ML Engineer
RightNow-AI/openfang
Machine learning engineer expert for PyTorch, scikit-learn, model evaluation, and MLOps
A full ML pipeline where an agent team collaborates to perform data preparation, model design, training, evaluation, and deployment readiness.
Install ML Experiment
$ npx skills add revfactory/harness-100 --skill ml-experiment -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install revfactory/harness-100 ml-experiment --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/revfactory/harness-100.git skills-src && mkdir -p .claude/skills && cp -r skills-src/en/31-ml-experiment/.claude/skills/ml-experiment .claude/skills/ml-experiment && 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 "ml-experiment" agent skill from https://github.com/revfactory/harness-100/tree/main/en/31-ml-experiment/.claude/skills/ml-experiment into .claude/skills/ml-experiment/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ml-experiment", 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/revfactory/harness-100/tree/main/en/31-ml-experiment/.claude/skills/ml-experimentType 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 revfactory/harness-100 --skill ml-experiment -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install revfactory/harness-100 ml-experiment --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/revfactory/harness-100.git skills-src && mkdir -p .agents/skills && cp -r skills-src/en/31-ml-experiment/.claude/skills/ml-experiment .agents/skills/ml-experiment && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ml-experiment" agent skill from https://github.com/revfactory/harness-100/tree/main/en/31-ml-experiment/.claude/skills/ml-experiment into .agents/skills/ml-experiment/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ml-experiment", 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 revfactory/harness-100 --skill ml-experiment -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install revfactory/harness-100 ml-experiment --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/revfactory/harness-100.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/en/31-ml-experiment/.claude/skills/ml-experiment .cursor/skills/ml-experiment && 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 "ml-experiment" agent skill from https://github.com/revfactory/harness-100/tree/main/en/31-ml-experiment/.claude/skills/ml-experiment into .cursor/skills/ml-experiment/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ml-experiment", 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/revfactory/harness-100.git --path en/31-ml-experiment/.claude/skills/ml-experiment--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 revfactory/harness-100 --skill ml-experiment -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install revfactory/harness-100 ml-experiment --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/revfactory/harness-100.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/en/31-ml-experiment/.claude/skills/ml-experiment .gemini/skills/ml-experiment && 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 "ml-experiment" agent skill from https://github.com/revfactory/harness-100/tree/main/en/31-ml-experiment/.claude/skills/ml-experiment into .gemini/skills/ml-experiment/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ml-experiment", 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 revfactory/harness-100 ml-experimentInstalls 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 revfactory/harness-100 --skill ml-experiment -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/revfactory/harness-100.git skills-src && mkdir -p .github/skills && cp -r skills-src/en/31-ml-experiment/.claude/skills/ml-experiment .github/skills/ml-experiment && 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 "ml-experiment" agent skill from https://github.com/revfactory/harness-100/tree/main/en/31-ml-experiment/.claude/skills/ml-experiment into .github/skills/ml-experiment/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ml-experiment", 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 revfactory/harness-100 --skill ml-experiment -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install revfactory/harness-100 ml-experiment --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/revfactory/harness-100.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/en/31-ml-experiment/.claude/skills/ml-experiment .opencode/skills/ml-experiment && 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 "ml-experiment" agent skill from https://github.com/revfactory/harness-100/tree/main/en/31-ml-experiment/.claude/skills/ml-experiment into .opencode/skills/ml-experiment/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ml-experiment", 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
ml-experiment- GitHub stars
- 1.3k
- Token cost
- ~1.9k tokens
- SKILL.md length
- 674 words
- Files
- 1
- Skills in repo
- 464
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
A full ML pipeline where an agent team collaborates to perform data preparation, model design, training, evaluation, and deployment readiness.
- Works in 3 steps: Preparation (Orchestrator performs… → Team Assembly and Execution → Integration and Final Outputs
- Design an ML experiment
- SKILL.md covers Execution Mode, Agent Composition, Workflow and Scale-Based Modes, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
ML Experiment is an agent skill from revfactory/harness-100. A full ML pipeline where an agent team collaborates to perform data preparation, model design, training, evaluation, and deployment readiness. Use this skill for 'design an ML experiment', 'train a model', 'machine learning project', 'build a deep learning model', 'classification model', 'regression model', 'data preprocessing', 'model evaluation', 'hyperparameter tuning', 'MLOps setup', 'XGBoost model', 'PyTorch model', and other ML experiment tasks. Supports data-preprocessing-only or evaluation-only requests…
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Data & Analytics, covering Machine learning, Deep learning and MLOps. It works with Amazon SageMaker, Vertex AI and PyTorch. The licence is Apache-2.0.
