Approximate deep learning model components with symbolic equations using PySR
$ npx skills add lamm-mit/scienceclaw --skill symtorch -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install lamm-mit/scienceclaw symtorch --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/lamm-mit/scienceclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/symtorch .claude/skills/symtorch && 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 "symtorch" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/symtorch into .claude/skills/symtorch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "symtorch", 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/lamm-mit/scienceclaw/tree/main/skills/symtorchType 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 lamm-mit/scienceclaw --skill symtorch -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install lamm-mit/scienceclaw symtorch --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/symtorch .agents/skills/symtorch && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "symtorch" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/symtorch into .agents/skills/symtorch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "symtorch", 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 lamm-mit/scienceclaw --skill symtorch -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install lamm-mit/scienceclaw symtorch --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/symtorch .cursor/skills/symtorch && 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 "symtorch" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/symtorch into .cursor/skills/symtorch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "symtorch", 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/lamm-mit/scienceclaw.git --path skills/symtorch--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 lamm-mit/scienceclaw --skill symtorch -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install lamm-mit/scienceclaw symtorch --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/symtorch .gemini/skills/symtorch && 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 "symtorch" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/symtorch into .gemini/skills/symtorch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "symtorch", 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 lamm-mit/scienceclaw symtorchInstalls 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 lamm-mit/scienceclaw --skill symtorch -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/symtorch .github/skills/symtorch && 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 "symtorch" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/symtorch into .github/skills/symtorch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "symtorch", 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 lamm-mit/scienceclaw --skill symtorch -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install lamm-mit/scienceclaw symtorch --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/symtorch .opencode/skills/symtorch && 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 "symtorch" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/symtorch into .opencode/skills/symtorch/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "symtorch", 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.
symtorchApproximate deep learning model components with symbolic equations using PySR
Symtorch is an agent skill from lamm-mit/scienceclaw. Approximate deep learning model components with symbolic equations using PySR
Its SKILL.md is about 620 tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including scripts (for example `scripts/USAGE.md` and `scripts/symtorch_client.py`).
It sits in AI & LLM Engineering, covering Deep learning. It works with arXiv. The licence is Apache-2.0.
Read from SKILL.md and the folder at commit ab9aba1. It shows what the files ask for, not the result of running them.
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.
Ships 2 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
gitpippython3From the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
github.comarxiv.orgsymtorch.readthedocs.ioastroautomata.github.ioFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Symtorch loads about 624 tokens when it runs. Until then it costs about 22 tokens; SKILL.md has 269 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.
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); the scripts in this folder are not scanned.
The full file from lamm-mit/scienceclaw at commit ab9aba1, republished under its Apache-2.0 licence (© lamm-mit). 269 words, ~624 tokens.
.claude/skills/symtorch/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.Approximate deep learning model components with symbolic equations using PySR
https://github.com/elizabethsztan/InterpretSR
Use this as the implementation source: clone the repo and follow its README for install, dependencies, and how to run code or experiments. The generated client prints JSON with a suggested git clone command.
https://arxiv.org/abs/2602.21307
This is the paper reference. The client can optionally fetch live Atom metadata (title, abstract) for agents; it does not run training or upstream research code by itself.
The *_client.py script prints JSON that combines a GitHub repository (clone URL + suggested git clone) with optional paper context from arXiv (live Atom metadata when reference_url is arXiv). Run the real code by cloning the repo and following its README — the skill is your agent-facing entrypoint, not a substitute for the repo’s install steps.
To call a REST API instead, set BASE_URL in scripts/symtorch_client.py or wrap the upstream CLI with subprocess after clone.
Extracted for operators and agents. Confirm against the upstream repository or paper before relying on it in production.
Install SymTorch from PyPI:
pip install torch-symbolicThe README does not document specific CLI commands or entrypoints. Refer to the official documentation at ReadTheDocs for usage examples and API reference.
No environment variables or configuration files are documented in the README. See the accompanying website and full documentation for configuration details.
The same text lives in scripts/USAGE.md for tools that prefer reading files under scripts/.
python3 scripts/symtorch_client.py NoneNone© lamm-mit, 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
SKILL.md and 2 other files (scripts) in skills/symtorch of lamm-mit/scienceclaw.
