lingzhi227/agent-research-skills

experiment-code

Write ML experiment code with iterative improvement.

Quelltext ansehen

Verwendung

  1. Installationsbefehl kopieren und das Quellpaket vor der Installation in der eigenen Agentenumgebung prüfen.
  2. Benötigte Werkzeuge, Zugangsdaten und Hosts im Original prüfen.
  3. Eingabe und gewünschtes Ergebnis beschreiben und die Ausgabe mit den Quellen abgleichen.
npx skills add https://github.com/lingzhi227/agent-research-skills --skill experiment-code

Vor dem Start

  • Die Installation umfasst weder Modellabo noch API-Kontingent oder Dateizugriffsrechte.
  • Sterne und Installationen zeigen Aktivität, keine unabhängige Qualitäts- oder Sicherheitsprüfung.
Originales Skill-Dokument

Aus dem Quell-Repository gerendert; Überschriften, Beispiele, Code, Tabellen, Links und Bilder bleiben erhalten.

Experiment Code

Generate and iteratively improve ML experiment code for research papers.

Input

  • $0 — Task: generate, improve, debug, plot
  • $1 — Research plan, idea description, or error message

References

  • Experiment prompts and patterns: ~/.claude/skills/experiment-code/references/experiment-prompts.md
  • Code patterns (error handling, repair, hill-climbing): ~/.claude/skills/experiment-code/references/code-patterns.md

Action: generate

Generate initial experiment code following this structure:

  1. Plan experiments first — List all runs needed (hyperparameter sweeps, ablations, baselines)
  2. Write self-contained code — All code in project directory, no external imports from reference repos
  3. Include proper logging — Save results to JSON, print intermediate metrics
  4. Generate figures — At minimum Figure1.png and Figure2.png

Mandatory Structure

project/
├── experiment.py      # Main experiment script
├── plot.py            # Visualization script
├── notes.txt          # Experiment descriptions and results
├── run_1/             # Results from run 1
│   └── final_info.json
├── run_2/
└── ...

Constraints

  • No placeholder code (pass, ..., raise NotImplementedError)
  • Must use actual datasets (not toy data unless explicitly requested)
  • PyTorch or scikit-learn preferred (no TensorFlow/Keras)
  • Each run uses: python experiment.py --out_dir=run_i

Action: improve

Improve existing experiment code:

  1. Read current code and results
  2. Reflect on what worked and what didn't
  3. Apply targeted edits (prefer small edits over full rewrites)
  4. Re-run and compare scores
  5. Keep the best-performing code variant

Action: debug

Fix experiment code errors:

  1. Read the error message (truncate to last 1500 chars if very long)
  2. Identify the root cause
  3. Apply minimal fix
  4. Up to 4 retry attempts before changing approach

Action: plot

Generate publication-quality plots from experiment results:

  1. Read all run_*/final_info.json files
  2. Generate comparison plots with proper labels
  3. Use the figure-generation skill for styling

Rules

  • Always plan experiments before writing code
  • After each run, document results in notes.txt
  • Include print statements explaining what results show
  • Method MUST not get 0% accuracy — verify accuracy calculations
  • Use seeds for reproducibility
  • Before each experiment include a print statement explaining exactly what the results are meant to show

Related Skills

Verwandte Aufgaben

aus demselben Repository

Weitere Skills

Alle Skills
lingzhi227
Community

backward-traceability

Make every number in the final PDF traceable to the exact code line that produced it. Uses \hypertarget/\hyperlink LaTeX commands and \num{formula} evaluated at compile time. Use for reproducibility and data integrity verification.

Installationen / 1h
2
GitHub Stars
451
Aktualisiert
27. Feb.
lingzhi227
Community

paper-assembly

Orchestrate the full paper pipeline end-to-end. Manage state propagation between phases (literature → plan → code → experiments → figures → tables → writing → review), support checkpointing and resumption. Use for assembling a complete paper from components.

Installationen / 1h
1
GitHub Stars
420
Aktualisiert
27. Feb.
lingzhi227
Community

literature-review

Conduct comprehensive literature reviews using multi-perspective dialogue simulation. Generate diverse expert personas, conduct grounded Q&A conversations, and synthesize findings into structured knowledge. Use when starting a new research project or writing a survey section.

Installationen / 1h
1
GitHub Stars
414
Aktualisiert
27. Feb.
lingzhi227
Community

algorithm-design

Design algorithms with LaTeX pseudocode and UML diagrams. Generate algorithmic environments, Mermaid class/sequence diagrams, and ensure consistency between pseudocode and implementation. Use when formalizing methods for a paper.

Installationen / 1h
2
GitHub Stars
390
Aktualisiert
27. Feb.