When your agent uses it
- Design an ML experiment
- Machine learning project
- Build a deep learning model
- Classification model
Example prompts
- “design an ML experiment”
- “train a model”
- “machine learning project”
- “/ml-experiment”
Workflow steps
3 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 8e8d35c. 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.
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
ML Experiment loads about 1.9k tokens when it runs. Until then it costs about 186 tokens; SKILL.md has 674 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 revfactory/harness-100 at commit 8e8d35c, republished under its Apache-2.0 licence (© revfactory). 674 words, ~1,947 tokens.
Download SKILL.mdSave it as
.claude/skills/ml-experiment/SKILL.md (or your agent's skills folder).- name
- ml-experiment
- description
- A full ML pipeline where an agent team collaborates to perform data preparation, model design, training, evaluation, and deployment readiness. Use this skill for 'design an ML experiment', 'train a model', 'machine learning project', 'build a deep learning model', 'classification model', 'regression model', 'data preprocessing', 'model evaluation', 'hyperparameter tuning', 'MLOps setup', 'XGBoost model', 'PyTorch model', and other ML experiment tasks. Supports data-preprocessing-only or evaluation-only requests as well. Note: model serving infrastructure (SageMaker/Vertex AI) direct deployment, large-scale distributed training cluster management, and real-time inference service operation are outside this skill's scope.
ML Experiment — Full ML Pipeline
An agent team collaborates to perform the full ML experiment lifecycle: data preparation → model design → training → evaluation → deployment readiness.
Execution Mode
Agent Team — 5 members communicate directly via SendMessage and cross-validate.
Agent Composition
| Agent | File | Role | Type |
|---|---|---|---|
| data-engineer | .claude/agents/data-engineer.md | Collection, preprocessing, feature engineering | general-purpose |
| model-designer | .claude/agents/model-designer.md | Architecture, hyperparameters, loss functions | general-purpose |
| training-manager | .claude/agents/training-manager.md | Experiment tracking, checkpoints, reproducibility | general-purpose |
| evaluation-analyst | .claude/agents/evaluation-analyst.md | Metrics, bias verification, interpretability | general-purpose |
| experiment-reviewer | .claude/agents/experiment-reviewer.md | Cross-validation, reproducibility, final report | general-purpose |
Workflow
Phase 1: Preparation (Orchestrator performs directly)
- Extract from user input:
- Problem Definition: Classification/regression/generation/recommendation/time-series, etc.
- Data: Data source, files, format, scale
- Target Metric: Specific goals such as accuracy, F1, RMSE
- Constraints (optional): Framework, GPU, inference speed, model size
- Existing Code (optional): Existing models, preprocessing code, experiment results
- Create
_workspace/directory at the project root - Organize input and save to
_workspace/00_input.md - If existing files are present, copy to
_workspace/and skip the corresponding Phase - Determine execution mode based on request scope
Phase 2: Team Assembly and Execution
| Order | Task | Owner | Dependencies | Output |
|---|---|---|---|---|
| 1 | Data Preparation | data-engineer | None | _workspace/01_data_preparation.md |
| 2 | Model Design | model-designer | Task 1 | _workspace/02_model_design.md |
| 3 | Training Setup | training-manager | Tasks 1, 2 | _workspace/03_training_config.md |
| 4 | Evaluation Analysis | evaluation-analyst | Tasks 1, 2, 3 | _workspace/04_evaluation_report.md |
| 5 | Experiment Review | experiment-reviewer | Tasks 1-4 | _workspace/05_review_report.md |
Inter-team communication flow:
- data-engineer completes → Sends feature/shape/data characteristics to model-designer, data loader to training, class distribution to evaluation
- model-designer completes → Sends model code/hyperparameter space to training, model structure/evaluation metrics to evaluation
- training completes → Sends training curves/best model/experiment logs to evaluation
- evaluation completes → Sends evaluation report to reviewer
- reviewer cross-validates all outputs. If 🔴 must-fix issues found, sends correction requests to the relevant agent → rework → re-verify (up to 2 times)
Phase 3: Integration and Final Outputs
- Check all files in
_workspace/ - Verify that all 🔴 must-fix items from the review report have been addressed
- Report final summary to the user:
- Data Preparation —
01_data_preparation.md - Model Design —
02_model_design.md - Training Configuration —
03_training_config.md - Evaluation Report —
04_evaluation_report.md - Review Report —
05_review_report.md - Experiment Code —
experiment_code/
- Data Preparation —
Scale-Based Modes
| User Request Pattern | Execution Mode | Agents Deployed |
|---|---|---|
| "Design the full ML experiment" | Full Pipeline | All 5 |
| "Preprocess the data" | Data Mode | data-engineer + reviewer |
| "Design the model architecture" | Model Mode | model-designer + reviewer |
| "Evaluate this model" (existing results) | Evaluation Mode | evaluation-analyst + reviewer |
| "Review this experiment" | Review Mode | reviewer only |
Leveraging existing files: If the user provides preprocessing code, trained models, etc., skip the corresponding steps.