Open the folder on GitHubat commit ab9aba1
Symtorch 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 |
|---|---|---|---|---|---|---|
| Symtorch this skilllamm-mit/scienceclaw | 244 | — | ~624 | Automated safety check: Pass | Apache-2.0 | |
| Sparse Autoencoder Training with SAELensOrchestra-Research/AI-Research-SKILLs | 13k | 6 repos | ~3.2k | Automated safety check: Pass | MIT | |
| TransformerLens InterpretabilityOrchestra-Research/AI-Research-SKILLs | 13k | 4 repos | ~3k | Automated safety check: Pass | MIT | |
| Alphagenome Predictionsgenomicsxai/alphagenome-pytorch | 162 | — | ~868 | Automated safety check: Pass | Apache-2.0 | |
| pyvene Causal InterventionsOrchestra-Research/AI-Research-SKILLs | 13k | 3 repos | ~3.5k | Automated safety check: Pass | MIT | |
| ML Training RecipesOrchestra-Research/AI-Research-SKILLs | 13k | 2 repos | ~2.8k | Automated safety check: Pass | MIT |
Orchestra-Research/AI-Research-SKILLs
Guides training and analyzing sparse autoencoders with SAELens to break neural network activations into interpretable features, including superposition and monosemanticity studies.
Orchestra-Research/AI-Research-SKILLs
Guides mechanistic interpretability work with TransformerLens: loading models, caching activations, using HookPoints, activation patching and attention-pattern analysis.
genomicsxai/alphagenome-pytorch
Run AlphaGenome-PyTorch to get genomic track predictions — via the agt predict CLI (single locus, BED regions, whole chromosomes, raw FASTA sequences, or per-gene count tables/AnnData), variant…
Orchestra-Research/AI-Research-SKILLs
Guides causal experiments on PyTorch models with pyvene, such as causal tracing, activation patching and interchange intervention training, to test how a model works.
Orchestra-Research/AI-Research-SKILLs
PyTorch training reference: architecture choice by data type, scaling rules, a training loop, optimizer and learning-rate choices, and fixes for loss spikes or OOM.
Orchestra-Research/AI-Research-SKILLs
Sets up and runs NVIDIA Cosmos Policy evaluations on the LIBERO and RoboCasa simulators, including headless GPU rendering and inference latency profiling.
lamm-mit/scienceclaw
Query FRED (Federal Reserve Economic Data) API for 800,000+ economic time series from 100+ sources.
lamm-mit/scienceclaw
Generates comprehensive drug research reports with compound disambiguation, evidence grading, and mandatory completeness sections.
lamm-mit/scienceclaw
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index.
lamm-mit/scienceclaw
Cloud-based quantum chemistry platform with Python API. An agent skill from lamm-mit/scienceclaw.
lamm-mit/scienceclaw
Create professional infographics using Nano Banana Pro AI with smart iterative refinement.
lamm-mit/scienceclaw
Generate comprehensive disease research reports using 100+ ToolUniverse tools.
Works with
Categories
Approximate deep learning model components with symbolic equations using PySR. Symtorch is an agent skill from lamm-mit/scienceclaw.
Symtorch fits situations like: tasks that involve Deep learning.
Run `npx skills add lamm-mit/scienceclaw --skill symtorch -a claude-code`. Or copy the skill folder (skills/symtorch in lamm-mit/scienceclaw) into .claude/skills/symtorch in your project. Claude Code loads it when a task matches its description.
Run `npx skills add lamm-mit/scienceclaw --skill symtorch -a codex`. Or copy the skill folder (skills/symtorch in lamm-mit/scienceclaw) into .agents/skills/symtorch in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lamm-mit/scienceclaw --skill symtorch -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/symtorch, .gemini/skills/symtorch, .github/skills/symtorch and .opencode/skills/symtorch in your project.
Going by SKILL.md and its folder, Symtorch needs Python for the scripts in its folder and the command-line tools its instructions call (git, pip and python3). Our summary lists: Python 3.
SKILL.md names 4 domains. As links in the text: github.com, arxiv.org, symtorch.readthedocs.io and astroautomata.github.io. This is read from the text; nothing was executed.
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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Symtorch 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.
About 624 tokens (SKILL.md is roughly 2.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Symtorch: Sparse Autoencoder Training with SAELens (Orchestra-Research/AI-Research-SKILLs, 13k stars), TransformerLens Interpretability (Orchestra-Research/AI-Research-SKILLs, 13k stars), Alphagenome Predictions (genomicsxai/alphagenome-pytorch, 162 stars) and pyvene Causal Interventions (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
lamm-mit (a GitHub user) maintains it in lamm-mit/scienceclaw, which has 244 GitHub stars. The repository holds 85 skills in this directory. The repository was last updated on August 21, 2026.
Source: lamm-mit/scienceclaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
