all publishers

K-Dense AI

@k-dense-ai source repo

865 published skills · page 1 of 9

  1. ▌
    Space Weather Scientist · k-dense-ai
    Think and work like an expert Space Weather Scientist. Use when a task calls for Space Weather Scientist judgment. Reasons from Dungey coupling and prolonged southward Bz through ICME vs. CIR/SIR drivers; uses OMNI/CDAWeb, L1 RTSW, WSA-Enlil, CCMC/CAMEL validation, SuperMAG SYM-H, GloTEC/IRI, and NOAA G/S/R scales while treating sheath-vs-cloud Bz, catalog false alarms, and Dst timing artifacts as first-class failure modes.
    57.3k repo stars
  2. ▌
    Thermodynamics Engineer · k-dense-ai
    Think and work like an expert Thermodynamics Engineer. Use when a task calls for Thermodynamics Engineer judgment. Reasons from energy conservation, entropy generation, state properties, and exergy quality through cycle modeling on T-s/h-s diagrams, IAPWS-IF97/REFPROP/CoolProp property models, LMTD/ε-NTU and pinch analysis, and ASME PTC/AHRI acceptance protocols, while treating efficiency-above-Carnot claims, pinch violations, compressor surge, and inconsistent HHV/LHV bases as first-class failure modes.
    57.3k repo stars
  3. ▌
    Transportation Engineer · k-dense-ai
    Think and work like an expert Transportation Engineer. Use when a task calls for Transportation Engineer judgment. Reasons from four-step and activity-based travel demand (CUBE/Visum/EMME), AASHTO Green Book geometry, HCM capacity, MPO LRTP and NEPA 23 CFR 771 project development, and multimodal corridor MOEs while treating unvalidated TDM forecasts and capacity-without-demand balance as first-class failure modes.
    57.3k repo stars
  4. ▌
    Turbomachinery Engineer · k-dense-ai
    Think and work like an expert Turbomachinery Engineer. Use when a task calls for Turbomachinery Engineer judgment. Reasons from Euler work transfer, velocity triangles, decomposed loss correlations, and map-based off-design margin through meanline-to-throughflow-to-RANS/URANS analysis, Campbell and unbalance rotordynamics, and ASME PTC 10/PTC 6 and API 617 testing while treating surge and rotating stall, clearance rubs and tip leakage, pump cavitation below NPSHr, and seal cross-coupling instability as first-class failure modes.
    57.3k repo stars
  5. ▌
    Viticulturist Enologist · k-dense-ai
    Think and work like an expert Viticulturist / Enologist. Use when a task calls for Viticulturist / Enologist judgment. Reasons from source–sink canopy balance, terroir as water/nitrogen-mediated ripening, sugar–acid–phenolic trajectories, glucophilic AF and Oenococcus MLF, molecular SO₂ at pH, FOSS/OIV analytics, ISO 4120/QDA sensory, and NDVI selective harvest while treating stuck ferment (YAN/fructose), smoke glycoside release, pH-blind SO₂, and mineral-terroir folklore as first-class failure modes.
    57.3k repo stars
  6. ▌
    Biological Oceanographer · k-dense-ai
    Think and work like an expert Biological Oceanographer. Use when a task calls for Biological Oceanographer judgment. 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 chlorophyll algorithms, and eDNA-detection-as-abundance as first-class failure modes.
    57.3k repo stars
  7. ▌
    Cell Signaling Biologist · k-dense-ai
    Think and work like an expert Cell Signaling Biologist. Use when a task calls for Cell Signaling Biologist judgment. 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.
    57.3k repo stars
  8. ▌
    Clinical Trial Scientist · k-dense-ai
    Think and work like an expert Clinical Trial Scientist. Use when a task calls for Clinical Trial Scientist judgment. Reasons from protocol SAPs, ICH-GCP, randomization/blinding, and CDISC SDTM while treating protocol deviations and immortal time as first-class failure modes.
    57.3k repo stars
  9. ▌
    Cognitive Neuroscientist · k-dense-ai
    Think and work like an expert Cognitive Neuroscientist. Use when a task calls for Cognitive Neuroscientist judgment. Reasons from latent constructs through converging behavior, fMRI/M/EEG, TMS, and lesion evidence; designs factorial and dissociation contrasts, fMRIPrep/GLMsingle/MNE pipelines, MVPA/RSA, and COBIDAS reporting while treating pure insertion, reverse inference, motion confounds, and in-sample decoding as first-class failure modes.
    57.3k repo stars
  10. ▌
    Comparative Physiologist · k-dense-ai
    Think and work like an expert Comparative Physiologist. Use when a task calls for Comparative Physiologist judgment. Reason from the Krogh principle and oxygen cascade through intermittent-flow respirometry, SMR/BMR/MMR scope, Q10 and heterothermy, hemoglobin P50, allometry and PGLS, while treating chamber drift, activity artifacts, phylogenetic pseudoreplication, and SMR definition mismatch as first-class failure modes.
    57.3k repo stars
  11. ▌
    Control Systems Engineer · k-dense-ai
    Think and work like an expert Control Systems Engineer. Use when a task calls for Control Systems Engineer judgment. Reasons from plant dynamics, stability margins, and disturbance-rejection specs through Bode/Nyquist and Routh-Hurwitz analysis, LQR/H-infinity and pole placement, Kalman/EKF observers, RGA pairing, and HIL validation while treating integrator windup, actuator saturation and backlash limit cycles, sensor delay masking phase margin, and estimator divergence as first-class failure modes.
    57.3k repo stars
  12. ▌
    Critical Care Researcher · k-dense-ai
    Think and work like an expert Critical Care Researcher. Use when a task calls for Critical Care Researcher judgment. Reasons from acute physiology trajectories, modular organ dysfunction, and cluster-aware trial design through APACHE/SAPS/SOFA scoring, Berlin/Sepsis-3/KDIGO definitions, MIMIC-IV phenotyping, and target-trial emulation with clone-censor-weighting while treating immortal-time bias, cluster contamination, competing risks from early death, and sepsis-phenotype cohort inflation as first-class failure modes.
    57.3k repo stars
  13. ▌
    Fire Protection Engineer · k-dense-ai
    Think and work like an expert Fire Protection Engineer. Use when a task calls for Fire Protection Engineer judgment. Reasons from NFPA 13 Hazen-Williams hydraulics (K-factor, remote area, hose stream) and NFPA 101 egress (occupant load, travel distance, capacity factors) through NFPA 92 smoke containment/management, ASET/RSET PBD, and FDS/CFAST/CONTAM/PyroSim modeling while treating breached compartmentation, C-factor/fitting errors, and supply-curve shortfall as first-class failure modes.
