Skip to main content
affpapa.org
RU EN
skill CX Codex

symbolic-equation — Claude Code skill: what it does, how to install

Discovers scientific equations from numerical datasets using LLM-guided evolutionary search. Useful for symbolic regression and extracting interpretable physical laws.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add lingzhi227/agent-research-skills --skill symbolic-equation -a claude-code
Open on GitHub

What symbolic-equation does

The skill implements the LLM-SR approach to discover mathematical equations from data. It expects input arrays such as np.ndarray, target variables, and physical context. The language model generates candidate formulas as versioned Python functions, checking each against negative MSE.

Candidate solutions live across independent populations called islands, with 10 islands by default. The system clusters formulas by score signatures and samples them using a temperature-controlled softmax. Higher temperatures promote early exploration. Later iterations focus strictly on the top clusters.

Parameter tuning requires scipy BFGS or Adam. Discovered expressions must use standard mathematical operations, and recursive functions are strictly forbidden. Every 4 hours, the bottom half of the islands resets to prevent convergence traps. The search favors shorter equations when accuracy is equal.

What it helps with

  • discover an analytical equation from experimental data points
  • model physical oscillator dynamics using input arrays
  • optimize equation parameters using scipy BFGS or Adam
  • extract interpretable mathematical laws instead of black-box models

Example prompts for the agent

  • Find an acceleration equation for a damped oscillator using input arrays x and v
  • Run symbolic regression to predict pressure from temperature and volume data
  • Discover a mathematical relation for target variable y given features x1 and x2

How to install symbolic-equation

1Skills CLI (Vercel)

npx skills add lingzhi227/agent-research-skills --skill symbolic-equation -a claude-code

2Manually: put the files in place

~/.claude/skills/symbolic-equation/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/symbolic-equation/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about symbolic-equation

How do I install symbolic-equation in Claude Code?

Run npx skills add lingzhi227/agent-research-skills --skill symbolic-equation -a claude-code. The files will be placed in ~/.claude/skills/symbolic-equation/SKILL.md.

What does symbolic-equation do?

It discovers interpretable mathematical equations from datasets using LLM-guided evolutionary search. The tool maintains multi-island populations and optimizes fitness via negative MSE.

What constraints apply to the generated equations?

Formulas must rely only on standard math operations without recursion. Free parameters are fitted using scipy BFGS or Adam, and simpler expressions are preferred over complex ones.

Similar skills

Everything for Science and research →
scipy-best-practices Mindrally A skill that gives your coding agent rules for SciPy work: optimization, linear algebra, stats, signal processing. Useful when the Python code does math, not UI. CX Codex +1 1,000installs correlation-analysis agiprolabs Computes correlations between assets: rolling windows, hierarchical clustering, tail dependence. Useful for diversification checks and pairs trading. CX Codex +1 464installs statistics-math pluginagentmarketplace A coding-agent skill with Python recipes for statistics, probability, linear algebra and regression. Useful when you need to compute metrics or test a hypothesis. CX Codex +1 432installs matplotlib tondevrel A skill that tells your agent how to build matplotlib figures: line and scatter plots, heatmaps, multi-panel layouts. Useful when the data sits in NumPy or Pandas and the output goes into a paper or report. CX Codex +1 374installs zarr-python K-Dense-AI Stores and queries chunked N-D scientific arrays with Zarr-Python 3. Useful for configuring sharding, codecs, and remote storage access. CX Codex +1 1,900installs

From the same set23

novelty-assessment Runs a research idea through literature search and returns a verdict: novel or not. Useful before you commit to a direction. CX Codex +1 1,800installs idea-generation A skill that generates research ideas, refines them over several rounds and checks novelty against the literature. Useful before you commit to a paper topic. CX Codex +1 1,800installs rebuttal-writing Turns reviewer comments on a paper into a structured, point-by-point rebuttal backed by evidence from the manuscript. CX Codex +1 1,700installs code-debugging Structured error analysis for ML experiments and research code. It categorizes tracebacks, limits retry cycles, and explains fixes line by line. CX Codex +1 1,700installs experiment-code Writes and iterates on ML experiment code for a research paper: training, evaluation, debugging, plots. Useful when you need a batch of runs and a comparison. CX Codex +1 1,600installs paper-to-code Turns an ML research paper into a runnable code repository. Useful when reproducing published experiments and models without manual scaffolding. CX Codex +1 1,600installs atomic-decomposition Splits a research idea into atomic concepts, then finds the math formula in papers and the matching code for each one. CX Codex +1 1,600installs paper-compilation Compiles a LaTeX paper to PDF, catches build errors and checks citations and references. Useful when pdflatex throws errors and the log is a mess. CX Codex +1 1,600installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor