New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Experiment Code

by lingzhi227 in lingzhi227/agent-research-skills

Write ML experiment code with iterative improvement. An agent skill from lingzhi227/agent-research-skills.

No licenceAuto-check passedResearch & Science

Install Experiment Code

skills CLI
$ npx skills add lingzhi227/agent-research-skills --skill experiment-code -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install lingzhi227/agent-research-skills experiment-code --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/lingzhi227/agent-research-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/experiment-code .claude/skills/experiment-code && rm -rf skills-src

Use ~/.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/

Facts

Skill name
experiment-code
GitHub stars
384
Token cost
~774 tokens
SKILL.md length
293 words
Files
3 (incl. references)
Skills in repo
31
Repo updated
First seen
Licence
None found

At a glance

Write ML experiment code with iterative improvement. An agent skill from lingzhi227/agent-research-skills.

  • Works in 4 steps: Plan experiments first — List all runs… → Write self-contained code — All code in… → Include proper logging — Save results to… → …
  • Implementing experiments for a research paper
  • SKILL.md covers Input, References, Action: generate and Action: improve, plus 4 more sections
  • Calls python

What it does

Experiment Code is an agent skill from lingzhi227/agent-research-skills. Write ML experiment code with iterative improvement. Generate training/evaluation pipelines, debug errors, and optimize results through code reflection. Use when implementing experiments for a research paper.

Its SKILL.md is about 770 tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/code-patterns.md` and `references/experiment-prompts.md`).

It sits in Research & Science. The repository describes itself as: Skills for Claude Code — deep-research: systematic academic literature review.

When your agent uses it

  • Implementing experiments for a research paper

Example prompts

  • “/experiment-code”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  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 Figure_1.png and Figure_2.png

What it can do on your machine

Read from SKILL.md and the folder at commit 9e6c085. 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

    Shell commands in SKILL.md call:

    • python

    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

Experiment Code loads about 774 tokens when it runs, and up to ~3.6k if it reads all its reference files. Until then it costs about 56 tokens; SKILL.md has 293 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~56
When it runs · the whole SKILL.md, loaded when a task matches
~774
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.6k

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 293 words (~774 tokens).

“Generate and iteratively improve ML experiment code for research papers.”

— opening of SKILL.md by lingzhi227
name
experiment-code
argument-hint
plan-or-idea

Read the full SKILL.md on GitHub

Files

SKILL.md and 2 other files (references) in skills/experiment-code of lingzhi227/agent-research-skills.

  • SKILL.md
  • references/code-patterns.md
  • references/experiment-prompts.md

Open the folder on GitHubat commit 9e6c085

Compare with similar skills

Experiment Code 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.

Experiment Code compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Experiment Code this skilllingzhi227/agent-research-skills384—~774Automated safety check: PassNone
Hypothesis Generationspacering-net/codeg3.8k15 repos~3.6kAutomated safety check: NotesMIT
GitHub Deep Researchbytedance/deer-flow83k5 repos~1.3kAutomated safety check: PassMIT
Nature Paper CardYuan1z0825/nature-skills46k2 repos~2.1kAutomated safety check: PassApache-2.0
Read arXiv Paperkarpathy/nanochat58k2 repos~494Automated safety check: PassMIT
Content Research Writerweapp-tailwindcss/weapp-tailwindcss1.9k25 repos~3.5kAutomated safety check: PassMIT

Similar skills

  • Hypothesis Generation

    spacering-net/codeg

    Structured hypothesis formulation from observations. An agent skill from spacering-net/codeg.

    3.8k GitHub starsUsed in 15 repos~3.6k tokens
    Research & ScienceAuto-check: notes

  • GitHub Deep Research

    bytedance/deer-flow

    Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.

    83k GitHub starsUsed in 5 repos~1.3k tokens
    Research & ScienceAuto-check passed

  • Nature Paper Card

    Yuan1z0825/nature-skills

    Builds a structured deep-reading card for one scientific paper, covering methods, how experiments support claims, limitations and research ideas, with a script to prepare the source.

    46k GitHub starsUsed in 2 repos~2.1k tokens
    Research & ScienceAuto-check passed

  • Read arXiv Paper

    karpathy/nanochat

    Fetches the TeX source of an arXiv paper from its URL, reads it and writes a markdown summary tied to the nanochat project.

