Best agent skills for Data Scientists, page 9

Refresh GitNexus indexing and regenerate local GitNexus skills when repository status is stale.

ML4ITS/TimeVQVAE

Verify a Docglow change actually works before submitting or merging a PR.

docglow/docglow

Inspect a PyTorch baseline with torch.compile graphs/code and torch.profiler before drafting a custom kernel, then compare TileLang and PyTorch timelines, forward/backward regions, and allocations.

sablin39/tilelang-cuda-skills

Plans memory headroom, works through out-of-memory failures and watches temperature and power during long ML training jobs on NVIDIA DGX Spark.

wshobson/agents

Route a verl-omni performance investigation to the right tool and capture a usable trace.

verl-project/verl-omni

A skill your agent uses when operating or maintaining the RS-PaperClaw pipeline that fetches remote-sensing arXiv papers, creates per-paper issues, builds daily digests, reconciles issue sets, and…

thinson/RS-PaperClaw

Implement, migrate, review, or debug Panda CSS styles in the Bangumi frontend.

bangumi/frontend

交互式测验，将你的 AI/ML 知识映射到 523 节课、20 个阶段的 AI Engineering from Scratch 课程起点。

fancyboi999/ai-engineering-from-scratch-zh

A chart & report builder for AI. An agent skill from matsonj/mviz.

matsonj/mviz

Audit TSZ repo iteration speed and quality. An agent skill from tsz-org/tsz.

tsz-org/tsz

Fetch a region of GWAS summary statistics from the NHGRI-EBI GWAS Catalog harmonised collection via tabix-on-FTP.

ClawBio/ClawBio

Deliberate-choice procedure for a medium-to-high-stakes engineering fork — when the first plausible solution (the instinct, the default next-token pull) would be costly to get wrong.

syahiidkamil/Software-Engineer-AI-Agent-Atlas

Fetch financial, market, economic, fundamental, news, options, crypto, ETF, index, and macro data through the OpenBB Python interface instead of the OpenBB MCP server.

monarchjuno/vibe-investing

Explore, construct, and speak with identities in an LLM's latent space using YouSim's simulator prompts and its /locate /summon /speak /steer /request command grammar.

plastic-labs/yousim

Move hardcoded lookup/config constants (gender maps, header dicts, value translations, column-label maps, date formats) out of a crawler and into the dataset .yml — as datapatch lookups wherever…

opensanctions/opensanctions

A skill your agent uses when a user asks how many tokens (or how much context/cost) ContextPilot has saved, or wants a ContextPilot savings status/summary inside Hermes Agent — e.g.

EfficientContext/ContextPilot

用 catbus CLI 读取或操作小红书（RedNote）、抖音、TikTok、B 站（Bilibili）、快手、微博、闲鱼、淘宝、京东、X（Twitter）这 10 个平台：搜索、详情、评论、用户、推荐流、下载、发布、点赞关注、私信、直播弹幕，输出统一的 JSON。用户要查询、采集、导出、监听或操作这些平台上的内容和账号时使用。

cv-cat/catbus

Stage-aware prompt coaching, prompt improvement, lookback analysis, prompting habit feedback, and local reports about prompt quality for AI coding agents such as Claude Code or Codex.

chengzhongwei/Prompt-sensei

Open OwnMem Console, the local dashboard for this repository's memory.

grpcer/ownmem

Find and assess Indonesian public-data sources using a dated, evidence-backed catalog.

suryast/indonesia-gov-apis

Prepare an interview task for a candidate, as part of our hiring process.

polarsource/polar

Add event tracking calls to Vue/Nuxt components in the Insights app using the useTrackEvent composable.

linuxfoundation/insights

Audit imaging acquisition, reconstruction, series eligibility, quantitative transforms and protocol drift; not model training.

huang-sir1/radiology-skills

DeepSeek API 助手 - 编程辅助、模型选择、API调用指南、定价信息. An agent skill from dongsheng123132/u-claw.

dongsheng123132/u-claw

Analyze user retention and churn using survival analysis, cohort analysis, and machine learning.

liangdabiao/claude-data-analysis-ultra-main

Drive a live marimo notebook in VS Code as a workspace: run Python in the same kernel the user does, inspect and explore live notebook state and data, prototype and debug code, and commit durable…

marimo-team/marimo-lsp

KQL language expertise for writing correct, efficient Kusto queries using the Fabric RTI MCP tools.

microsoft/fabric-rti-mcp

Image-to-code replication pipeline. An agent skill from Yu-369/VibeCurb.

Yu-369/VibeCurb

Prisma Client API reference covering model queries, filters, operators, and client methods.

curvenote/curvenote

Convert a Jupyter notebook (.ipynb) to a marimo notebook (.py).

ericmjl/llamabot

A skill your agent uses when implementing any endpoint, form handler, CLI tool, or function that accepts external input.

aiming-lab/MetaClaw

Keeps the engagement record for client work. An agent skill from suboss87/FDEOps.

suboss87/FDEOps

Patterns for invoking the Apify CLI (apify) from agents. An agent skill from apify/apify-cli.

apify/apify-cli

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

Orchestra-Research/AI-Research-SKILLs

Turns a natural-language description of routing intent into a valid Lemonade collection.router policy JSON.

amd/skills

Review a proposed Agent Skill for structural validity and content quality before publishing.

mongodb/agent-skills

Mine AI coding-agent session transcripts into structured, gate-validated GPU-kernel optimization records for the wiki.

alibaba/atrex-kernel-agent

Create, build, validate, and upload a Packs SDK agent (pack.ts using sdk.newAgent()) to your Coda/Superhuman account, including registering an API token, wiring up tools…

coda/packs-sdk

Capture a Nsight Systems (.nsys-rep) profile of a short PithTrain run for performance analysis.

mlc-ai/pith-train

Create original, material-reference-driven, consistent, photorealistic character casting sheets for commercial, advertising, cinematic, model, occupational, everyday, historical…

dacnay816y62-hub/character-casting-studio-skill

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

Profile CUDA kernels with Nsight Compute on B200 / sm100. An agent skill from mit-han-lab/ncu-report-skill.

mit-han-lab/ncu-report-skill

A skill your agent uses when adding a new optimized kernel or operator to veomni/ops/.

ByteDance-Seed/VeOmni

Build DSPy 3.2.x programs through spec, program, metric and baseline; extend to optimization and export when requested and justified by task budget.

intertwine/dspy-agent-skills

Audit and improve the prompt surface of Avibe Agents across backends (Claude, Codex/GPT, OpenCode) — global and project rules, Agent system prompts, Skills, delegation briefs, and Task and Watch…

avibe-bot/avibe

Designs clear, testable prompts for agent workflows. An agent skill from repowise-dev/claude-code-prompts.

repowise-dev/claude-code-prompts

Build a new time-series analytics use case on top of the deployed Time Series Analytics microservice — bring it up with Docker Compose (from a repo clone, or by fetching the compose files from…

open-edge-platform/edge-ai-libraries

Triage and repair hipfire runtime failures such as daemon hangs, stale serve.pid, port 11435 conflicts, ROCm include-path problems, missing precompiled kernels, VRAM OOM, kernel JIT failures, and…

warpfront/hipfire