K-Dense-AI/scientific-agents

Expert-thinking AGENTS.md profiles that teach AI agents to reason like senior scientists and engineers.

168Stars on the repository
200Mods indexed here, across every type
20d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

bioinformatician

49

K-Dense-AI/scientific-agents

Plugin Claude Code

Bundles 1 agent · 74 tokens together

Reference-build discipline (GRCh38/GENCODE/Ensembl, MANE), batch-as-covariate DE (DESeq2/edgeR), index hopping/UDI, GATK/BQSR/PLINK GWAS multiplicity, nf-core reproducibility, and scRNA-seq ambient-RNA/doublet artifacts.

not rated 168 +6 20d ago A tokens not measured original MIT

K-Dense-AI/scientific-agents

Plugin Claude Code

Bundles 1 agent · 73 tokens together

Builds production genomics DAGs in Nextflow/nf-core, Snakemake, and WDL/Cromwell with digest-pinned containers, GIAB regression CI (nf-test, pytest), QC-gated MultiQC runbooks, and CLIA-grade provenance—distinct from analyst-focused bioinformatician DE/GWAS reasoning.

not rated 168 +6 20d ago A tokens not measured original MIT

K-Dense-AI/scientific-agents

Plugin Claude Code

Bundles 1 agent · 101 tokens together

Reasons from light-nutrient-grazing coupling, the microbial loop, and size-structured export through CTD/MOCNESS sampling, 14C and O2/Ar production with 234Th export flux, imaging and flow cytometry enumeration, and SILVA/PR2 metabarcoding while treating spatial patchiness, diel-migration tow aliasing, CDOM-biased…

not rated 168 +6 20d ago A tokens not measured original MIT

K-Dense-AI/scientific-agents

Plugin Claude Code

Bundles 1 agent · 84 tokens together

Reasons from material-biology interfaces, degradation-product toxicity, and mechanical mismatch to host tissue through ISO 10993 biological evaluation plans, ISO 10993-12 extract conditions, GPC/ICP/SEM characterization, and sterilization validation while treating endotoxin contamination, pH shift from acidic…

not rated 168 +6 20d ago A tokens not measured copy · 86% MIT

biomedical-engineer

53

K-Dense-AI/scientific-agents

Plugin Claude Code

Bundles 1 agent · 74 tokens together

Reasons from ISO 14971 risk management, ISO 10993 biocompatibility matrices, ASTM F/ISO 14242 mechanical and wear testing, and FDA 510(k) substantial equivalence; treats stress shielding, UHMWPE osteolysis, F2129 corrosion artifacts, and predicate/material mismatches as first-class failure modes.

not rated 168 +6 20d ago A tokens not measured original MIT

K-Dense-AI/scientific-agents

Plugin Claude Code

Bundles 1 agent · 85 tokens together

Reasons from contrast mechanisms, the resolution-SNR-scan-time triangle, and measurement reliability through DICOM/BIDS pipelines, QIBA profiles, phantom QC (ACR, NEMA IQ, Catphan), and blinded central reads (RECIST, RANO, PERCIST) while treating motion, partial volume effects, and cross-scanner harmonization drift as.

not rated 168 +6 20d ago A tokens not measured original MIT

biophysical-chemist

55

K-Dense-AI/scientific-agents

Plugin Claude Code

Bundles 1 agent · 88 tokens together

Reasons from free energy landscapes, binding equilibria (Kd, ΔG = ΔH − TΔS), and probe–system coupling through ITC, SPR/BLI, smFRET, AUC, and global fitting (KinTek, SEDFIT) while treating probe perturbation, mass-transport-limited kon, aggregation-driven avidity, and two-state melting violations as first-class failur.

not rated 168 +6 20d ago A tokens not measured original MIT

biophysicist

56

K-Dense-AI/scientific-agents

Plugin Claude Code

Bundles 1 agent · 90 tokens together

Reasons from energy landscapes, kT-scale thermodynamics, conformational ensembles, and the equilibrium-versus-kinetics distinction through smFRET, optical/magnetic tweezers, patch clamp, cryo-EM, and MD with force-field validation while treating photobleaching and blinking, FRET crosstalk, tether and series-resistance.

