Ito Training
affaan-m/ECC
Inspect the availability of ML training on a completed Itô compute booking and, when the canonical backend becomes available, hand off an explicitly confirmed training manifest.
Look at what the ACTIVE teach run is practicing right now: renders the live checkpoint under the trainer's own env knobs (actuator, spawn mix, reward gates — read from the live trainer process) and…
Apache-2.0Auto-check passed
Install Watch Training
$ npx skills add jonathanhawkins/microduck-lab --skill watch-training -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jonathanhawkins/microduck-lab watch-training --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/jonathanhawkins/microduck-lab.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/watch-training .claude/skills/watch-training && 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 "watch-training" agent skill from https://github.com/jonathanhawkins/microduck-lab/tree/main/.claude/skills/watch-training into .claude/skills/watch-training/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "watch-training", 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/jonathanhawkins/microduck-lab/tree/main/.claude/skills/watch-trainingType 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 jonathanhawkins/microduck-lab --skill watch-training -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jonathanhawkins/microduck-lab watch-training --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jonathanhawkins/microduck-lab.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/watch-training .agents/skills/watch-training && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "watch-training" agent skill from https://github.com/jonathanhawkins/microduck-lab/tree/main/.claude/skills/watch-training into .agents/skills/watch-training/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "watch-training", 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 jonathanhawkins/microduck-lab --skill watch-training -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jonathanhawkins/microduck-lab watch-training --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jonathanhawkins/microduck-lab.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/watch-training .cursor/skills/watch-training && 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 "watch-training" agent skill from https://github.com/jonathanhawkins/microduck-lab/tree/main/.claude/skills/watch-training into .cursor/skills/watch-training/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "watch-training", 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/jonathanhawkins/microduck-lab.git --path .claude/skills/watch-training--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 jonathanhawkins/microduck-lab --skill watch-training -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jonathanhawkins/microduck-lab watch-training --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jonathanhawkins/microduck-lab.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/watch-training .gemini/skills/watch-training && 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 "watch-training" agent skill from https://github.com/jonathanhawkins/microduck-lab/tree/main/.claude/skills/watch-training into .gemini/skills/watch-training/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "watch-training", 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 jonathanhawkins/microduck-lab watch-trainingInstalls 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 jonathanhawkins/microduck-lab --skill watch-training -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jonathanhawkins/microduck-lab.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/watch-training .github/skills/watch-training && 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 "watch-training" agent skill from https://github.com/jonathanhawkins/microduck-lab/tree/main/.claude/skills/watch-training into .github/skills/watch-training/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "watch-training", 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 jonathanhawkins/microduck-lab --skill watch-training -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jonathanhawkins/microduck-lab watch-training --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jonathanhawkins/microduck-lab.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/watch-training .opencode/skills/watch-training && 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 "watch-training" agent skill from https://github.com/jonathanhawkins/microduck-lab/tree/main/.claude/skills/watch-training into .opencode/skills/watch-training/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "watch-training", 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
watch-training- GitHub stars
- 132
- Token cost
- ~525 tokens
- SKILL.md length
- 226 words
- Files
- 2
- Skills in repo
- 7
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Look at what the ACTIVE teach run is practicing right now: renders the live checkpoint under the trainer's own env knobs (actuator, spawn mix, reward gates — read from the live trainer process) and…
- : watch the training
- Runs Shell scripts from its folder; calls bash
- What is it practicing
- Screenshot the training
What it does
Watch Training is an agent skill from jonathanhawkins/microduck-lab. Look at what the ACTIVE teach run is practicing right now: renders the live checkpoint under the trainer's own env knobs (actuator, spawn mix, reward gates — read from the live trainer process) and writes contact sheets to read. Use during any training run to visually verify the behavior instead of steering by reward curves — charts have hidden one-sided flops, neck-leans, and parking that a single glance at frames caught. Trigger on: "watch the training", "what is it practicing", "screenshot the training", "is…
Its SKILL.md is about 530 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `watch.sh`).
The repository describes itself as: Train RL policies for the Pollen Microduck 🦆 on an ordinary Mac, no CUDA GPU, and watch them learn live in the browser. The licence is Apache-2.0.
