NumPy agent skills for Claude Code, Codex and other agents.

面向中文自然语言的 Tushare 数据研究技能。用于把“看看这只股票最近怎么样”“帮我查财报趋势”“最近哪个板块最强”“北向资金在买什么”“给我导出一份行情数据”这类请求，转成可执行的数据获取、清洗、对比、筛选、导出与简要分析流程。适用于 A 股、指数、ETF/基金、财务、估值、资金流、公告新闻、板块概念与宏观数据等研究场景。

zillionare/zillionare

Sets up FAISS for fast nearest-neighbor search over large collections of dense vectors, choosing between Flat, IVF, HNSW and product quantization indexes.

Orchestra-Research/AI-Research-SKILLs

Estimates reaction fluxes inside cells from steady-state carbon-13 labeling data with a bundled mfapy-based solver, and reports which fluxes the data pin down.

K-Dense-AI/scientific-agent-skills

Profiles slow Python code with cProfile and memory profilers, then applies targeted fixes for CPU, memory, I/O and query bottlenecks.

wshobson/agents

Perform bounded, local exploratory analysis of explicitly supported scientific files.

Oleafly/Oleafly

Composites several moments from real drone footage into one still with ghost trails, then lays out paper figures and an editable PowerPoint file.

XXLiu-HNU/visualize_uav_trajectory

World-class data science skill for statistical modeling, experimentation, causal inference, and advanced analytics.

Raidriar7170/hermes-skilleval

Execute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh).

cortega26/chile-hub

Runs Cantera constant-volume or constant-pressure ignition simulations and reports temperature-based ignition delay with mechanism provenance and checks.

K-Dense-AI/scientific-agent-skills

Helps an agent write ComfyUI custom nodes in Python, including wrapping an existing script, mapping data types and handling image batches.

ConstantineB6/comfy-pilot

Procedure for writing and updating Matft's documentation (the Docusaurus site in website/ and the doc comments on the public API that become the Swift-DocC API reference).

jjjkkkjjj/Matft

Writes statistical analysis code for experimental data, runs it through a four-round review, and reports effect sizes, p-values and confidence intervals.

lingzhi227/agent-research-skills

Runs a math modeling contest pipeline for CUMCM and MCM/ICM entries in Codex CLI, with git checkpoints, verified solver code and human review at each stage.

RealSeaberry/AutoMCM-Pro

Academic backtesting framework for quantitative research. An agent skill from gauss314/skills.

gauss314/skills

Procedure for designing and writing Matft's XCTest cases with high coverage — boundary values, dtypes, memory layouts, NaN/inf, empty arrays, broadcasting, platform differences, performance and…

jjjkkkjjj/Matft

Generate a royalty-free lofi (or rain / typing / chime / any ambient) soundtrack ENTIRELY in code — no sampled audio ships.

IvanWng97/pixtuoid

Loads, cleans, aggregates and joins tabular data with pandas under a verification rule: every number reported must be one that the code actually printed.

pipeshub-ai/pipeshub-ai

Running Albucore micro-benchmarks under benchmarks/, synthetic router timings, and comparing PyPI releases with uv --no-project.

albumentations-team/albucore

撰写文笔精炼、富有深度的量化交易博文，论点清晰、证据确凿、叙事层次更加丰富。适用于量化交易博文、因子研究、回测复盘、数据源排查、市场微观结构、策略原理、风险控制、职业观察、量化人物故事等选题。文章将聚焦具体角度，提供详实的大纲、证据规划及成稿，力求内容兼具思想深度与诚实性，而非单纯口号式宣传；同时，通过人物经历、引言、贡献及行业背景的融入，让文章更具可读性和吸引力。

zillionare/zillionare

Runs exploratory data analysis on tabular data after you confirm each column's measurement level, then writes CSV tables and a narrative summary.

TyrealQ/q-skills

Reads, edits, anonymizes and converts DICOM medical imaging files with pydicom, including pixel data extraction and compressed transfer syntaxes.

davila7/claude-code-templates

Albucore image processing conventions - shapes (H,W,C), dtypes (uint8/float32), benchmark-driven backend routing (OpenCV, NumPy, Torch CPU, LUT, NumKong), tests, and lockfile discipline.

albumentations-team/albucore

Runs reproducible math computations and counterexample searches with SymPy, NumPy and mpmath, logging evidence without presenting results as proofs.

tradecatlabs/vibe-coding-cn

Builds, fits, checks and compares Bayesian models in PyMC, from priors and NUTS sampling to variational inference, LOO and WAIC comparison, and diagnostics.

davila7/claude-code-templates

Analyzes uploaded cohort data to compute retention curves and feature adoption trends, builds heatmaps and charts, and suggests qualitative follow-up research.

phuryn/pm-skills

Walks through producing a master audio track plus stems in Python, from checking a reference file and timing sections by BPM to effects, a zip archive and final verification.

HKUDS/OpenSpace

Procedure for benchmarking Matft's PerformanceTests against Numpy and reporting the results (and, when asked, updating the speed comparison table on the docs site, website/docs/performance.md).

jjjkkkjjj/Matft

Processes tabular datasets too large for RAM with Vaex: lazy DataFrames, fast aggregations, big-data plots and ML pipelines over CSV, HDF5, Arrow and Parquet.

davila7/claude-code-templates

Analyzes CSV, Parquet and JSON data with DuckDB, Polars, numpy and matplotlib, preferring a persistent kernel over repeated one-shot processes.

code-yeongyu/oh-my-openagent

Code review for py4vasp changes. An agent skill from vasp-dev/py4vasp.

vasp-dev/py4vasp

Review and improve Python docstrings for Great Docs API reference generation.

pymc-labs/pathmc

Procedure for adding tests for Matft's image processing (Matft.image., indexing or channel swapping on images, etc.), generating comparison images that put the result next to an OpenCV reference…

jjjkkkjjj/Matft

Detects Elliott Wave structures in price data with a Zigzag swing finder and Fibonacci checks, and turns completed waves into long, short or flat signals.

HKUDS/Vibe-Trading

Chunked N-D arrays for cloud storage. An agent skill from davila7/claude-code-templates.

davila7/claude-code-templates

Parallel/distributed computing. An agent skill from davila7/claude-code-templates.

davila7/claude-code-templates

Parse FCS (Flow Cytometry Standard) files v2.0-3.1. An agent skill from davila7/claude-code-templates.

davila7/claude-code-templates

Procedure for releasing a new version of Matft (decide the version → check tests → write release notes → create and push an annotated tag → publish a GitHub Release).

jjjkkkjjj/Matft

Proves a RuView result is real by running a deterministic SHA-256 proof and a witness bundle, and by checking reports for untagged or unreproducible accuracy claims.

ruvnet/RuView

Checks that the tools and Python packages needed for a math modeling paper workflow are installed and offers platform-specific install commands for anything missing.

jihe520/MathModelAgent

Pricing completo de opciones europeas y americanas. An agent skill from gauss314/skills.

gauss314/skills

Set up and maintain documentation for scientific Python packages.

Yikai-Liao/symusic

Guide for writing and modifying NKI kernels. An agent skill from uw-syfi/vibesys.

uw-syfi/vibesys

Zero-shot univariate time series forecasting using the Reverso foundation model (NumPy/Numba CPU-only inference).

oaustegard/claude-skills

Optimize or review eager CPU-only Albucore PyTorch runtime paths with benchmark-backed decisions.

albumentations-team/albucore

Construcción y optimización cuantitativa de portafolios: Markowitz (scipy.optimize + Monte Carlo), Black-Litterman (prior CAPM, views absolutas/relativas, posterior bayesiano), HRP/HERC/NCO…

gauss314/skills

Portuguese guide to building a retrieval-augmented generation assistant over a company's documents, with embeddings, section-based chunking, retrieval and a client workflow.

Hermes-brasil/hermes-brasil

Runs a math modeling competition entry end to end, in AI-led or human-led mode, with Git checkpoints and self-verified solver code before it enters the LaTeX paper.

RealSeaberry/AutoMCM-Pro

Detects 15 classic candlestick patterns with vectorized pandas code and combines bullish and bearish scores into a long, short or flat trading signal.

HKUDS/Vibe-Trading