researcher
01Agent
Gather primary evidence across papers, web sources, repos, docs, and local artifacts.
8.6k 5d ago A 20 tokens
original MIT
reviewer
02Agent
Run tough but constructive internal research critique of an AI research artifact.
8.6k 5d ago A 16 tokens
original MIT
verifier
03Agent
Post-process a draft to add inline citations and verify every source URL.
8.6k 5d ago A 17 tokens
original MIT
writer
04Agent
Turn research notes into clear, structured briefs and drafts.
8.6k 5d ago A 13 tokens
original MIT
Instructions file CodexOpenCode
Instructions for companion-inc/feynman, covering agents, pi subagents, what belongs here, feature scope and pi runtime changes.
8.6k 5d ago A 1,610 tokens
original MIT
Instructions file
Instructions for companion-inc/feynman.
8.6k 5d ago A 3 tokens
copy · 100% MIT
Skill Claude CodeCodex
Search, read, and query research papers via Feynman's alphaXiv-backed alpha tools. Use when the user asks about academic papers, wants to find research on a topic, needs to read a specific paper, ask questions about a paper, inspect a paper's code repository, or manage paper annotations.
8.6k 5d ago A 65 tokens
original MIT
alphafold2
08Skill Claude CodeCodex
Predict or audit protein structures with AlphaFold2-style workflows. Use when a research task needs monomer/multimer structure prediction, MSA/template handling, confidence metrics, or comparison against PDB/AlphaFold references.
8.6k 5d ago A 49 tokens
original MIT
autoresearch
09Skill Claude CodeCodex
Bounded research experiment loop that tries hypotheses, measures benchmark evidence, keeps what works, and records what fails. Use when the user asks to optimize a research metric, run an experiment loop, improve model/retrieval/evaluation performance iteratively, or benchmark a research hypothesis.
8.6k 5d ago A 58 tokens
original MIT
boltz
10Skill Claude CodeCodex
Run or plan Boltz biomolecular structure predictions for proteins, complexes, ligands, or nucleic-acid assemblies. Use when a task asks for Boltz setup, inputs, outputs, confidence interpretation, or reproduction.
8.6k 5d ago A 47 tokens
original MIT
borzoi
11Skill Claude CodeCodex
Use Borzoi-style regulatory genomics models for sequence-to-expression or variant-effect analysis. Use when the task asks for noncoding variant impact, regulatory sequence design, or expression prediction.
8.6k 5d ago A 41 tokens
original MIT
chai1
12Skill Claude CodeCodex
Run or prepare Chai-1 structure predictions for biomolecular complexes. Use when a task asks for Chai-1 inputs, multimers, ligand/nucleic acid structure prediction, or confidence review.
8.6k 5d ago A 44 tokens
original MIT
Skill Claude CodeCodex
Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.
8.6k 5d ago A 45 tokens
original MIT
contributing
14Skill Claude CodeCodex
Contribute changes to the Feynman repository itself. Use when the task is to add features, fix bugs, update prompts or skills, change install or release behavior, improve docs, or prepare a focused PR against this repo.
8.6k 5d ago A 49 tokens
original MIT
customize
15Skill Claude CodeCodex
Configure Feynman specialists, skills, connectors, permissions, memory categories, compute providers, and project setup. Use when the task asks to customize the research workbench or create a reusable Feynman research capability.
8.6k 5d ago A 46 tokens
original MIT
Skill Claude CodeCodex
Run a thorough, source-heavy investigation on any topic. Use when the user asks for deep research, a comprehensive analysis, an in-depth report, or a multi-source investigation. Produces a cited research brief with provenance tracking.
8.6k 5d ago A 49 tokens
original MIT
diffdock
17Skill Claude CodeCodex
Run or plan DiffDock molecular docking workflows. Use when a task asks for protein-ligand pose prediction, docking setup, ligand/protein preparation, pose ranking, or docking-result verification.
8.6k 5d ago A 41 tokens
original MIT
docker
18Skill Claude CodeCodex
Execute research code inside isolated Docker containers for safe replication, experiments, and benchmarks. Use when the user selects Docker as the execution environment or asks to run code safely, in isolation, or in a sandbox.
8.6k 5d ago A 43 tokens
original MIT
eli5
19Skill Claude CodeCodex
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
8.6k 5d ago A 63 tokens
original MIT
esmfold2
20Skill Claude CodeCodex
Predict quick protein structures with ESMFold-style workflows. Use when a task needs fast MSA-free folding, sequence triage, variant structure screening, or confidence review.
8.6k 5d ago A 38 tokens
original MIT
evo2
21Skill Claude CodeCodex
Use Evo2-style biological sequence models for generation, scoring, or variant-effect analysis. Use when a task asks about DNA/RNA/protein sequence likelihood, editing, design, or long-context biological modeling.
8.6k 5d ago A 45 tokens
original MIT
fair-esm2
22Skill Claude CodeCodex
Use ESM2 protein language models for embeddings, mutation scoring, remote homology, or representation analysis. Use when a task needs protein embeddings, zero-shot variant scores, clustering, or sequence-function triage.
8.6k 5d ago A 47 tokens
original MIT
Skill Claude CodeCodex
Compose a publication-grade multi-panel scientific figure from a claim, dataset, or draft result. Use when the task needs panel planning, consistent figure layout, figure review, or final figure assembly.
8.6k 5d ago A 42 tokens
original MIT
figure-style
24Skill Claude CodeCodex
Apply scientific plotting and figure-quality rules to a single plot or panel. Use when drawing, cleaning, labeling, or reviewing plots for research artifacts.
8.6k 5d ago A 32 tokens
original MIT