    58k GitHub starsUsed in 2 repos~494 tokens
    Research & ScienceAuto-check passed

  • Content Research Writer

    weapp-tailwindcss/weapp-tailwindcss

    Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section.

    1.9k GitHub starsUsed in 25 repos~3.5k tokens
    Research & ScienceAuto-check passed

  • Peer Review

    spacering-net/codeg

    Structured manuscript/grant review with checklist-based evaluation.

    3.8k GitHub starsUsed in 18 repos~5.9k tokens
    Research & ScienceAuto-check: notes

More from lingzhi227/agent-research-skills

All 31 skills in this repo

  • Backward Traceability

    lingzhi227/agent-research-skills

    Makes each number in a LaTeX paper link back to the code line that produced it, using hypertarget and hyperlink tags and compile-time `\num` formulas.

    384 GitHub stars~802 tokensUpdated 7 mo ago
    Auto-check passed

  • Statistical Data Analysis

    lingzhi227/agent-research-skills

    Writes statistical analysis code for experimental data, runs it through a four-round review, and reports effect sizes, p-values and confidence intervals.

    384 GitHub stars~886 tokensUpdated 7 mo ago
    Auto-check passed

  • Excalidraw Canvas Toolkit

    lingzhi227/agent-research-skills

    Draws and refines Excalidraw diagrams on a live canvas through MCP tools or a REST API, with screenshots, file import and export, snapshots and Mermaid conversion.

    384 GitHub stars~3.8k tokensUpdated 7 mo ago
    Auto-check passed

  • Research Experiment Designer

    lingzhi227/agent-research-skills

    Plans research experiments in four progressive stages, from a first working implementation through baseline tuning and creative research to ablation studies.

    384 GitHub stars~752 tokensUpdated 7 mo ago
    Auto-check passed

  • Scientific Figure Generation

    lingzhi227/agent-research-skills

    Generates publication-quality scientific figures with matplotlib or seaborn through query expansion, a run-and-retry coding loop and a visual check of the rendered PNG.

    384 GitHub stars~809 tokensUpdated 7 mo ago
    Auto-check passed

  • Research Idea Generation

    lingzhi227/agent-research-skills

    Generates and iteratively refines research ideas for a given area, checking each one's novelty against Semantic Scholar and arXiv, and scoring it on interestingness, feasibility and novelty.

    384 GitHub stars~747 tokensUpdated 7 mo ago
    Auto-check passed

Categories

Questions about Experiment Code

What does Experiment Code do?

Write ML experiment code with iterative improvement. An agent skill from lingzhi227/agent-research-skills. Experiment Code is an agent skill from lingzhi227/agent-research-skills. Write ML experiment code with iterative improvement.

When should I use Experiment Code?

Experiment Code fits situations like: implementing experiments for a research paper.

How do I install Experiment Code in Claude Code?

Run `npx skills add lingzhi227/agent-research-skills --skill experiment-code -a claude-code`. Or copy the skill folder (skills/experiment-code in lingzhi227/agent-research-skills) into .claude/skills/experiment-code in your project. Claude Code loads it when a task matches its description.

How do I install Experiment Code in Codex?

Run `npx skills add lingzhi227/agent-research-skills --skill experiment-code -a codex`. Or copy the skill folder (skills/experiment-code in lingzhi227/agent-research-skills) into .agents/skills/experiment-code in your project. Codex loads it when a task matches its description.

Can I use Experiment Code 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 lingzhi227/agent-research-skills --skill experiment-code -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/experiment-code, .gemini/skills/experiment-code, .github/skills/experiment-code and .opencode/skills/experiment-code in your project.

What does Experiment Code need to run?

Going by SKILL.md and its folder, Experiment Code needs the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Experiment Code 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 Experiment Code 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 Experiment Code use?

No licence was found for Experiment Code or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Experiment Code use?

About 774 tokens (SKILL.md is roughly 3.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.8k tokens, read only when the agent opens those files.

What are the alternatives to Experiment Code?

Skills that share tags, products or a category with Experiment Code: Hypothesis Generation (spacering-net/codeg, 3.8k stars), GitHub Deep Research (bytedance/deer-flow, 83k stars), Nature Paper Card (Yuan1z0825/nature-skills, 46k stars) and Read arXiv Paper (karpathy/nanochat, 58k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Experiment Code?

lingzhi227 (a GitHub user) maintains it in lingzhi227/agent-research-skills, which has 384 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on February 27, 2026.

Source: lingzhi227/agent-research-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.