advaitpaliwal/feynman

1

deep-research Run a thorough, source-heavy investigation on any topic. Use when the user asks for deep research, a comprehensive an…

advaitpaliwal/feynman

162

2

paper-writing Turn research findings into a polished paper-style draft with sections, equations, and citations. Use when the user a…

advaitpaliwal/feynman

154

3

literature-review Run a literature review using paper search and primary-source synthesis. Use when the user asks for a lit review, pap…

advaitpaliwal/feynman

130

4

eli5 Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear take…

advaitpaliwal/feynman

129

5

alpha-research Search, read, and query research papers via Feynman's alphaXiv-backed alpha tools. Use when the user asks about acade…

advaitpaliwal/feynman

117

6

autoresearch Bounded research experiment loop that tries hypotheses, measures benchmark evidence, keeps what works, and records wh…

advaitpaliwal/feynman

106

7

paper-code-audit Compare a paper's claims against its public codebase. Use when the user asks to audit a paper, check code-claim consi…

advaitpaliwal/feynman

106

8

jobs Inspect visible research run state, scheduled research follow-ups when available, and durable watch artifacts. Use wh…

advaitpaliwal/feynman

104

9

replication Plan a replication of a paper, claim, or benchmark, and execute only after an explicit environment choice. Use when t…

advaitpaliwal/feynman

104

10

source-comparison Compare multiple sources on a topic and produce a grounded comparison matrix. Use when the user asks to compare paper…

advaitpaliwal/feynman

102

11

preview Preview Markdown, LaTeX, PDF, or code artifacts when preview commands are visible, or fall back to shell/browser tool…

advaitpaliwal/feynman

101

12

watch Create a research watch baseline and optionally schedule follow-up checks when scheduling tools are visible. Use when…

advaitpaliwal/feynman

100

13

session-search Recover prior Feynman work from session transcripts. Use the optional /search command only when it is installed and v…

advaitpaliwal/feynman

97

14

docker Execute research code inside isolated Docker containers for safe replication, experiments, and benchmarks. Use when t…

advaitpaliwal/feynman

96

15

session-log Write a durable session log capturing completed work, findings, open questions, and next steps. Use when the user ask…

advaitpaliwal/feynman

96

16

modal-compute Run explicitly chosen research benchmark or replication jobs on Modal's serverless infrastructure. Use when a Feynman…

advaitpaliwal/feynman

93

17

runpod-compute Provision and manage GPU pods on RunPod for explicitly chosen long-running research experiments. Use when a Feynman r…

advaitpaliwal/feynman

93

18

contributing Contribute changes to the Feynman repository itself. Use when the task is to add features, fix bugs, update prompts o…

advaitpaliwal/feynman

88

19

ml-training-recipe Find implementable ML training recipes from papers, datasets, docs, and code. Use when the user wants to fine-tune, t…

advaitpaliwal/feynman

79

20

peer-review Simulate a tough but constructive peer review of an AI research artifact. Use when the user asks for a review, critiq…

advaitpaliwal/feynman

70

21

research-review Run a tough but constructive internal research critique of an AI research artifact. Use when the user asks for a revi…

advaitpaliwal/feynman

38

22

figure-style Apply scientific plotting and figure-quality rules to a single plot or panel. Use when drawing, cleaning, labeling, o…

advaitpaliwal/feynman

30

23

paper-narrative Shape the scientific story across a manuscript, abstract, figures, and evidence. Use when a task asks for paper struc…

advaitpaliwal/feynman

28

24

figure-composer Compose a publication-grade multi-panel scientific figure from a claim, dataset, or draft result. Use when the task n…

advaitpaliwal/feynman

27

25

self-awareness Inspect the active Feynman workbench session, artifacts, execution log, settings, and provenance. Use when the task a…

advaitpaliwal/feynman

27

26

borzoi Use Borzoi-style regulatory genomics models for sequence-to-expression or variant-effect analysis. Use when the task …

advaitpaliwal/feynman

26

27

customize Configure Feynman specialists, skills, connectors, permissions, memory categories, compute providers, and project set…

advaitpaliwal/feynman

26

28

evo2 Use Evo2-style biological sequence models for generation, scoring, or variant-effect analysis. Use when a task asks a…

advaitpaliwal/feynman

26

29

fair-esm2 Use ESM2 protein language models for embeddings, mutation scoring, remote homology, or representation analysis. Use w…

advaitpaliwal/feynman

26

30

scgpt Use scGPT-style single-cell foundation model workflows. Use when a task asks for single-cell embeddings, perturbation…

advaitpaliwal/feynman

26

31

alphafold2 Predict or audit protein structures with AlphaFold2-style workflows. Use when a research task needs monomer/multimer …

advaitpaliwal/feynman

25

32

boltz Run or plan Boltz biomolecular structure predictions for proteins, complexes, ligands, or nucleic-acid assemblies. Us…

advaitpaliwal/feynman

25

33

chai1 Run or prepare Chai-1 structure predictions for biomolecular complexes. Use when a task asks for Chai-1 inputs, multi…

advaitpaliwal/feynman

25

34

compute-env-setup Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU lib…

advaitpaliwal/feynman

25

35

diffdock Run or plan DiffDock molecular docking workflows. Use when a task asks for protein-ligand pose prediction, docking se…

advaitpaliwal/feynman

25

36

esmfold2 Predict quick protein structures with ESMFold-style workflows. Use when a task needs fast MSA-free folding, sequence …

advaitpaliwal/feynman

25

37

indication-dossier Build a source-backed biomedical indication dossier. Use when a research task asks for disease biology, target ration…

advaitpaliwal/feynman

25

38

ligandmpnn Design protein sequences around ligand or small-molecule contexts with LigandMPNN-style workflows. Use when a task as…

advaitpaliwal/feynman

25

39

managed-model-endpoints Register or audit Feynman-managed model endpoints. Use when a research workflow needs a local or remote model service…

advaitpaliwal/feynman

25

40

openfold3 Run or plan OpenFold3-style structure prediction workflows. Use when a task asks for open protein or complex predicti…

advaitpaliwal/feynman

25

41

pdf-explore Read, extract, and cross-check content across scientific PDFs. Use when a task needs methods, figures, tables, citati…

advaitpaliwal/feynman

25

42

product-self-knowledge Answer questions about Feynman's own product behavior, runtime, settings, commands, skills, connectors, and package s…

advaitpaliwal/feynman

25

43

proteinmpnn Design protein sequences from fixed backbone structures with ProteinMPNN-style workflows. Use when a task asks for ba…

advaitpaliwal/feynman

25

44

remote-compute-modal Dispatch Feynman research notebook or experiment jobs to Modal. Use when a task has explicitly chosen Modal for bound…

advaitpaliwal/feynman

25

45

remote-compute-ssh Run Feynman research jobs on SSH, Slurm, or lab hosts. Use when a task needs remote host setup, job submission, log h…

advaitpaliwal/feynman

25

46

scvi-tools Run scvi-tools single-cell workflows. Use when a task asks for scVI/scANVI setup, latent embeddings, batch correction…

advaitpaliwal/feynman

25

47

skill-creator Create or revise Feynman skills. Use when a research workflow needs a reusable on-demand capability, skill metadata, …

advaitpaliwal/feynman

25

48

solublempnn Design or screen protein sequences for solubility-aware constraints with SolubleMPNN-style workflows. Use when a task…

advaitpaliwal/feynman

25

49

using-model-endpoint Call a configured Feynman model endpoint and interpret its response. Use when a task needs inference from a registere…

advaitpaliwal/feynman

25