datascience

Plugin datascience from marketplace stellarshenson-marketplace in stellarshenson/claude-code-plugins. Commands read from the repo's manifest — 3 days ago.

Skills (20)

• adversarial-review

  Hostile independent review by spawning fresh reviewer subagents - invokes the devils-advocate:adversarial-review skill, picking the adversary a data science project needs (data-scientist, architect, popular-science, ux-designer); find, fix, re-confirm clean

• apply-footnotes

  Add or fix footnotes in a notebook or markdown file using Jupyter-compatible anchor pattern

• apply-progressbar

  Add or fix progress bars in a notebook or script - choose classic (tqdm) or modern (rich) style

• apply-style

  Apply rich output styling standards to a notebook or script - fix colors, formatting, print patterns

• challenge

  Apply the psychological prompting challenge - stakes, incentive, competitive framing. Use ONLY when the user explicitly asks for the challenge framing ("challenge me", "apply the challenge", "use competitive framing"); a hard problem alone is not the trigger, because the framing is a style the user

• datascience

  Data science project conventions and standards. Auto-triggered when working with data science projects, notebooks, datasets, ML models, PyTorch, Polars, sklearn, or any data analysis workflow. Applies naming conventions, file format standards, project structure rules, and code patterns.

• dataset

  Acquire public and private datasets into a task folder under the project's external data directory - each corpus lands as a gitignored `dataset-*.zip` archive plus a tracked `dataset-*.md` sidecar recording licence, size, provenance, restrictions and the mapping onto the task, generated from one spe

• fix-notebook

  Fix a notebook to comply with all standards - structure, styling, progress bars, header narrative

• fix-project

  Port an existing project to copier-data-science standards or update an existing copier project

• footnotes

  Markdown footnotes for Jupyter notebooks and markdown files using anchor links and span elements. Auto-triggered when adding references, citations, notes, or footnotes in any markdown context. Works in JupyterLab, GitHub, and standard markdown renderers.

• hypothesis

  Structure and maintain hypothesis-driven research documentation - a canonical append-only experiments log (each hypothesis with a self-contained, independently reproducible experiment setup, prediction, result, verdict) and a SOTA design doc distilling the winners. Use when the user is writing up an

• new-project

  Create a new data science project from copier template

• notebook-standards

  Jupyter notebook structure standards - section order, GPU-by-UUID selection, grouped imports, the configuration render, the semantic colour system (rich output + matplotlib colormaps), Polars-over-pandas dataframes, equations, charting every load-bearing result inline, fine-grained progress bars, ch

• notebook

  Create a new Jupyter notebook with proper structure, styling, and progress bars

• papers

  Paper reference workflow - download every cited paper, article, report or book and write a structured digest (overview, main findings, key takeaways, tags) carrying a resolvable online provenance link into the project's references/papers/ library. The digest is named for the source kind - paper dige

• popular-science

  Write an accessible, well-sourced popular-science article or explainer from technical work - an experiment result, a research finding, a design, a README - for a curious non-specialist. Applies industry best practices: a hook and an early nut graf, the ladder of abstraction (show and tell), every em

• progressbars

  Use this skill when implementing progress bars in Python scripts or notebooks. Covers tqdm (classic) and rich (modern) styles, library configuration, Jupyter compatibility, and completion fixes.

• prompt-engineering

  Apply research-backed prompt engineering techniques to improve LLM output quality. Offers multiple techniques with templates and references. Auto-triggered when crafting system prompts, agent instructions, or LLM prompts.

• review

  Review a notebook or script for compliance with data science standards

• update-prompt

  Update a prompt, system instruction, or agent definition by applying a research-backed prompt engineering technique

Slash commands (15)

• /datascience:adversarial-review

  Hostile independent review by spawning fresh reviewer subagents - invokes the devils-advocate:adversarial-review skill, picking the adversary a data science project needs (data-scientist, architect, popular-science, ux-designer); find, fix, re-confirm clean

• /datascience:apply-footnotes

  Add or fix footnotes in a notebook or markdown file using Jupyter-compatible anchor pattern

• /datascience:apply-progressbar

  Add or fix progress bars in a notebook or script - choose classic (tqdm) or modern (rich) style

• /datascience:apply-style

  Apply rich output styling standards to a notebook or script - fix colors, formatting, print patterns

• /datascience:challenge

  Apply the psychological prompting challenge - stakes, incentive, competitive framing. Use ONLY when the user explicitly asks for the challenge framing ("challenge me", "apply the challenge", "use competitive framing"); a hard problem alone is not the trigger, because the framing is a style the user

• /datascience:dataset

  Acquire a dataset into the project's external data directory - gitignored archive plus tracked licence sidecar generated from one spec - or audit the corpora a project already holds

• /datascience:fix-notebook

  Fix a notebook to comply with all standards - structure, styling, progress bars, header narrative

• /datascience:fix-project

  Port an existing project to copier-data-science standards or update an existing copier project

• /datascience:hypothesis

  Write or update a hypothesis-driven experiments log and its SOTA design doc - record a round, or conclude the design

• /datascience:new-project

  Create a new data science project from copier template

• /datascience:notebook

  Create a new Jupyter notebook with proper structure, styling, and progress bars

• /datascience:papers

  Download every cited paper and write a structured digest into references/papers/ - the paper reference library for a project's design / experiment / hypothesis docs

• /datascience:popular-science

  Create or update an accessible, well-sourced popular-science article or explainer from technical work - hook, nut graf, ladder of abstraction, sourced-and-numbered claims, best-in-class figures, arc-back kicker with conclusions and next steps

• /datascience:review

  Review a notebook or script for compliance with data science standards

• /datascience:update-prompt

  Update a prompt, system instruction, or agent definition by applying a research-backed prompt engineering technique

Similar plugins