    57.3k repo stars
  14. ▌
    Flavor Fragrance Chemist · k-dense-ai
    Think and work like an expert Flavor & Fragrance Chemist. Use when a task calls for Flavor & Fragrance Chemist judgment. Reasons from odor activity values, threshold perception, matrix release, and degradation kinetics through GC-MS with retention indices, GC-O/AEDA, chiral GC authentication, ISO 8586 trained sensory panels, and IFRA/FEMA regulatory limits while treating aldehyde oxidation, citral cyclization, top-note fade, and allergen exceedance as first-class failure modes.
    57.3k repo stars
  15. ▌
    Fluid Mechanics Engineer · k-dense-ai
    Think and work like an expert Fluid Mechanics Engineer. Use when a task calls for Fluid Mechanics Engineer judgment. Reasons from Navier–Stokes reductions through Darcy–Weisbach/Crane TP-410 pipe networks, pump system curves, NPSH/affinity laws, HI turbomachinery selection, and ASME V&V 20 CFD validation when simulation supports design.
    57.3k repo stars
  16. ▌
    Geological Oceanographer · k-dense-ai
    Think and work like an expert Geological Oceanographer. Use when a task calls for Geological Oceanographer judgment. Reasons from sediment transport mechanics, stratigraphic context, and accommodation through multibeam (EM122/EM712) and sub-bottom/seismic imaging, gravity and piston cores with XRF/X-ray CT, CTD tow-yo ORP/Mn/CH4 plume surveys, and Bouma/Lowe facies analysis, while treating bathymetry-mimicking multipath artifacts, bioturbation homogenizing event beds, glacial isostasy mistaken for eustasy, and single-core turbidite extrapolation as first-class failure modes.
    57.3k repo stars
  17. ▌
    Global Health Researcher · k-dense-ai
    Think and work like an expert Global Health Researcher. Use when a task calls for Global Health Researcher judgment. Reasons from burden, equity, and health-system building blocks through DHS/MICS/DHIS2/GBD triangulation, cluster and stepped-wedge designs, RE-AIM/CFIR implementation science, and CIOMS-fair partnership while treating survey weights, HMIS completeness, and GBD smoothing as first-class failure modes.
    57.3k repo stars
  18. ▌
    Instrumentation Engineer · k-dense-ai
    Think and work like an expert Instrumentation Engineer. Use when a task calls for Instrumentation Engineer judgment. Reasons from the process variable, its transduction chain, 4-20 mA loop integrity, and traceable calibration through ISA-5.1 P&IDs, NAMUR NE43 fault bands, ISO 5167 orifice sizing, and GUM uncertainty budgets while treating plugged impulse lines, double-applied square-root, ground-loop noise, and unrevalidated SIS bypasses as first-class failure modes.
    57.3k repo stars
  19. ▌
    Molecular Neuroscientist · k-dense-ai
    Think and work like an expert Molecular Neuroscientist. Use when a task calls for Molecular Neuroscientist judgment. Reasons from NPQ transmission, AMPAR/NMDAR trafficking, monoamine receptor/transporter systems, optogenetics (ChR2/Chrimson/ACR) with retinal-artifact controls, AAV/rabies circuit tracing, and region RNA-seq with DESeq2/SynGO—integrating synaptic biochemistry, perturbation, and omics while treating mini-detection bias, TVA leak, and batch/composition confounds as first-class failure modes.
    57.3k repo stars
  20. ▌
    Natural Products Chemist · k-dense-ai
    Think and work like an expert Natural Products Chemist. Use when a task calls for Natural Products Chemist judgment. Reasons from dereplication (GNPS FBMN, NPAtlas, SNAP-MS, COCONUT), bioassay-guided and MS-triggered isolation, NMR/HRMS structure tiers (DP4+/DU8+), antiSMASH/MIBiG BGC linkage, and PAINS/IMP assay interference while treating HMBC ambiguity, stereochemical misassignment, and aggregator false positives as first-class failure modes.
    57.3k repo stars
  21. ▌
    Observational Astronomer · k-dense-ai
    Think and work like an expert Observational Astronomer. Use when a task calls for Observational Astronomer judgment. Reasons from the CCD signal-to-noise equation, sky- versus read-noise-limited scaling, airmass extinction and seeing laws, and a CALSPEC-anchored calibration chain through ETC-backed proposals, ccdproc/PypeIt/DRAGONS and CRDS-pinned JWST reductions, optimal extraction with telluric correction, Gaia-anchored astrometry, ZOGY difference imaging, and Rubin broker-to-TOM-to-TNS follow-up while treating IR persistence and reciprocity failure, fringing and shutter-timing errors, differential-refraction slit losses, difference-image dipoles, and red-noise-inflated light curves as first-class failure modes.
    57.3k repo stars
  22. ▌
    Optoelectronics Engineer · k-dense-ai
    Think and work like an expert Optoelectronics Engineer. Use when a task calls for Optoelectronics Engineer judgment. Reasons from photon–electron conversion, ABC recombination, and IQE/EQE/WPE budgets; runs LIV/pulsed laser, EMVA 1288, and responsivity metrology; designs with Lumerical/Sentaurus/COMSOL TCAD and foundry PDKs while treating efficiency droop, thermal rollover, LIV kinks, and calibration geometry as first-class failure modes.
    57.3k repo stars
  23. ▌
    Quantum Optics Scientist · k-dense-ai
    Think and work like an expert Quantum Optics Scientist. Use when a task calls for Quantum Optics Scientist judgment. Reasons from field quadratures, atom-photon coupling (g, κ, γ), and heralding efficiency budgets through g⁽²⁾ Hanbury Brown-Twiss measurement, balanced homodyne tomography, HOM interference, and SNSPD/APD detector calibration while treating afterpulsing-faked antibunching, LO phase drift erasing squeezing, accidentals and dark counts, and unaddressed Bell-test loopholes as first-class failure modes.
    57.3k repo stars
  24. ▌
    Rehabilitation Scientist · k-dense-ai
    Think and work like an expert Rehabilitation Scientist. Use when a task calls for Rehabilitation Scientist judgment. Reasons from ICF/disablement models, COSMIN MCID/MDC triangulation, TIDieR-Rehab/CONSORT 2025 trial design, gait lab and PROMIS outcomes, motor-learning mechanisms, and RE-AIM implementation science; treats natural recovery, therapist allegiance, and lab-vs-function confounds as first-class failure modes.
    57.3k repo stars
  25. ▌
    Remote Sensing Scientist · k-dense-ai
    Think and work like an expert Remote Sensing Scientist. Use when a task calls for Remote Sensing Scientist judgment. Reasons from sensor physics, atmospheric state, surface BRDF, and sampling geometry through Sen2Cor/LaSRC/6S atmospheric correction, sub-pixel coregistration, SAR radiometric terrain correction, and Olofsson area-adjusted accuracy while treating misregistration, NDVI saturation, BRDF anisotropy, mixed pixels, and spatial label leakage as first-class failure modes.
    57.3k repo stars
  26. ▌
    Soil Fertility Scientist · k-dense-ai
    Think and work like an expert Soil Fertility Scientist. Use when a task calls for Soil Fertility Scientist judgment. Reasons from plant-available nutrient supply, pH-governed availability, and CEC/base saturation through Mehlich-3 extraction, buffer-pH lime calculations with ECCE/ENM, 4R stewardship, and regional extension calibration while treating uncalibrated cross-extractant comparison, no-till stratification, environmental P/nitrate loss, and N mineralization-immobilization leakage as first-class failure modes.
    57.3k repo stars
  27. ▌
    Sustainability Scientist · k-dense-ai
    Think and work like an expert Sustainability Scientist. Use when a task calls for Sustainability Scientist judgment. Reasons from measurable capitals, planetary-boundary safe operating space, and absolute-versus-intensity impact through GHG Protocol Scope 1/2/3 accounting, GRI/ISSB/ESRS disclosure, MCI circularity and MFA, and IPCC SSP/IEA/NGFS scenario analysis, while treating greenwashing offsets without additionality or permanence, Scope 3 EEIO collapse, masked SDG trade-offs and leakage, and intensity gains hiding absolute growth as first-class failure modes.
    57.3k repo stars
  28. ▌
    Translational Researcher · k-dense-ai
    Think and work like an expert Translational Researcher. Use when a task calls for Translational Researcher judgment. Reasons from T0–T4 stage gates, murine vs NHP translatability, PK/PD allometric bridging, MRSD/MABEL FIH dose selection, BEST/CLIA/CAP biomarker tiers, and CONSORT/SPIRIT/STROBE reporting while treating target-wrong, model-wrong, non-predictive biomarker, and preclinical irreproducibility as first-class failure modes.
    57.3k repo stars
  29. ▌
    Water Resources Engineer · k-dense-ai
    Think and work like an expert Water Resources Engineer. Use when a task calls for Water Resources Engineer judgment. Watershed hydrology through HEC-HMS into HEC-RAS floodplain and stormwater BMP design — catchment balance, DSS coupling, FEMA products, and quantity/quality detention with defensible calibration.
    57.3k repo stars
  30. ▌
    Welding Joining Engineer · k-dense-ai
    Think and work like an expert Welding & Joining Engineer. Use when a task calls for Welding & Joining Engineer judgment. Reasons from heat input, t8/5, HAZ metallurgy, and restraint/shrinkage through AWS D1.1 prequalified vs qualified WPS, ASME IX/ISO 15614 PQR essential variables, RT/UT acceptance (static vs cyclic), FSW wormhole/kissing-bond windows, and neutron/XRD/hole-drilling residual stress while treating prequalification overreach, planar-UT mis-disposition, and cold-FSW root bonds as first-class failure modes.
    57.3k repo stars
  31. ▌
    Agricultural Entomologist · k-dense-ai
    Think and work like an expert Agricultural Entomologist. Use when a task calls for Agricultural Entomologist judgment. Reasons from pest population dynamics, economic injury levels and thresholds, and degree-day phenology through systematic scouting, IRAC mode-of-action rotation, RCBD efficacy trials, and conservation biocontrol while treating misidentification, secondary pest flares from enemy removal, resistance under repeated MoA, and trap-catch-without-field-verification as first-class failure modes.
    57.3k repo stars
  32. ▌
    Animal Geneticist Breeder · k-dense-ai
    Think and work like an expert Animal Geneticist & Breeder. Use when a task calls for Animal Geneticist & Breeder judgment. Reasons from additive genetic variance, response to selection (R = i h sigma_A), accuracy, and inbreeding depression through REML/BLUP and ssGBLUP pipelines (BLUPF90, ASReml, WOMBAT), economic selection indices, optimum-contribution mate allocation, and Interbull MACE while treating confounded contemporary groups, prediction bias/dispersion, popular-sire inbreeding and rising deleterious haplotypes, GxE reranking, and pedigree or genotype-calling errors as first-class failure modes.
    57.3k repo stars
  33. ▌
    Behavioral Neuroscientist · k-dense-ai
    Think and work like an expert Behavioral Neuroscientist. Use when a task calls for Behavioral Neuroscientist judgment. Reasons from contingency structure, deprivation state, and latent arousal/motivation variables through Morris water maze, contextual/cued fear conditioning, operant schedules on Med Associates rigs, and DeepLabCut/SLEAP/SimBA tracking validated against ethograms, while treating thigmotaxis-as-anxiety, locomotor confounds of memory deficits, peripheral CNO sedation, and trials-as-n pseudoreplication as first-class failure modes.
    57.3k repo stars
  34. ▌
    Bioprocess Microbiologist · k-dense-ai
    Think and work like an expert Bioprocess Microbiologist. Use when a task calls for Bioprocess Microbiologist judgment. 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.
    57.3k repo stars
  35. ▌
    Building Science Engineer · k-dense-ai
    Think and work like an expert Building Science Engineer. Use when a task calls for Building Science Engineer judgment. 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.
    57.3k repo stars
  36. ▌
    Computer Vision Scientist · k-dense-ai
    Think and work like an expert Computer Vision Scientist. Use when a task calls for Computer Vision Scientist judgment. Reasons from image formation, projective geometry (pinhole intrinsics and extrinsics, epipolar/PnP/bundle adjustment, similarity-scale ambiguity), and COCO/LVIS AP mechanics through DINOv3/SigLIP 2 foundation baselines, RF-DETR/YOLO26/SAM 3 models, COLMAP 4/GLOMAP and VGGT geometry, pycocotools/TrackEval/BOP evaluation, and CVPR reporting and EU AI Act limits while treating train–test and pretraining leakage, AP evaluation-setting gaming, preprocessing mismatches (EXIF, BGR, aliased resizing), label noise, and camera-convention and scale errors as first-class failure modes.
    57.3k repo stars
  37. ▌
    Crop Protection Scientist · k-dense-ai
    Think and work like an expert Crop Protection Scientist. Use when a task calls for Crop Protection Scientist judgment. Reasons from IPM, EIL/ET, and FRAC/HRAC/IRAC MoA rotation through GEP/EPPO efficacy trials, CDMS label law, BBCH timing, DRT application, PPDB/fate modeling, and MRL/GAP alignment while treating resistance, drift, herbicide carryover, and abiotic mimicry as first-class failure modes.
    57.3k repo stars
  38. ▌
    Crystal Growth Specialist · k-dense-ai
    Think and work like an expert Crystal Growth Specialist. Use when a task calls for Crystal Growth Specialist judgment. Reasons from thermodynamic driving force, interface stability, constitutional supercooling, and dopant segregation (keff vs. k0, G/R) through Cz/Bridgman/FZ/LEC/PVT growth, CGSim and phase-field simulation, XRT topography, etch-pit counting, and FTIR/SIMS mapping while treating striations, inclusions, crucible-reaction contamination, and cool-down slip and cracking as first-class failure modes.
    57.3k repo stars
  39. ▌
    Edge Embedded AI Engineer · k-dense-ai
    Think and work like an expert Edge / Embedded AI Engineer. Use when a task calls for Edge / Embedded AI Engineer judgment. Reasons from tensor-arena budgets, full-int8 PTQ with representative calibration, and TFLM/CMSIS-NN or Vela/Ethos-U compile paths through ONNX Runtime QNN HTP and mobile delegates—treating train–serve preprocessing skew, float thresholds on quantized outputs, and NPU operator fallback as first-class failure modes.
    57.3k repo stars
  40. ▌
    Electromagnetics Engineer · k-dense-ai
    Think and work like an expert Electromagnetics Engineer. Use when a task calls for Electromagnetics Engineer judgment. Reasons from Maxwell scaling and S-parameters through HFSS/CST/ADS workflows, SOLT/TRL calibration, mesh ΔS convergence, Smith-chart matching, anechoic OTA, and CISPR/FCC Part 15 / IEC-IEEE 62209-1528 SAR compliance while treating PML reflections, probe de-embedding, and chamber ripple as first-class failure modes.
    57.3k repo stars
  41. ▌
    Embedded Systems Engineer · k-dense-ai
    Think and work like an expert Embedded Systems Engineer. Use when a task calls for Embedded Systems Engineer judgment. Reasons from hardware timing, interrupt latency, memory maps, and deterministic WCET resource bounds through DWT CYCCNT and Saleae logic-analyzer timing proofs, SWD/JTAG (J-Link/OpenOCD) with CFSR/HFSR/BFAR fault decode, FreeRTOS/Zephyr respecting configMAX_SYSCALL_INTERRUPT_PRIORITY, MISRA C:2012 and ISO 26262 ASIL discipline, Nordic PPK2 power profiling, and MCUboot signed OTA while treating priority inversion, Cortex-M7 uncached-DMA D-cache incoherence, CAN bus-off, I2C NACK storms, and brownout-during-flash-write NVS corruption as first-class failure modes.
    57.3k repo stars
  42. ▌
    Formal Methods Researcher · k-dense-ai
    Think and work like an expert Formal Methods Researcher. Use when a task calls for Formal Methods Researcher judgment. Reasons from operational semantics and temporal logics through SPIN/TLA+/PRISM, Coq/Lean/Isabelle, Z3/CVC5, refinement and separation logic, vacuity and false-positive diagnosis, and Dafny/F* versus property-based testing boundaries.
    57.3k repo stars
  43. ▌
    Industrial Microbiologist · k-dense-ai
    Think and work like an expert Industrial Microbiologist. Use when a task calls for Industrial Microbiologist judgment. Reasons from SmF/SSF physiology, fed-batch μ/OTR–OUR/RQ, DoE media optimization, PAT (Raman soft sensors), ICH Q8/Q7 characterization, bioleaching, SVI/F/M filament ID, and phage (10⁴–10⁶ PFU/mL) plant hygiene; treats antifoam kLa penalty, F₀ CIP/SIP cold spots, DSP mass balance, and golden-batch vs biofilm red herrings as first-class failure modes.
    57.3k repo stars
  44. ▌
    Low Temperature Physicist · k-dense-ai
    Think and work like an expert Low-Temperature Physicist. Use when a task calls for Low-Temperature Physicist judgment. Reasons from kT budgets, He-3/He-4 dilution refrigeration, and BCS/GL superconductivity; measures Tc, QHE, and Landauer conductance with lock-in/SQUID workflows while treating wiring heat loads, Kapitza resistance, flux trapping, TLS dielectric loss, and sample-vs-MXC thermometer mismatch as first-class failure modes.
    57.3k repo stars
  45. ▌
    Machine Learning Engineer · k-dense-ai
    Think and work like an expert Machine Learning Engineer. Use when a task calls for Machine Learning Engineer judgment. Reasons from decision-policy framing, Google's Rules of ML, point-in-time data, and prefill/decode inference physics through GBDT/PyTorch baselines, vLLM/SGLang/KServe serving with FP8/AWQ quantization, hybrid-retrieval RAG, RAGAS and human-validated LLM judges, OpenTelemetry GenAI tracing, and post-Omnibus EU AI Act obligations while treating train-serve skew, temporal leakage, prompt injection, LLM nondeterminism, and degenerate feedback loops as first-class failure modes.
    57.3k repo stars
  46. ▌
    Mathematical Statistician · k-dense-ai
    Think and work like an expert Mathematical Statistician. Use when a task calls for Mathematical Statistician judgment. Reasons from LAN, empirical processes, and influence functions; proves M/Z-estimator limits, minimax rates (Fano/Le Cam/Assouad), and semiparametric efficiency while validating with ADEMP simulations and treating naive bootstrap, non-Donsker classes, and debiasing sparsity violations as first-class failure modes.
    57.3k repo stars
  47. ▌
    Microelectronics Engineer · k-dense-ai
    Think and work like an expert Microelectronics Engineer. Use when a task calls for Microelectronics Engineer judgment. Reasons from CTE mismatch, θja networks (JESD51), and package RLC through wire bond (Au–Al IMC, loop height), flip-chip (UBM, underfill, HIP/NWO), J-STD-020 MSL, and JESD22 TCT/uHAST; treats datasheet θja without board definition, wire sweep, die-attach voids, and soak-mode mismatch as first-class failure modes.
    57.3k repo stars
  48. ▌
    Veterinary Epidemiologist · k-dense-ai
    Think and work like an expert Veterinary Epidemiologist. Use when a task calls for Veterinary Epidemiologist judgment. Reasons from herd-level units, Rogan–Gladen prevalence, R₀/SIR transmission models, and WOAH freedom-from-disease surveillance through outbreak line lists, SaTScan clusters, cluster field trials (REFLECT), and STROBE-Vet/AHSURED reporting while treating pseudo-replication, test-biased apparent prevalence, reporting-intensity clusters, and mis-specified generation intervals as first-class failure modes.
    57.3k repo stars
  49. ▌
    Veterinary Microbiologist · k-dense-ai
    Think and work like an expert Veterinary Microbiologist. Use when a task calls for Veterinary Microbiologist judgment. Reasons from pre-analytic specimen quality, CLSI VET01 AST, MALDI-TOF/PCR/WGS, and ISCAID significance thresholds through ACVM/AAVLD/WOAH workflows, NARMS/Vet-LIRN AMR surveillance, and One Health zoonoses while treating wound-swab contaminants, PCR-without-viability, human breakpoints on veterinary isolates, DTM false positives, MRSP biofilm, and Brucella BSL-3 exposure as first-class failure modes.
    57.3k repo stars
  50. ▌
    Vlsi Chip Design Engineer · k-dense-ai
    Think and work like an expert VLSI / Chip Design Engineer. Use when a task calls for VLSI / Chip Design Engineer judgment. Reasons from PPA tradeoffs, timing slack, on-chip variation, and foundry rule decks through MCMM STA with OCV/POCV in PrimeTime/Tempus, UPF power intent, SpyGlass/JasperGold CDC, and Calibre DRC/LVS while treating clock-domain crossings, post-CTS hold violations, IR drop, and TT-only signoff as first-class failure modes.
    57.3k repo stars
  51. ▌
    Water Resources Scientist · k-dense-ai
    Think and work like an expert Water Resources Scientist. Use when a task calls for Water Resources Scientist judgment. Reasons from hydrologic-cycle mass and energy balance, green-versus-blue water, and nonstationarity through MODFLOW, SWAT/HEC-RAS, WEAP, Budyko closure, and multi-objective KGE/NSE calibration while treating equifinality, unaccounted return flows and stream depletion, single-drought-year safe yield, and efficiency-rebound effects as first-class failure modes.
    57.3k repo stars
  52. ▌
    Causal Inference Scientist · k-dense-ai
    Think and work like an expert Causal Inference Scientist. Use when a task calls for Causal Inference Scientist judgment. 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 unmeasured confounding (Rosenbaum bounds, E-values) as first-class failure modes.
    57.3k repo stars
  53. ▌
    Computer Hardware Engineer · k-dense-ai
    Think and work like an expert Computer Hardware Engineer. Use when a task calls for Computer Hardware Engineer judgment. Reasons from CPI/AMAT and MESI/MOESI coherence through SystemVerilog RTL, PrimeTime/Design Compiler/Innovus signoff, PCIe LTSSM/TLP, SVA formal, and clock-gating power while treating CDC metastability, false-path abuse, X-optimism, and coherency traffic as first-class failure modes.
    57.3k repo stars
  54. ▌
    Condensed Matter Physicist · k-dense-ai
    Think and work like an expert Condensed Matter Physicist. Use when a task calls for Condensed Matter Physicist judgment. Reasons from Bloch bands, quasiparticles, and symmetry through ARPES/STM/neutron/transport workflows, VASP/QE/Wannier90/DMFT, and Materials Project/ICSD/MPDS while treating matrix-element artifacts, Mott vs. DFT gaps, pseudogap vs. SC gap, and Planckian bad-metal transport as first-class failure modes.
    57.3k repo stars
  55. ▌
    Developmental Psychologist · k-dense-ai
    Think and work like an expert Developmental Psychologist. Use when a task calls for Developmental Psychologist judgment. Reasons from developmental trajectories, measurement invariance, and familial-environmental context through age-normed instruments (Bayley, WPPSI/WISC, CBCL, MacArthur-Bates CDI), false-belief and violation-of-expectation paradigms, and lme4/lavaan growth models while treating verbal-demand confounding of theory of mind, informative attrition, adult-normed task misapplication, and parent-versus-direct-assessment divergence as first-class failure modes.
    57.3k repo stars
  56. ▌
    Dynamical Systems Theorist · k-dense-ai
    Think and work like an expert Dynamical Systems Theorist. Use when a task calls for Dynamical Systems Theorist judgment. Reasons from state spaces, invariant sets, bifurcations, and multiple time scales through normal-form classification, center-manifold reduction, Floquet/Poincaré maps, and continuation tools like AUTO, MatCont, and DynamicalSystems.jl while treating spurious chaos from finite-time Lyapunov bias, false limit cycles mistaken for tori, numerical blow-up versus true singularity, and Takens embedding artifacts as first-class failure modes.
    57.3k repo stars
  57. ▌
    Electric Machines Engineer · k-dense-ai
    Think and work like an expert Electric Machines Engineer. Use when a task calls for Electric Machines Engineer judgment. Reasons from magnetic circuit design, dq-frame machine models, FEM flux paths, and drive efficiency maps while treating saturation, cogging, thermal derating, and inverter harmonics as first-class failure modes.
    57.3k repo stars
  58. ▌
    High Energy Astrophysicist · k-dense-ai
    Think and work like an expert High-Energy Astrophysicist. Use when a task calls for High-Energy Astrophysicist judgment. Reasons from Compton/synchrotron radiative processes and compact-object energetics through HEASARC/Fermi/Swift/XMM/Chandra/NuSTAR/XRISM pipelines, XSPEC/Sherpa spectral fitting, pile-up and background systematics, blazar/GRB/TDE campaigns, and GCN multi-messenger coordination while treating RMF versioning, soft-proton flares, and look-elsewhere significance as first-class failure modes.
    57.3k repo stars
  59. ▌
    Mechanical Design Engineer · k-dense-ai
    Think and work like an expert Mechanical Design Engineer. Use when a task calls for Mechanical Design Engineer judgment. Reasons from function, datum reference frames, and tolerance budgets; releases inspectable drawings and MBD through ASME Y14.5 GD&T, WC/RSS/Monte Carlo stack-ups, SAE J1739 DFMEA (Action Priority), and Boothroyd–Dewhurst DFM/DFA—not stress plots alone.
    57.3k repo stars
  60. ▌
    Nuclear Medicine Scientist · k-dense-ai
    Think and work like an expert Nuclear Medicine Scientist. Use when a task calls for Nuclear Medicine Scientist judgment. Reasons from radioactive decay, biodistribution kinetics, and detector physics through HPLC/TLC radiochemical-purity QC, dose-calibrator cross-calibration, OSEM/PSF reconstruction, and MIRD/OLINDA dosimetry while treating partial-volume effects, attenuation mismatch, 68Ge breakthrough and other radionuclidic impurity, and unharmonized cross-center SUV as first-class failure modes.
    57.3k repo stars
  61. ▌
    Palliative Care Researcher · k-dense-ai
    Think and work like an expert Palliative Care Researcher. Use when a task calls for Palliative Care Researcher judgment. Reasons from serious-illness trajectories, multidimensional symptom burden, goals-of-care concordance, and caregiver dyad outcomes through validated PROMs (ESAS-r, IPOS, FACIT-Pal), prespecified MCID responder analysis, mixed-effects and joint survival-QoL models, and CONSORT-PRO/SPIRIT/PCORI reporting while treating death-related attrition, unjustified proxy substitution, inconsistent palliative-care exposure definitions, and hospice-versus-consult conflation as first-class failure modes.
    57.3k repo stars
  62. ▌
    Pollution Control Engineer · k-dense-ai
    Think and work like an expert Pollution Control Engineer. Use when a task calls for Pollution Control Engineer judgment. Reasons from PTE, Title V Part 70, and NPDES limits through scrubber/baghouse/ESP/RTO selection, CEMS and stack-test demonstration, and parametric O&M (ΔP, pH, L/G) while treating synthetic-minor strategy, sulfite-blinded FGD, bag leaks, and WET/TIE toxicity as first-class failure modes.
    57.3k repo stars
  63. ▌
    Power Electronics Engineer · k-dense-ai
    Think and work like an expert Power Electronics Engineer. Use when a task calls for Power Electronics Engineer judgment. Reasons from volt-second and charge balance, switched-mode energy transfer, and small-signal loop gain through PLECS/LTspice/SIMPLIS simulation, Steinmetz and Dowell magnetics loss accounting, Bode injection on hardware, and LISN-based EMI scans while treating shoot-through, RHP-zero subharmonic oscillation, Qrr and ZVS-window loss, and CM-choke saturation as first-class failure modes.
    57.3k repo stars
  64. ▌
    Quality Six Sigma Engineer · k-dense-ai
    Think and work like an expert Quality / Six Sigma Engineer. Use when a task calls for Quality / Six Sigma Engineer judgment. Reasons from process variation, defect operational definitions, and customer-critical characteristics through Shewhart control charts, Gage R&R (%GRR, ndc), Cp/Cpk and Pp/Ppk capability, DMAIC tollgates, and AIAG PPAP/PFMEA in Minitab or JMP while treating Cpk on unstable processes, attribute data forced as normal, gauge spread consuming tolerance, and unverified projected savings as first-class failure modes.
    57.3k repo stars
  65. ▌
    Renewable Energy Scientist · k-dense-ai
    Think and work like an expert Renewable Energy Scientist. Use when a task calls for Renewable Energy Scientist judgment. Reasons from resource-to-energy conversion, P50/P90 yield risk, LCOE/LCA boundaries, IEC monitoring, and grid constraints while troubleshooting PV soiling/PID/clipping, wind wakes/icing/yaw, hydro drought, geothermal scaling, and biomass feedstock variability.
    57.3k repo stars
  66. ▌
    Research Software Engineer · k-dense-ai
    Think and work like an expert Research Software Engineer. Use when a task calls for Research Software Engineer judgment. Reasons from Software Carpentry and FAIR4RS through SemVer releases, CITATION.cff/SPDX metadata, pytest/Hypothesis CI gates, Docker/Apptainer on Slurm, and maintainability discipline for citable, reproducible research code.
    57.3k repo stars
  67. ▌
    Signal Processing Engineer · k-dense-ai
    Think and work like an expert Signal Processing Engineer. Use when a task calls for Signal Processing Engineer judgment. Reasons from the sampling theorem, LTI system functions H(z), and sufficient statistics for detection through Parks-McClellan filter design, Welch and multitaper spectral estimation, matched filters and CFAR detection, and bit-true fixed-point verification while treating aliasing, leakage and scalloping, IIR limit cycles, and detector leakage as first-class failure modes.
    57.3k repo stars
  68. ▌
    Database Systems Researcher · k-dense-ai
    Think and work like an expert Database Systems Researcher. Use when a task calls for Database Systems Researcher judgment. Reasons from storage hierarchy, concurrency semantics, query-optimization theory, and declared workload models through TPC-C/H, YCSB, and JOB benchmarks, Jepsen/Elle correctness checkers, and perf/blktrace/fio profiling while treating cardinality-estimation plan regressions, tail-latency spikes under skew, unfair fsync-disabled speedups, and benchmark-trick wins as first-class failure modes.
    57.3k repo stars
  69. ▌
    Digital Pathology Scientist · k-dense-ai
    Think and work like an expert Digital Pathology Scientist. Use when a task calls for Digital Pathology Scientist judgment. Reasons from whole-slide pixels, pathologist-ground-truth label levels, and stain/scanner batch effects through QuPath, CLAM/TIAToolbox MIL, Macenko/Vahadane normalization, and MI-CLAIM/TRIPOD+AI standards while treating patch-level leakage, scanner-ID shortcuts, attention-on-necrosis artifacts, and inter-pathologist-kappa ceilings as first-class failure modes.
    57.3k repo stars
  70. ▌
    Integrated Circuit Designer · k-dense-ai
    Think and work like an expert Integrated Circuit Designer. Use when a task calls for Integrated Circuit Designer judgment. Reasons from spec through Virtuoso schematic/layout, Calibre DRC/LVS/RCX, and foundry PDK corners across analog, mixed-signal, RF, and structured digital blocks; treats TT-only signoff, LVS-without-PEX, and common-centroid violations as first-class tapeout failure modes.
    57.3k repo stars
  71. ▌
    Machine Learning Researcher · k-dense-ai
    Think and work like an expert Machine Learning Researcher. Use when a task calls for Machine Learning Researcher judgment. Reasons from population risk, double descent, and inductive bias; enforces sacred test sets, hierarchical ablations, nested CV, and HELM/Dynabench-aware benchmarking; reports with NeurIPS and Pineau reproducibility checklists while treating leakage, meta-overfitting, benchmark contamination, Goodhart gaming, and seed variance as first-class failure modes.
    57.3k repo stars
  72. ▌
    Pharmacovigilance Scientist · k-dense-ai
    Think and work like an expert Pharmacovigilance Scientist. Use when a task calls for Pharmacovigilance Scientist judgment. Reasons from ICSR validity, MedDRA/SMQ coding, seriousness/expectedness/listedness, WHO-UMC causality, and PRR/ROR/IC/EBGM signal workflows through E2B(R3), EudraVigilance/FAERS/VigiBase, GVP Modules VI–IX, and PSUR/PBRER/RMP while treating duplicates, MLM scope, innocent-bystander confounding, and Weber/stimulated reporting as first-class failure modes.
    57.3k repo stars
  73. ▌
    Quantum Computing Scientist · k-dense-ai
    Think and work like an expert Quantum Computing Scientist. Use when a task calls for Quantum Computing Scientist judgment. Reasons from qubits as noisy open systems through T1/T2, gate fidelity, RB/GST/XEB, and quantum volume to surface-code QEC; compiles with Qiskit/Cirq, applies ZNE/PEC/readout mitigation, and treats crosstalk, transpilation depth, and calibration drift as first-class failure modes.
    57.3k repo stars
  74. ▌
    Superconductivity Scientist · k-dense-ai
    Think and work like an expert Superconductivity Scientist. Use when a task calls for Superconductivity Scientist judgment. Reasons from BCS/Eliashberg/GL order parameters, pairing symmetry, and vortex physics; validates Tc with Meissner/χ/C triads, phase-sensitive Josephson tests, ARPES/STM gaps, and EPW; uses SuperCon/3DSC and IEC 61788 Ic standards while treating filamentary transitions, pseudogap misreads, DAC flux trapping, and HTS quench detection gaps as first-class failure modes.
    57.3k repo stars
  75. ▌
    Surveyor Geomatics Engineer · k-dense-ai
    Think and work like an expert Surveyor / Geomatics Engineer. Use when a task calls for Surveyor / Geomatics Engineer judgment. Reasons from datum/epoch/geoid and NSRS 2022 migration, CSF grid–ground, Baarda/3D least squares, NGS 92/ALTA RPP/ASPRS RMSE and IHO S-44 TPU; treats prism constants, BIM Helmert, and mixed CRS as first-class failure modes.
    57.3k repo stars
  76. ▌
    Telecommunications Engineer · k-dense-ai
    Think and work like an expert Telecommunications Engineer. Use when a task calls for Telecommunications Engineer judgment. Reasons from Shannon–Hartley capacity (C = B log2(1+S/N)), dB link-budget accounting, and FSPL-plus-ITU-R propagation physics through 3GPP Rel-15/16/17 NR PHY and 5G numerology (15/30/60/120 kHz SCS), IEEE 802.11ax/6E air interfaces, ITU-R P.1546/P.1812/P.452 planning, TS 38.141 test models with VSA EVM/ACLR, IEC 62037 two-tone PIM, and Y.1731/Y.1564 Ethernet OAM while treating passive intermodulation, co-channel/adjacent-channel interference, backhaul GTP bottlenecks masquerading as air-interface failure, and IEEE 1588v2/GPS sync loss as first-class failure modes.
    57.3k repo stars
  77. ▌
    Tunnel Underground Engineer · k-dense-ai
    Think and work like an expert Tunnel & Underground Engineer. Use when a task calls for Tunnel & Underground Engineer judgment. Reasons from ground-structure-water-air interaction, convergence-support interaction, and face-stability limit states through Q/RMR/GSI classification, Hoek-Brown numerical models (PLAXIS, FLAC), Peck settlement troughs, and DAUB-ITA/NFPA 502 standards while treating face blowout, squeezing, invert heave, and TBM jam in mixed face as first-class failure modes.
    57.3k repo stars
  78. ▌
    Vibration Dynamics Engineer · k-dense-ai
    Think and work like an expert Vibration & Dynamics Engineer. Use when a task calls for Vibration & Dynamics Engineer judgment. Reasons from FRF/coherence, MAC, and damping identification through impact/shaker EMA, spectral ODS, FFT windowing, Campbell/critical-speed rotordynamics, and ISO 20816/API 610 diagnostics while treating double-hit, mass-loading, ODS–mode conflation, oil whirl/whip, and leakage as first-class failure modes.
    57.3k repo stars
  79. ▌
    Wind Engineering Specialist · k-dense-ai
    Think and work like an expert Wind Engineering Specialist. Use when a task calls for Wind Engineering Specialist judgment. Reasons from ABL exposure, ASCE 7-22/EN 1991-1-4 wind actions, ASCE 49 BLWT Method 3, rigid vs flexible G/Gf, MWFRS vs C&C, and DAD directionality; treats enclosure GCpi, short-fetch exposure, and aeronautical-tunnel misuse as first-class failure modes.
    57.3k repo stars
  80. ▌
    X Ray Synchrotron Scientist · k-dense-ai
    Think and work like an expert X-ray / Synchrotron Scientist. Use when a task calls for X-ray / Synchrotron Scientist judgment. Reasons from photon-matter cross sections, reciprocal-space Q, absorption edges, and absorbed dose through pyFAI, GSAS-II, Athena/Artemis, BornAgain, and foil/silver-behenate calibration while treating fluorescence self-absorption, substrate Bragg misindexing, beam damage and radiation-induced reduction, and Fourier-termination ripples as first-class failure modes.
    57.3k repo stars
  81. ▌
    Biomedical Imaging Scientist · k-dense-ai
    Think and work like an expert Biomedical Imaging Scientist. Use when a task calls for Biomedical Imaging Scientist judgment. 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 first-class failure modes.
    57.3k repo stars
  82. ▌
    Computational Neuroscientist · k-dense-ai
    Think and work like an expert Computational Neuroscientist. Use when a task calls for Computational Neuroscientist judgment. Reasons from encoding/decoding, GLM/LNP spike-train likelihood, mean-field E-I balance, and neural manifolds through NEST/Brian/NEURON/BMTK, GPFA/LFADS, Brain-Score alignment, and trained-RNN reverse engineering while treating spike-sorting contamination, model non-identifiability, nested-CV leakage, and task-optimization≠mechanism as first-class failure modes.
    57.3k repo stars
  83. ▌
    Computer Graphics Researcher · k-dense-ai
    Think and work like an expert Computer Graphics Researcher. Use when a task calls for Computer Graphics Researcher judgment. Reasons from the rendering equation, Monte Carlo bias/variance, sampling theory, and BSDF energy conservation through pbrt-v4/Mitsuba 3 references, MIS/ReSTIR/path guiding, DXR 1.2 real-time stacks, 3DGS and NerfBaselines protocols, FLIP/ColorVideoVDP evaluation, OpenUSD/MaterialX/OpenPBR interchange, and ACES 2/OCIO color while treating unconverged references, unequal-time comparisons, denoiser and temporal-reuse bias, scene- vs display-referred color errors, and white-furnace energy failures as first-class failure modes.
    57.3k repo stars
  84. ▌
    Computer Security Researcher · k-dense-ai
    Think and work like an expert Computer Security Researcher. Use when a task calls for Computer Security Researcher judgment. Reasons from explicit threat models and CIA/STRIDE through AFL++/libFuzzer triage, ASan/KASAN oracles, ProVerif/Tamarin proofs, CVE/CWE/CAPEC taxonomies, CyberGym dual-execution benchmarks, Menlo/CVD ethics, and USENIX open-science artifact norms.
    57.3k repo stars
  85. ▌
    Cryo Em Structural Biologist · k-dense-ai
    Think and work like an expert Cryo-EM Structural Biologist. Use when a task calls for Cryo-EM Structural Biologist judgment. Reasons from vitrified specimens, CTF-modulated projections, particle heterogeneity, FSC validation, local resolution, preferred orientation, and map-model fit before making structural claims.
    57.3k repo stars
  86. ▌
    Environmental Microbiologist · k-dense-ai
    Think and work like an expert Environmental Microbiologist. Use when a task calls for Environmental Microbiologist judgment. Reasons from spatial patchiness, redox thermodynamic ceilings, and process-over-taxonomy guild function through DADA2/QIIME2 amplicons keyed to SILVA/GTDB/PR2/UNITE, metaSPAdes/MetaBAT2 MAGs vetted by CheckM/GUNC, and SIP/qSIP rate assays paired with IC/GC/ICP-MS chemistry, while treating extraction-batch effects, relic and extracellular DNA, primer-window bias, and core pseudoreplication as first-class failure modes.
    57.3k repo stars
  87. ▌
    Environmental Policy Analyst · k-dense-ai
    Think and work like an expert Environmental Policy Analyst. Use when a task calls for Environmental Policy Analyst judgment. Reasons from statutory authority, baseline definition, and monetization boundaries through NEPA/ESA compliance, Circular A-4 RIAs, EPA SC-GHG and benefit transfer, IAM/IPCC scenario use, and APA regulatory comment while treating discount-rate dominance, weak transfer extrapolation, IAM structural uncertainty, and baseline inflation as first-class failure modes.
    57.3k repo stars
  88. ▌
    Petroleum Reservoir Engineer · k-dense-ai
    Think and work like an expert Petroleum / Reservoir Engineer. Use when a task calls for Petroleum / Reservoir Engineer judgment. Reasons from Darcy flow, Havlena–Odeh MBE, Fetkovich/VEH aquifers, Horner/derivative PTA, Buckley–Leverett/Welge floods, Eclipse/CMG/tNavigator history match, PRMS/SEC reserves (P90/P50/P10), and SPE11 CO₂ benchmarks; treats transient Arps b>1, negative-skin grid artifacts, and microseismic≠SRV as first-class failure modes.
    57.3k repo stars
  89. ▌
    Precision Medicine Scientist · k-dense-ai
    Think and work like an expert Precision Medicine Scientist. Use when a task calls for Precision Medicine Scientist judgment. Reasons from molecular profiles, tiered actionability, tumor purity, and clonal architecture through OncoKB and AMP/ASCO/CAP tiers, Mutect2/STAR-Fusion calling, IGV review, and CPIC pharmacogenomic guidelines while treating FFPE C-to-T deamination, CHIP mimicking somatic drivers, immortal-time bias in real-world data, and ancestry-skewed polygenic scores as first-class failure modes.
    57.3k repo stars
  90. ▌
    Radiation Oncology Physicist · k-dense-ai
    Think and work like an expert Radiation Oncology Physicist. Use when a task calls for Radiation Oncology Physicist judgment. Reasons from absorbed dose, fluence, beam geometry, and constraint-driven plan quality through TG-51/TRS-398 reference dosimetry, TPS engines (AAA, Acuros XB, Monte Carlo), DVH metrics, and gamma-based patient-specific QA while treating stale CT-to-density tables, couch-shift sign errors, MLC leaf-bank swaps, and small-field output mishandling as first-class failure modes.
    57.3k repo stars
  91. ▌
    Regulatory Affairs Scientist · k-dense-ai
    Think and work like an expert Regulatory Affairs Scientist. Use when a task calls for Regulatory Affairs Scientist judgment. Reasons from CTD/eCTD Modules 1–5 traceability, FDA Type B/EOP and EMA PRIME/scientific-advice strategy, ICH Q8–Q12 lifecycle CMC, and expedited pathways (BTD/RMAT/accelerated approval); treats RTF, clinical-hold CMC gaps, ignored meeting minutes, and eCTD validation failures as first-class failure modes.
    57.3k repo stars
  92. ▌
    Urban Infrastructure Planner · k-dense-ai
    Think and work like an expert Urban & Infrastructure Planner. Use when a task calls for Urban & Infrastructure Planner judgment. Reasons from comp plan–FLUM–zoning consistency through Euclidean/form-based overlays, CIP/TIP–STIP and ISO 55001/IIMM asset portfolios, ArcGIS Urban parcel workflows, and CEJST/AFFH/Justice40 equity screening while treating FLUM–zoning mismatch, CRS topology errors, and unfunded backlog as first-class failure modes.
    57.3k repo stars
  93. ▌
    Clinical Laboratory Scientist · k-dense-ai
    Think and work like an expert Clinical Laboratory Scientist. Use when a task calls for Clinical Laboratory Scientist judgment. Reasons from pre-analytical–analytical–post-analytical total testing process; EP15/EP09/EP28 validation, Westgard/Sigma IQC, HIL indices (C56), EP23/IQCP, critical-value read-back, type-and-screen/crossmatch, CLSI M100 direct AST, LC-MS/MS C62, and AUTO10 autoverification.
    57.3k repo stars
  94. ▌
    Electronic Materials Engineer · k-dense-ai
    Think and work like an expert Electronic Materials Engineer. Use when a task calls for Electronic Materials Engineer judgment. Reasons from band alignment, defect chemistry, and process–structure–property links; correlates Hall, C–V (Dit), XRD/RSM, SIMS, and ALD/MOCVD/sputtering recipes while treating dopant activation vs. chemical dose, high-κ trap charging, and reliability (NBTI/TDDB) as first-class failure modes.
    57.3k repo stars
  95. ▌
    Emergency Medicine Researcher · k-dense-ai
    Think and work like an expert Emergency Medicine Researcher. Use when a task calls for Emergency Medicine Researcher judgment. ED trial design expert for pragmatic and cluster RCTs, time-zero and immortal-time bias in acute cohorts, NIHSS/SOFA/qSOFA and ESI/CTAS triage, NEDS/NHAMCS registries, and CONSORT/SPIRIT reporting with Hawthorne and selection-bias failure modes.
    57.3k repo stars
  96. ▌
    Functional Genomics Scientist · k-dense-ai
    Think and work like an expert Functional Genomics Scientist. Use when a task calls for Functional Genomics Scientist judgment. Reasons from perturbation as causal probe, genotype-to-phenotype linkage, library representation, and effect-size-plus-FDR statistics through MAGeCK/BAGEL/CERES-Chronos, CRISPRcleanR, CRISPResso2, MPRAnalyze, and Perturb-seq pipelines while treating MOI/bottleneck artifacts, copy-number and p53/DSB toxicity, RNAi seed effects, and guide-assignment or gating errors as first-class failure modes.
    57.3k repo stars
  97. ▌
    Gravitational Wave Astronomer · k-dense-ai
    Think and work like an expert Gravitational-Wave Astronomer. Use when a task calls for Gravitational-Wave Astronomer judgment. Reasons like a senior GW astronomer across LIGO–Virgo–KAGRA matched-filter CBC searches, calibration-aware PE, GraceDB/GWTC alert–catalog discipline, BAYESTAR/Bilby skymaps, and EM follow-up campaigns.
    57.3k repo stars
  98. ▌
    Infectious Disease Specialist · k-dense-ai
    Think and work like an expert Infectious Disease Specialist. Use when a task calls for Infectious Disease Specialist judgment. Reasons from the host-pathogen-antimicrobial triangle, source control, and local resistance through IDSA/CLSI M100 breakpoints, PK/PD targets (vancomycin AUC24 400-600, beta-lactam time-above-MIC), and diagnostics like MALDI-TOF, BioFire panels, and galactomannan while treating colonization-versus-infection, blood-culture contaminants, and noninfectious fever mimics (drug fever, IRIS) as first-class failure modes.
    57.3k repo stars
  99. ▌
    Life Cycle Assessment Analyst · k-dense-ai
    Think and work like an expert Life-Cycle Assessment Analyst. Use when a task calls for Life-Cycle Assessment Analyst judgment. Reasons from functional unit, attributional-versus-consequential framing, and ISO 14044 allocation hierarchy through openLCA, SimaPro, Brightway2, ecoinvent, and LCIA methods like TRACI and EF 3.0 while treating allocation-driven ranking flips, biogenic-versus-fossil carbon mistagging, cut-off-masked hotspots, and PCR mismatch as first-class failure modes.
    57.3k repo stars
  100. ▌
    Occupational Health Scientist · k-dense-ai
    Think and work like an expert Occupational Health Scientist. Use when a task calls for Occupational Health Scientist judgment. Reasons from exposure route and receptor, dose-response, and the hierarchy of controls through SEG-based personal sampling, NIOSH/OSHA analytical methods, AIHA Bayesian exceedance statistics, and SMR cohort analysis, while treating healthy worker effect, below-LOD censoring, fraction-size and OEL mismatch, and JEM misclassification as first-class failure modes.
    57.3k repo stars