Electron Heap Snapshot Analysiskeybase/client | 9.3k | — | ~875 | Automated safety check: Pass | BSD-3-Clause | |
| Issue Fixmono/SkiaSharp | 5.6k | — | ~5.1k | Automated safety check: Pass | MIT | |
| PlotJuggler 4 Perf ProfilingPlotJuggler/PlotJuggler | 6.2k | — | ~1.6k | Automated safety check: Notes | MPL-2.0 | |
| Electron DevTools Trace Analysiskeybase/client | 9.3k | — | ~809 | Automated safety check: Pass | BSD-3-Clause |
Similar skills
Electron Heap Snapshot Analysis
keybase/client
Analyzes V8, Chrome and Electron .heapsnapshot files with Node scripts to find memory leaks, detached DOM nodes and the retainer paths that keep objects alive.
Issue Fix
mono/SkiaSharp
Fix bugs in SkiaSharp C bindings. An agent skill from mono/SkiaSharp.
PlotJuggler 4 Perf Profiling
PlotJuggler/PlotJuggler
Guides CPU profiling of PlotJuggler 4 on Linux with perf: count first, record cheaply with LBR, then read per-thread, flat, flamegraph or time-window views.
Electron DevTools Trace Analysis
keybase/client
Analyzes Chrome or Electron DevTools Performance trace exports with Python scripts to find where render time actually goes, without opening DevTools.
Python Performance Optimization
wshobson/agents
Profiles slow Python code with cProfile and memory profilers, then applies targeted fixes for CPU, memory, I/O and query bottlenecks.
More from aiskillstore/marketplace
All 1,108 skills in this repoCode Stats
aiskillstore/marketplace
Analyze codebase with tokei (fast line counts by language) and difft (semantic AST-aware diffs).
File Search
aiskillstore/marketplace
Modern file and content search using fd, ripgrep (rg), and fzf.
Data Processing
aiskillstore/marketplace
Process JSON with jq and YAML/TOML with yq. An agent skill from aiskillstore/marketplace.
Doc Scanner
aiskillstore/marketplace
Scans for project documentation files (AGENTS.md, CLAUDE.md, GEMINI.md, COPILOT.md, CURSOR.md, WARP.md, and 15+ other formats) and synthesizes guidance.
Find Replace
aiskillstore/marketplace
Modern find-and-replace using sd (simpler than sed) and batch replacement patterns.
Investigating Codebases
aiskillstore/marketplace
Automatically activated when user asks how something works, wants to understand unfamiliar code, needs to explore a new codebase, or asks questions like "where is X implemented?", "how does Y…
Related
Categories
Questions about When Debugging ML Training Use ML Training Debugger
What does When Debugging ML Training Use ML Training Debugger do?
Debug ML training issues and optimize performance including loss divergence, overfitting, and slow convergence. When Debugging ML Training Use ML Training Debugger is an agent skill from aiskillstore/marketplace.
When should I use When Debugging ML Training Use ML Training Debugger?
When Debugging ML Training Use ML Training Debugger fits situations like: tasks that involve Debugging; tasks that involve Performance optimization.
How do I install When Debugging ML Training Use ML Training Debugger in Claude Code?
Run `npx skills add aiskillstore/marketplace --skill when-debugging-ml-training-use-ml-training-debugger -a claude-code`. Or copy the skill folder (skills/dnyoussef/when-debugging-ml-training-use-ml-training-debugger in aiskillstore/marketplace) into .claude/skills/when-debugging-ml-training-use-ml-training-debugger in your project. Claude Code loads it when a task matches its description.
How do I install When Debugging ML Training Use ML Training Debugger in Codex?
Run `npx skills add aiskillstore/marketplace --skill when-debugging-ml-training-use-ml-training-debugger -a codex`. Or copy the skill folder (skills/dnyoussef/when-debugging-ml-training-use-ml-training-debugger in aiskillstore/marketplace) into .agents/skills/when-debugging-ml-training-use-ml-training-debugger in your project. Codex loads it when a task matches its description.
Can I use When Debugging ML Training Use ML Training Debugger in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aiskillstore/marketplace --skill when-debugging-ml-training-use-ml-training-debugger -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/when-debugging-ml-training-use-ml-training-debugger, .gemini/skills/when-debugging-ml-training-use-ml-training-debugger, .github/skills/when-debugging-ml-training-use-ml-training-debugger and .opencode/skills/when-debugging-ml-training-use-ml-training-debugger in your project.
What does When Debugging ML Training Use ML Training Debugger need to run?
SKILL.md names no scripts, command-line tools or credentials: When Debugging ML Training Use ML Training Debugger is instructions for the agent only. Our summary lists: Python 3.
Does When Debugging ML Training Use ML Training Debugger access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is When Debugging ML Training Use ML Training Debugger safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does When Debugging ML Training Use ML Training Debugger use?
No licence was found for When Debugging ML Training Use ML Training Debugger or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does When Debugging ML Training Use ML Training Debugger use?
About 4.1k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to When Debugging ML Training Use ML Training Debugger?
Skills that share tags, products or a category with When Debugging ML Training Use ML Training Debugger: Cmux Debugging Guide (manaflow-ai/cmux, 28k stars), Electron Heap Snapshot Analysis (keybase/client, 9.3k stars), Issue Fix (mono/SkiaSharp, 5.6k stars) and PlotJuggler 4 Perf Profiling (PlotJuggler/PlotJuggler, 6.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains When Debugging ML Training Use ML Training Debugger?
aiskillstore (a GitHub organization) maintains it in aiskillstore/marketplace, which has 430 GitHub stars. The repository holds 1,108 skills in this directory. The repository was last updated on October 7, 2026.
Source: aiskillstore/marketplace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.