Skip to main content
affpapa.org
RU EN
skill CX Codex

dask — Claude Code skill: parallel Python beyond memory

A skill that teaches the agent to use Dask for DataFrames, arrays and tasks that outgrow RAM or run across a cluster.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add K-Dense-AI/scientific-agent-skills --skill dask -a claude-code
Open on GitHub

What dask does

The skill maps out the five Dask components and helps the agent pick the right one. DataFrames carry pandas operations onto data larger than RAM and read many CSV or Parquet files at once. Arrays bring blocked NumPy computation to HDF5, Zarr and NetCDF. Bags handle text logs and JSON, Futures let you build custom task graphs with dependencies. Chunking, schedulers and distributed diagnostics get their own coverage.

Reference files such as references/dataframes.md, references/arrays.md and references/bags.md sit alongside code examples. The agent may use Read, Write, Edit and Bash, so it can both write a script and run it.

You need Python 3.10+ and dask 2026.8.0. DataFrame work calls for pandas 2+ and PyArrow 16+, and Zarr 3.4 needs Python 3.12+. Cloud paths like s3:// and gs:// only work with s3fs or gcsfs, and private data needs provider credentials. Since 2025.1.0 the expression-based DataFrame API is the only implementation, so installing dask-expr separately or setting dataframe.query-planning: False will break things.

What it helps with

  • compute a dataframe that does not fit in RAM
  • read hundreds of CSV or Parquet files as one dataframe
  • parallelise NumPy operations across cores
  • parse a stream of JSON logs without loading the whole file
  • build a custom task graph with dependencies via Futures

Example prompts for the agent

  • Read every data/2024-*.csv with Dask and average the values per category
  • This array is too big for memory — rewrite the computation with dask.array and chunks
  • Parse logs/*.json with dask.bag and write the result to Parquet

How to install dask

1Skills CLI (Vercel)

npx skills add K-Dense-AI/scientific-agent-skills --skill dask -a claude-code

2Manually: put the files in place

~/.claude/skills/dask/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/dask/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about dask

How do I install the dask skill in Claude Code?

Run npx skills add K-Dense-AI/scientific-agent-skills --skill dask -a claude-code. The skill file lands at ~/.claude/skills/dask/SKILL.md.

What does the dask skill do?

It gives the agent guidance on Dask: scaling pandas and NumPy past memory limits, processing files in partitions, and running work on a cluster. Reference docs cover DataFrames, Arrays, Bags and Futures.

What does the dask skill require?

Python 3.10+ and dask 2026.8.0. DataFrame workflows need pandas 2+ and PyArrow 16+, and cloud paths need s3fs or gcsfs with provider credentials.

Similar skills

All skills for Data and databases →
xlsx official anthropics Creates, reads, edits, and converts spreadsheet files. Use it when the requested deliverable is an Excel workbook or another tabular file. 187,223installs google-agents-cli-observability official Google This skill guides you through tracing and monitoring AI agents, including ADK agents. Use it when you need to inspect agent execution or monitor a deployed agent. CX Codex +1 511,300installs caveman-evidence-review JuliusBrussee A read-only skill reviews Caveman Cloud evidence on LLM spend, traces, and routing. Use it to see where a project’s model budget goes. CX Codex +1 104,500installs migration JuliusBrussee Enforces reversible, compatibility-safe transitions for schema, data, and API updates. Useful whenever data loss or rollout downtime is unacceptable. CX Codex +1 103,900installs performance-optimization addyosmani An agent skill that measures before it changes code: Core Web Vitals budgets, N+1 queries, missing indexes and slow endpoints. CX Codex +1 65,200installs supabase official supabase Guides the agent through database configuration and strict RLS policies in Supabase. CX Codex GP ChatGPT 8installs

From the same set159

get-available-resources This skill inspects CPU, memory, disk, scheduler, container and accelerator limits for the current process. Use it before planning a resource-sensitive local workload. CX Codex +1 2,000installs matlab A skill for designing and reviewing numerical code in MATLAB and GNU Octave. Useful when you need to inspect a stranger's .m file or prepare a reproducible project. CX Codex +1 2,000installs market-research-reports Builds evidence-traceable market reports and models assumption-driven TAM, SAM, and SOM forecast scenarios. CX Codex +1 2,000installs infographics Turns your data into a PNG infographic through Nano Banana 2, then scores the result against a quality threshold. Handy when a report needs a picture instead of another table. CX Codex +1 2,000installs shap Guides AI agents in explaining and auditing machine learning predictions with SHAP. Useful for selecting explainers, checking additivity, and rendering attribution plots. CX Codex +1 2,000installs pyzotero Manages Zotero libraries through the pyzotero Python client: search references, edit records, handle collections, tags, and attachments. Use it for bibliography automation. CX Codex +1 2,000installs transformers A skill that walks your agent through Hugging Face Transformers: pulling checkpoints from the Hub, running pipeline inference, generating text and fine-tuning with Trainer. CX Codex +1 2,000installs generate-image Generates and edits images via OpenRouter Image API using Gemini, Recraft, and Seedream. Ideal for artwork, logos, concept art, and editing reference images. CX Codex +1 2,000installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor