Skip to main content
huangzesen
GitHub creator profile

huangzesen

Repository-level view of 594 collected skills across 27 GitHub repositories.

skills collected
594
repositories
27
updated
2026-06-24
repository map

Where the skills live

Top repositories by collected skill count, with their share of this creator catalog and occupation spread.

#01
heliosi-501-corpus-skill
501 skills · 2026-05-21
PhysicistsAstronomersSoftware DevelopersAtmospheric & Space ScientistsPhysical Scientists, All OtherBiological Scientists, All Other
10 occupation categories · 100% classified
84%share
#02
quant-company
25 skills · 2026-04-26
Software DevelopersNetwork & Computer Systems AdministratorsData Scientists
3 occupation categories · 100% classified
4.2%share
#03
warren-buffett-persona
18 skills · 2026-04-26
Financial & Investment AnalystsMarket Research Analysts & Marketing SpecialistsFundraisersPersonal Financial AdvisorsTechnical Writers
5 occupation categories · 100% classified
3.0%share
#04
zesen-huang
12 skills · 2026-04-25
AstronomersPhysicistsAtmospheric & Space ScientistsAnthropology & Archeology Teachers, PostsecondaryHuman Resources Assistants, Except Payroll & Timekeeping
5 occupation categories · 100% classified
2.0%share
#05
persona-jiachen-amber-liu
8 skills · 2026-05-04
Data ScientistsBiological Scientists, All OtherComputer Science Teachers, PostsecondarySocial Scientists & Related Workers, All OtherSoftware Developers
5 occupation categories · 100% classified
1.3%share
#06
li-bai-skill
5 skills · 2026-05-05
English Language & Literature Teachers, PostsecondaryWriters & AuthorsHistory Teachers, Postsecondary
3 occupation categories · 100% classified
0.8%share
#07
marco-velli
3 skills · 2026-04-24
PhysicistsPhysics Teachers, PostsecondaryWriters & Authors
3 occupation categories · 100% classified
0.5%share
#08
impersonate-meta
2 skills · 2026-05-29
EditorsTechnical WritersWriters & Authors
3 occupation categories · 100% classified
0.3%share
Showing the top 8 repositories here; full repository list continues below.
repository explorer

Repositories and representative skills

heliosi-501-corpus
physicists

Use when the user asks about HelioSI, the heliophysics paper-skill corpus, the 501-skill corpus, paper-to-skill compilation, generating hypotheses or experiments from heliophysics literature, selecting corpus entries by topic (PFSS, open flux, PSP switchbacks, SEPs, turbulence, solar-wind classification, instruments, MHD, agent-runtime design), or deciding which papers to verify against full text.

2026-05-21
hu-2022-deep-swim-cnn-discontinuities
software-developers

Use when running Deep-SWIM, a semi-supervised CNN pipeline that classifies 5-minute Wind/MFI magnetic-field windows (3s-resampled, B_x/B_y/B_z stacked as channels) as discontinuity vs ambient solar wind. Central paper claim: a four-layer 1D-CNN trained with contrastive learning + pseudo-labeling + Online Hard Example Mining (OHEM) reaches AUC ≈ 0.90 on the held-out validation set and precision 0.52 / recall 0.73 / AUC 0.82 on a one-day expert-hand-labelled test set (2018-11-18), under heavy class imbalance (~15 % discontinuity-positive windows). NeurIPS 2021 Machine Learning and the Physical Sciences workshop (Lamdouar et al. 2022, arXiv:2203.01184). Note: the slug retains a legacy first-author placeholder; the verified lead author is Hala Lamdouar (University of Oxford), not Hu.

2026-05-20
katsavrias-2025-periodic-density-structures-solar-orbiter
software-developers

Use when detecting and cataloguing quasi-Periodic Density Structures (PDSs) in Solar Orbiter density data with Multitaper + wavelet, and quantifying their radial-length-scale evolution between 0.3 and 1 au — central claim is slow-wind PDSs expand at ~10% and fast-wind PDSs compress at ~10% across that range (Katsavrias et al. 2025, arXiv:2511.15518; venue TODO verify).

2026-05-20
sasli-2026-ember-modulated-ion-acoustic-wave-ml
software-developers

Use when running EMBER (Electron heating from Modulated Burst-mode Event Recognition) on PSP FIELDS Digital Burst Memory (DBM) voltage waveforms to detect modulated ion-acoustic waves (mIAWs — including triggered IAWs and frequency-dispersed IAWs) and correlate them with anomalous core-electron heating. Central paper claim: an ensemble of 16 background-only anomaly detectors (physics-motivated + classical outlier + deep-learning), run on log-scaled Fourier spectrograms of DBM bursts from PSP Encounters 6–9 and 15, recovers ≈ 93 % of labelled mIAW events at an estimated 1 % FAR on a curated catalog of 42 anomalous + 496 background spectrograms; flagged intervals show core perpendicular T_e above adiabatic cooling and elevated T_e/T_i ratios, reproducing previously reported heating phenomenology without using temperatures in the detection step. Sasli et al. 2026, arXiv:2605.00162, submitted to Earth and Space Science.

2026-05-20
paper-gottweis-2025-ai-co-scientist-multi-agent-gemini
physicists

Use when the agent is positioning the consuming agent/manuscript against ai-scientist-system literature, borrowing a agent-runtime-async-tournament design pattern, or auditing a benchmark/manuscript claim related to it - central claim is "A multi-agent system on Gemini 2.0 implementing a generate-debate-evolve loop with asynchronous task execution and tournament-style hypothesis evolution improve" (arXiv preprint 2025).

2026-05-20
paper-liweiwu-2026-ai-co-scientist-ranking-search-models
physicists

Use when the agent is positioning the consuming agent/manuscript against domain-specific-ai-scientist literature, borrowing a agent-runtime-full-pipeline-cloud design pattern, or auditing a benchmark/manuscript claim related to it - central claim is "An AI Co-Scientist framework automates the full search-ranking research pipeline (idea -> code -> GPU training -> analysis) with single-LLM agents for routine t" (arXiv preprint 2026).

2026-05-20
paper-llmtreesearch-2026-multi-pathogen-disease-forecasting
physicists

Use when the agent is positioning the consuming agent/manuscript against domain-specific-ai-scientist literature, borrowing a agent-runtime-tree-search-executable-software design pattern, or auditing a benchmark/manuscript claim related to it - central claim is "An autonomous LLM-guided tree-search system iteratively generates, evaluates, and optimizes executable forecasting software for multi-pathogen disease forecasti" (arXiv preprint 2026).

2026-05-20
paper-yin-2024-turing-tests-ai-scientist-benchmark
physicists

Use when the agent is positioning the consuming agent/manuscript against benchmark literature, borrowing a scientific-discovery-benchmark design pattern, or auditing a benchmark/manuscript claim related to it - central claim is "Seven historically-inspired Turing-style benchmark tests (heliocentric model from celestial observations, laws of motion, vibrating-string ODE, Maxwell's equati" (arXiv preprint 2024).

2026-05-20
Showing top 8 of 501 collected skills in this repository.
Showing top 8 of 25 collected skills in this repository.
buffett-capitalism-politics
market-research-analysts-and-marketing-specialists-131161

Warren Buffett's views on American capitalism, democracy, taxes, wealth inequality, and political economy — the "capitalism is good but the rules are rigged" framework.

2026-04-26
buffett-insurance
financial-and-investment-analysts

Warren Buffett's insurance empire — GEICO, General Re, Ajit Jain, and the float mechanism that funds Berkshire's equity portfolio. Sources: Berkshire Hathaway annual reports, GEICO corporate history, Fortune, "The Essays of Warren Buffett."

2026-04-26
buffett-meetings
market-research-analysts-and-marketing-specialists-131161

Berkshire Hathaway annual meetings — "Woodstock of Capitalism" — history, format, culture, and how to discuss the meeting as Buffett. Use when asked about the annual meeting, shareholder events, Q&A format, or post-Munger era.

2026-04-26
buffett-moat-cases
financial-and-investment-analysts

Buffett's iconic moat investments — See's Candy, Coca-Cola, Apple, American Express — and the economic moat concept in practice

2026-04-26
buffett-munger-partnership
market-research-analysts-and-marketing-specialists-131161

The 65-year Buffett-Munger partnership — origins, intellectual influence, shared values, Berkshire architecture, and lasting legacy.

2026-04-26
buffett-operating
financial-and-investment-analysts

Berkshire Hathaway's operating subsidiaries — BNSF, See's Candy, Nebraska Furniture Mart, and Berkshire's philosophy for managing operating businesses

2026-04-26
buffett-philanthropy
market-research-analysts-and-marketing-specialists-131161

Buffett's philanthropy — Gates Foundation, The Giving Pledge, Susan Thompson Buffett Foundation, personal giving philosophy, children's roles, and what makes his approach distinct.

2026-04-26
buffett-voice
technical-writers

Buffett's communication style — letter-writing craft, speaking patterns, humor, storytelling, and investment narrative art. Sources: Berkshire shareholder letters, annual meeting transcripts, Fortune, Warren Buffett Archive.

2026-04-26
Showing top 8 of 18 collected skills in this repository.
biography
astronomers

Biography, career trajectory, institutional affiliations, and professional record of Zesen Huang (黄泽森), solar physicist. Focus: MHD turbulence, Alfvén wave physics, Parker Solar Probe data analysis.

2026-04-25
huang-alfven-physics
physicists

Zesen Huang's research on Alfvén wave physics, wave action conservation in the expanding solar wind, the Alfvénon (solitary Alfvén wave) model, and the switchback reinterpretation.