Show full SKILL.md (281 more words)Show less
Data Transfer Protocol
| Strategy | Method | Purpose |
|---|---|---|
| File-based | _workspace/ directory | Primary output storage and sharing |
| Code-based | _workspace/experiment_code/ | Executable code |
| Message-based | SendMessage | Real-time key information transfer, correction requests |
File naming convention: {order}_{agent}_{output}.{extension}
Error Handling
| Error Type | Strategy |
|---|---|
| Data not provided | Recommend public datasets + provide synthetic data generation code |
| No GPU | CPU-optimized settings + prioritize lightweight models |
| Problem type unclear | Infer from data characteristics + request user confirmation |
| Training divergence | Suggest LR reduction, Gradient Clipping, batch size adjustment |
| Agent failure | 1 retry → proceed without that output if failed, note omission in review report |
| 🔴 found in review | Send correction request to relevant agent → rework → re-verify (up to 2 times) |
Test Scenarios
Normal Flow
Prompt: "Build a survival prediction classification model using the Kaggle Titanic dataset. Target F1 score above 0.85." Expected Results:
- Data: EDA (missing values, distributions, correlations), preprocessing pipeline (Imputer+Scaler+Encoder), stratified split
- Model: Baseline (LogisticRegression) + XGBoost + RandomForest design
- Training: Optuna hyperparameter tuning, MLflow experiment tracking
- Evaluation: Confusion Matrix, SHAP analysis, model comparison, statistical verification
- Review: No data leakage confirmed, reproducibility confirmed, conclusion validity verified
Existing File Flow
Prompt: "Evaluate this trained model and suggest improvement directions" + model file attached Expected Results:
- Copy existing model to
_workspace/ - Evaluation mode: evaluation-analyst + reviewer deployed
- Performance analysis, error analysis, improvement recommendations provided
Error Flow
Prompt: "Build a machine learning model, but I don't have data yet" Expected Results:
- Request problem type confirmation
- Recommend 3-5 public datasets (UCI/Kaggle/HuggingFace)
- Provide synthetic data generation code
- State "Full pipeline can be executed after data acquisition"
Agent Extension Skills
| Skill | Path | Enhanced Agent | Role |
|---|---|---|---|
| feature-engineering-cookbook | .claude/skills/feature-engineering-cookbook/skill.md | data-engineer | Numeric/categorical/time-series transformations, feature selection, data leakage prevention |
| model-selection-guide | .claude/skills/model-selection-guide/skill.md | model-designer, evaluation-analyst | Model recommendations by problem, hyperparameter tuning, ensembles |
| experiment-tracking-setup | .claude/skills/experiment-tracking-setup/skill.md | training-manager | MLflow setup, reproducibility, model registry, experiment comparison |
© revfactory, 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
Just SKILL.md in en/31-ml-experiment/.claude/skills/ml-experiment of revfactory/harness-100.
Open the folder on GitHubat commit 8e8d35c
Compare with similar skills
ML Experiment 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 |
|---|---|---|---|---|---|---|
| ML Experiment this skillrevfactory/harness-100 | 1.3k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | |
| ML EngineerRightNow-AI/openfang | 18k | — | ~987 | Automated safety check: Pass | Apache-2.0 | |
| Databricks ML Trainingdatabricks/databricks-agent-skills | 345 | — | ~4.6k | Automated safety check: Pass | Custom licence | |
| Editomegaml/omegaml | 107 | — | ~206 | Automated safety check: Pass | Apache-2.0 | |
| AI ML Engineertheneoai/awesome-skills | 183 | — | ~2.9k | Automated safety check: Pass | MIT | |
| Senior ML Engineerdavila7/claude-code-templates | 32k | 3 repos | ~1.4k | Automated safety check: Pass | MIT |
Similar skills
- Official
Databricks ML Training
databricks/databricks-agent-skills
Train ML models on Databricks. An agent skill from databricks/databricks-agent-skills.
Edit
omegaml/omegaml
how to use the edit command properly
AI ML Engineer
theneoai/awesome-skills
Expert AI/ML Engineer with deep MLOps expertise. An agent skill from theneoai/awesome-skills.
Senior ML Engineer
davila7/claude-code-templates
World-class ML engineering skill for productionizing ML models, MLOps, and building scalable ML systems.
ML Model Training
secondsky/claude-skills
Train ML models with scikit-learn, PyTorch, TensorFlow. An agent skill from secondsky/claude-skills.
More from revfactory/harness-100
All 464 skills in this repoAnti Bot Analyzer
revfactory/harness-100
A skill for analyzing website anti-bot defense mechanisms and developing legitimate evasion strategies.
API Error Design Patterns
revfactory/harness-100
Reference for designing how an API reports failures: structured error codes, response shapes, client-friendly messages, an error catalog and retry or fallback advice.
API Security Checklist
revfactory/harness-100
Walks a backend-dev agent through OWASP API Top 10 checks, authentication and authorization patterns, and defense code during API design.
Arg Parser Generator
revfactory/harness-100
Methodology for systematically designing and generating CLI tool argument parser structures.
Audience Segmentation
revfactory/harness-100
Audience segmentation skill used by the analyst and curator agents.
Audio Storytelling
revfactory/harness-100
Audio storytelling skill used by the podcast scriptwriter and show note editor.
Related
Works with
Categories
Questions about ML Experiment
What does ML Experiment do?
A full ML pipeline where an agent team collaborates to perform data preparation, model design, training, evaluation, and deployment readiness. ML Experiment is an agent skill from revfactory/harness-100. A full ML pipeline where an agent team collaborates to perform data preparation, model design, training, evaluation, and deployment readiness.
When should I use ML Experiment?
ML Experiment fits situations like: design an ML experiment; machine learning project; build a deep learning model; classification model.
How do I install ML Experiment in Claude Code?
Run `npx skills add revfactory/harness-100 --skill ml-experiment -a claude-code`. Or copy the skill folder (en/31-ml-experiment/.claude/skills/ml-experiment in revfactory/harness-100) into .claude/skills/ml-experiment in your project. Claude Code loads it when a task matches its description.
How do I install ML Experiment in Codex?
Run `npx skills add revfactory/harness-100 --skill ml-experiment -a codex`. Or copy the skill folder (en/31-ml-experiment/.claude/skills/ml-experiment in revfactory/harness-100) into .agents/skills/ml-experiment in your project. Codex loads it when a task matches its description.
Can I use ML Experiment 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 revfactory/harness-100 --skill ml-experiment -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ml-experiment, .gemini/skills/ml-experiment, .github/skills/ml-experiment and .opencode/skills/ml-experiment in your project.
What does ML Experiment need to run?
SKILL.md names no scripts, command-line tools or credentials: ML Experiment is instructions for the agent only.
Does ML Experiment 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 ML Experiment 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 ML Experiment use?
ML Experiment 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 ML Experiment use?
About 1.9k tokens (SKILL.md is roughly 7.8k 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 ML Experiment?
Skills that share tags, products or a category with ML Experiment: ML Engineer (RightNow-AI/openfang, 18k stars), Databricks ML Training (databricks/databricks-agent-skills, 345 stars), Edit (omegaml/omegaml, 107 stars) and AI ML Engineer (theneoai/awesome-skills, 183 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains ML Experiment?
revfactory (a GitHub user) maintains it in revfactory/harness-100, which has 1,290 GitHub stars. The repository holds 464 skills in this directory. The repository was last updated on March 22, 2026.
Source: revfactory/harness-100 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.