not rated 168 +6 20d ago A tokens not measured original MIT

bioprocess-engineer

57

K-Dense-AI/scientific-agents

Plugin Claude Code

Bundles 1 agent · 100 tokens together

Reasons from QTPP–CPP–CQA QbD, CHO fed-batch/perfusion scale-up (P/V, kLa, mixing), platform mAb DSP (Protein A, low-pH viral hold, IEX polish, UF/DF), tech transfer and PPQ lifecycle; treats transport-limited scale-up, harvest fouling, on-column aggregation, SUB leachables, and arbitrary three-batch PPQ as…

not rated 168 +6 20d ago A tokens not measured original MIT

K-Dense-AI/scientific-agents

Plugin Claude Code

Bundles 1 agent · 78 tokens together

Reasons from kLa/OTR–OUR balance, fed-batch μ control, off-gas RQ, van't Riet scale-up, and contamination (phage, bioburden, adventitious agents); treats antifoam kLa penalty, exponential-feed open-loop risk, and SUB vs stainless transfer as first-class failure modes.

not rated 168 +6 20d ago A tokens not measured original MIT

biostatistician

59

K-Dense-AI/scientific-agents

Plugin Claude Code

Bundles 1 agent · 68 tokens together

Reasons from estimands, SAPs, and error budgets; aligns ICH E9(R1), CONSORT/STROBE, multiplicity, MMRM, Cox survival, causal DAGs, and GWAS FDR while treating immortal time, ICEs, and batch confounding as first-class failure modes.

not rated 168 +6 20d ago A tokens not measured original MIT

K-Dense-AI/scientific-agents

Plugin Claude Code

Bundles 1 agent · 122 tokens together

Reasons from coupled heat and mass transfer, moisture sorption (EMC/ERH on D245.7 isotherms), respiration, and closed unit-operation balances through ASABE standards (S352.2 oven moisture, S448 Page thin-layer kinetics, D272.3 airflow resistance), psychrometric aeration analysis, and SuperPro/Aspen bioprocess…

not rated 168 +6 20d ago A tokens not measured original MIT

botanist

61

K-Dense-AI/scientific-agents

Plugin Claude Code

Bundles 1 agent · 121 tokens together

Reasons from morphology, floras (FNA/Jepson/eFlora), voucher herbarium specimens (Darwin Core, Index Herbariorum), nomenclature (IPNI/POWO/Madrid Code), APG IV phylogeny, DNA barcoding (rbcL/matK/ITS2), community ecology (vegan adonis2/betadisper, TRY traits), and CITES/ABS ethics; treats vegetative mis-ID…

not rated 168 +6 20d ago A tokens not measured original MIT

K-Dense-AI/scientific-agents

Plugin Claude Code

Bundles 1 agent · 82 tokens together

Reasons from modality–paradigm fit (EEG, ECoG, Utah arrays), CSP/Riemannian decoding (pyriemann, MOABB), BCI2000/OpenBCI pipelines, and charge-density stimulation safety; validates within- vs cross-session claims and treats muscle ICA, impedance drift, and IDE/IRB gates as first-class failure modes.

not rated 168 +6 20d ago A tokens not measured original MIT

bridge-engineer

63

K-Dense-AI/scientific-agents

Plugin Claude Code

Bundles 1 agent · 83 tokens together

Reasons from load paths, limit states, redundancy, and durability through AASHTO LRFD rating (LRFR/inventory vs. operating), FEM grillage and OpenSees models, HEC-18 scour analysis, and NDE such as half-cell potential and phased-array UT while treating fracture-critical fatigue details, lost composite action, scour…

not rated 168 +6 20d ago A tokens not measured original MIT

K-Dense-AI/scientific-agents

Plugin Claude Code

Bundles 1 agent · 66 tokens together

Reasons from coupled heat-air-moisture transport through ASHRAE 160 moisture-design analysis, WUFI transient simulation, ACH50 leakage mapping, and ISO 10211 psi-values while treating exfiltration condensation, reservoir claddings, and mold-index sensitivity as first-class failure modes.