2026-04-25
huang-mhd-turbulence
atmospheric-and-space-scientists-192021

Zesen Huang's research on MHD turbulence theory, the expanding-box model, residual energy, intermittency, and anisotropic turbulence scaling in the solar wind, with emphasis on Parker Solar Probe and Solar Orbiter observations.

2026-04-25
huang-oscillations
astronomers

Zesen Huang's research on coronal oscillations (2-min, 3-min, 5-min p-modes near the Alfvén surface) and the novel Gaussianity Scalogram method for solar wind structure classification. Covers PSP data analysis, wave interpretation, and scientific framing as Huang himself would present it.

2026-04-25
huang-psp-observations
astronomers

Zesen Huang's Parker Solar Probe observational research — switchbacks, proton/electron heating, intermittency, CIRs, and the PSP mission context.

2026-04-25
huang-turbulence-spectrum
atmospheric-and-space-scientists-192021

Zesen Huang's research on the 1/f turbulence spectrum in the solar wind, the dynamic formation of the spectrum, and the landmark identification of two distinct types of 1/f ranges based on Parker Solar Probe and Solar Orbiter observations.

2026-04-25
huang-persona
physicists

Complete persona skill for Zesen Huang (黄泽森) — solar physicist, UCLA. Covers: MHD turbulence, Alfvén wave physics, Parker Solar Probe observations. Contains: 5 domain skills, 4 profile files, 1 paper analysis skill, 10 method cards, bibliography with 35 entries. Note: huang-alfven-physics is the most developed skill (v1.4, 805 lines).

2026-04-25
huang-methods
physicists

Cognitive fingerprint of Zesen Huang — 10 method cards (VM001–VM010), each induced from ≥3 evidence instances across domain skills. These are NOT generic methodology; they are recurring patterns observable in Huang's research program on MHD turbulence and Parker Solar Probe analysis.

2026-04-25
Showing top 8 of 12 collected skills in this repository.
persona-jiachen
data-scientists-152051

Complete persona skill for Jiachen (Amber) Liu — ML Systems researcher, AI for Science advocate, builder of AI-native research infrastructure. PhD from UMich (Mosharaf Chowdhury), Research Scientist at Meta Superintelligence Lab. Covers LLM serving, federated learning, AI agents for science, evaluation frameworks, and the AI co-scientist vision.

2026-05-04
arguments-jiachen
social-scientists-and-related-workers-all-other

VA argument index for Jiachen (Amber) Liu — searchable verifiable arguments across all research domains. Each VA follows the 7-field claim schema with citekeys.

2026-05-04
methods-jiachen
computer-science-teachers-postsecondary

Cognitive fingerprint of Jiachen (Amber) Liu — 8 method cards induced from her research patterns across LLM serving, federated learning, AI agents, and evaluation frameworks. Each card backed by ≥3 VA instances.

2026-05-04
ai-agents-for-science
biological-scientists-all-other

Domain knowledge on AI agents for scientific experimentation — Curie, EXP-Bench, AI Research Engineering Skills, and the AI co-scientist vision — as practiced by Jiachen (Amber) Liu.

2026-05-04
ai-research-infrastructure
software-developers

Domain knowledge on AI-native research infrastructure — Orchestra, Vibe Research, and the Agent-Native Research Artifact (ARA) protocol. Covers Jiachen (Amber) Liu's vision connecting LLM systems to AI agents for science, the AI Research Skills Library (86+ skills), and the philosophy of making everyone a scientist. Use when discussing Orchestra, vibe research, AI co-scientists, or agent-native publishing.

2026-05-04
evaluation-frameworks
data-scientists-152051

Domain knowledge on evaluation frameworks and benchmarks built by Jiachen (Amber) Liu — IaC-Eval, ML.ENERGY, EXP-Bench, Humanity's Last Exam, Sci-Reasoning, and the pattern of evaluation-as-research. Use this when you need to understand Amber's benchmarking work, position evaluation infrastructure as a research contribution, or discuss her unique approach to AI research.

2026-05-04
federated-learning
data-scientists-152051

Domain knowledge on federated learning systems — benchmarking, optimization, client clustering, and resource management — as practiced by Jiachen (Amber) Liu. Covers FedScale, Auxo, FedTrans, and Venn. All claims sourced from published papers; unverifiable items marked [unverified].

2026-05-04
llm-serving-domain
data-scientists-152051

Domain knowledge on LLM serving systems, QoE metrics, and energy benchmarking — as practiced by Jiachen (Amber) Liu. Covers the Andes QoE framework, ML.ENERGY benchmark, and user-centric serving philosophy. All claims sourced from published papers; unverifiable items marked [unverified].

2026-05-04
Showing 12 of 27 repositories