When your agent uses it
- : watch the training
- What is it practicing
- Screenshot the training
- Is training doing the right thing
Example prompts
- “watch the training”
- “what is it practicing”
- “screenshot the training”
- “/watch-training”
Requirements
- A Bash shell
What it can do on your machine
Read from SKILL.md and the folder at commit bbf0326. 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
Ships script files (Shell), which the agent can run.
Shell commands in SKILL.md call:
bash
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
Watch Training loads about 525 tokens when it runs. Until then it costs about 141 tokens; SKILL.md has 226 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
The full file from jonathanhawkins/microduck-lab at commit bbf0326, republished under its Apache-2.0 licence (© jonathanhawkins). 226 words, ~525 tokens.
Download SKILL.mdSave it as
.claude/skills/watch-training/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- watch-training
- description
- Look at what the ACTIVE teach run is practicing right now: renders the live checkpoint under the trainer's own env knobs (actuator, spawn mix, reward gates — read from the live trainer process) and writes contact sheets to read. Use during any training run to visually verify the behavior instead of steering by reward curves — charts have hidden one-sided flops, neck-leans, and parking that a single glance at frames caught. Trigger on: "watch the training", "what is it practicing", "screenshot the training", "is training doing the right thing".
watch-training — look at the live student, under its own rules
Reward curves between stages have repeatedly hidden what a policy actually
practices (a flat hold that was a one-sided leg-flop; a rising hold that was
spawn handouts). This skill renders the ACTIVE run's live.onnx under the
exact env the trainer subprocess is using — same actuator, same spawn family
mix, same reward-gate knobs — so the frames show the true current drill.
bash .claude/skills/watch-training/watch.shThen Read the printed ep*_sheet.png files (they are images; captions
carry trunk/head heights, pitch, contacts — see the render-rollout skill for
how to read them). Optional args pass through to render-rollout, e.g.
--seconds 12 --sheet-frames 20.
Notes:
- Read-only: never restarts training or the lab; safe at any time. It does
compete for CPU, so it runs under
niceand short episodes by default. - It needs a live trainer (it reads the knobs from the process env); for a FINISHED run use render-rollout directly and pass the stage knobs by hand (including the actuator the run's own stage declares (watch.sh harvests it from the live trainer, so it is already correct)).
- Monitoring loop pattern: call it at every stage boundary and mid-stage
telemetry checkpoint, and READ the sheet before trusting any curve. A
subagent can do the same: run the script, read the sheets, report what
the duck is physically doing and whether it matches the stage's
detail.
© jonathanhawkins, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in .claude/skills/watch-training of jonathanhawkins/microduck-lab.
- SKILL.md
- watch.sh
Open the folder on GitHubat commit bbf0326
Compare with similar skills
Watch Training 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 |
|---|---|---|---|---|---|---|
| Watch Training this skilljonathanhawkins/microduck-lab | 132 | — | ~525 | Automated safety check: Pass | Apache-2.0 | |
| Ito Trainingaffaan-m/ECC | 276k | 1 repos | ~1.5k | Automated safety check: Pass | MIT | |
| Ray Train Distributed TrainingOrchestra-Research/AI-Research-SKILLs | 13k | 2 repos | ~2.7k | Automated safety check: Pass | MIT | |
| Teachcursor/plugins | 11k | 9 repos | ~1.4k | Automated safety check: Pass | None | |
| Fal Trainnexu-io/open-design | 100k | — | ~293 | Automated safety check: Pass | Apache-2.0 | |
| Train Poseruvnet/RuView | 97k | — | ~504 | Automated safety check: Pass | MIT |
Similar skills
Ray Train Distributed Training
Orchestra-Research/AI-Research-SKILLs
Scales PyTorch, TensorFlow and Hugging Face training from a single GPU to multi-node clusters with Ray Train, including Ray Tune sweeps and checkpoint recovery.
- Official
Teach
cursor/plugins
Explain a body of work plainly so a person actually understands it.
Fal Train
nexu-io/open-design
Train custom AI models (LoRA) on fal.ai for personalized image generation tailored to a brand, character, or style.
Train Pose
ruvnet/RuView
Train/evaluate WiFi pose models honestly — camera-supervised (MediaPipe + CSI) and camera-free (WiFlow), always checked against the mean-pose baseline before any PCK is quoted.
Neural Training
ruvnet/ruflo
Neural pattern training with SONA (Self-Optimizing Neural Architecture), MoE (Mixture of Experts), and EWC++ for knowledge consolidation.
More from jonathanhawkins/microduck-lab
Record World
jonathanhawkins/microduck-lab
Record a /sim WORLD scenario — the living room, the playroom tidy loop, a soccer pitch, any scenario JSON — to an mp4, a captioned contact sheet and an events log, headless and under a seed, then…
Render Rollout
jonathanhawkins/microduck-lab
Render a microduck policy rollout to video AND to a frame contact sheet with per-frame diagnostics burned in, then READ the sheet to see what the policy actually does.
Tidy Trace
jonathanhawkins/microduck-lab
Debug the playroom tidy loop (Track 12) — trace one run state by state, see every release, landing and fall with context, and re-measure the walker facts the brain's constants rest on.
Train Loop
jonathanhawkins/microduck-lab
Run the CLOSED training loop on a MOSS/duck policy without a human having to ask "is it done yet": launch through the lab, block until the run finishes, print the standard report and the per-term…
Restart Servers
jonathanhawkins/microduck-lab
Restart the microduck dev stack — the duck-lab backend (farm, :8788) and the duck-viewer dev server (:63317).
Sim Smoke
jonathanhawkins/microduck-lab
Look at the /sim world page the way a user would — bring up the lab in world mode and the viewer, open the page in headless Chromium, press keys, screenshot it, and READ the screenshot and console.
Questions about Watch Training
What does Watch Training do?
Look at what the ACTIVE teach run is practicing right now: renders the live checkpoint under the trainer's own env knobs (actuator, spawn mix, reward gates — read from the live trainer process) and…. Watch Training is an agent skill from jonathanhawkins/microduck-lab. Look at what the ACTIVE teach run is practicing right now: renders the live checkpoint under the trainer's own env knobs (actuator, spawn mix, reward gates — read from the live trainer process) and writes contact sheets to read.
When should I use Watch Training?
Watch Training fits situations like: : watch the training; what is it practicing; screenshot the training; is training doing the right thing.
How do I install Watch Training in Claude Code?
Run `npx skills add jonathanhawkins/microduck-lab --skill watch-training -a claude-code`. Or copy the skill folder (.claude/skills/watch-training in jonathanhawkins/microduck-lab) into .claude/skills/watch-training in your project. Claude Code loads it when a task matches its description.
How do I install Watch Training in Codex?
Run `npx skills add jonathanhawkins/microduck-lab --skill watch-training -a codex`. Or copy the skill folder (.claude/skills/watch-training in jonathanhawkins/microduck-lab) into .agents/skills/watch-training in your project. Codex loads it when a task matches its description.
Can I use Watch Training 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 jonathanhawkins/microduck-lab --skill watch-training -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/watch-training, .gemini/skills/watch-training, .github/skills/watch-training and .opencode/skills/watch-training in your project.
What does Watch Training need to run?
Going by SKILL.md and its folder, Watch Training needs a shell for the scripts in its folder and the command-line tools its instructions call (bash). Our summary lists: A Bash shell.
Does Watch Training 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 Watch Training 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 Watch Training use?
Watch Training is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Watch Training use?
About 525 tokens (SKILL.md is roughly 2.1k 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 Watch Training?
Skills that share tags, products or a category with Watch Training: Ito Training (affaan-m/ECC, 276k stars), Ray Train Distributed Training (Orchestra-Research/AI-Research-SKILLs, 13k stars), Teach (cursor/plugins, 11k stars) and Fal Train (nexu-io/open-design, 100k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Watch Training?
jonathanhawkins (a GitHub user) maintains it in jonathanhawkins/microduck-lab, which has 132 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 1, 2026.
Source: jonathanhawkins/microduck-lab on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.