not rated 168 +6 20d ago A tokens not measured original MIT

cancer-biologist

65

K-Dense-AI/scientific-agents

Plugin Claude Code

Bundles 1 agent · 64 tokens together

Reasons from hallmark capabilities, clonal evolution, and TME context; separates driver from passenger, cell-autonomous from stromal mechanisms, and 2D artifacts from PDO/PDX-validated dependencies using TCGA, DepMap, OncoKB, and REMARK-grade biomarker logic.

not rated 168 +6 20d ago A tokens not measured original MIT

K-Dense-AI/scientific-agents

Plugin Claude Code

Bundles 1 agent · 114 tokens together

Reasons from carbon mass balance across reservoirs and timescales, sign conventions, and budget closure through the Global Carbon Budget protocol, ONEFlux/REddyProc eddy-covariance processing, atmospheric inversions (CarbonTracker, CAMS, GEOS-Chem), Δ¹⁴C/δ¹³C isotopic partitioning, and ILAMB model evaluation while…

not rated 168 +6 20d ago A tokens not measured original MIT

cardiologist

67

K-Dense-AI/scientific-agents

Plugin Claude Code

Bundles 1 agent · 107 tokens together

Reasons from oxygen supply-demand mismatch, forward flow, filling pressures, and pre-test probability through 12-lead ECG, TTE/TEE with ASE grading, cath hemodynamics, CMR, and ACC/AHA/ESC guidelines with risk scores like HEART, GRACE, and CHA2DS2-VASc, while treating context-free troponin elevation, low-flow…

not rated 168 +6 20d ago A tokens not measured original MIT

catalysis-engineer

68

K-Dense-AI/scientific-agents

Plugin Claude Code

Bundles 1 agent · 87 tokens together

Reasons from catalyst lifecycle margin, space velocity (WHSV/GHSV/LHSV), and deactivation economics through plant historian trends, MAT/pilot trickle-bed activity tests, Aspen HYSYS activity factors, and ASTM crush/attrition plus TPO/ICP spent-catalyst profiling while treating coke, poisoning, sintering, attrition…

not rated 168 +6 20d ago A tokens not measured original MIT

catalysis-scientist

69

K-Dense-AI/scientific-agents

Plugin Claude Code

Bundles 1 agent · 112 tokens together

Reasons from active-site structure, turnover frequency, selectivity, and the Sabatier principle through CO/H2 chemisorption site-counting, Weisz-Prater and Mears transport checks, Langmuir-Hinshelwood/Mars-van Krevelen kinetics, and operando DRIFTS/XAS while treating diffusion-limited apparent rates, DRIFTS spectator…

not rated 168 +6 20d ago A tokens not measured original MIT

K-Dense-AI/scientific-agents

Plugin Claude Code

Bundles 1 agent · 106 tokens together

Reasons from structural causal models, potential outcomes, and identification logic through DAGs and do-calculus, doubly-robust estimators (AIPW/TMLE, IPTW, g-formula), and design-based methods (IV, RD, Callaway-Sant'Anna DiD, synthetic control) while treating colliders and M-bias, positivity/overlap failure, and…

not rated 168 +6 20d ago A tokens not measured original MIT

cell-biologist

71

K-Dense-AI/scientific-agents

Plugin Claude Code

Bundles 1 agent · 89 tokens together

Reasons from compartment thermodynamics, membrane electrophysics, and necessity-plus-sufficiency logic through STR authentication, confocal/TIRF imaging, CRISPR and siRNA perturbation with rescue, and Western blot, treating mycoplasma, passage and serum-lot drift, edge effects, antibody cross-reactivity, siRNA seed…

not rated 168 +6 20d ago A tokens not measured original MIT

K-Dense-AI/scientific-agents

Plugin Claude Code

Bundles 1 agent · 77 tokens together

Reasons from RTK–RAS–MAPK and PI3K–Akt–mTOR phosphorylation networks, pathway crosstalk and feedback; validates with phospho-Western, phospho-flow, and PhosphoSitePlus while treating serum-starvation artifacts, inhibitor off-targets, and RNA footprint vs PTM mismatch as first-class failure modes.

not rated 168 +6 20d ago A tokens not measured original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: