Claude Code plugins for autonomous development workflows
stellarshenson/claude-code-plugins
Skill Claude CodeCodex
Autonomous build iteration orchestrator. Runs structured improvement cycles with multi-agent review. Use when asked to iterate, improve, fix bugs, refactor, run GC, implement features, do quality improvement, run cleanup, or execute structured development cycles. Phases - research, hypothesis, plan, implement, test…
stellarshenson/claude-code-plugins
Skill Claude CodeCodex
Write a BENCHMARK.md with measurable evaluation criteria through iterative dialogue. Pushes for programmatic metrics over subjective checklists. Invoked after program-writer, before workflow execution.
stellarshenson/claude-code-plugins
Skill Claude CodeCodex
Write a PROGRAM.md file through iterative dialogue with the user. Asks clarifying questions, proposes work items, refines based on feedback until the user approves. Invoked before workflow execution.
stellarshenson/claude-code-plugins
Skill Claude CodeCodex
Run the autobuild orchestrator for structured improvement cycles.
stellarshenson/claude-code-plugins
Skill Claude CodeCodex
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.
stellarshenson/claude-code-plugins
Skill Claude CodeCodex
Add or fix footnotes in a notebook or markdown file using Jupyter-compatible anchor pattern.
stellarshenson/claude-code-plugins
Skill Claude CodeCodex
Add or fix progress bars in a notebook or script - choose classic (tqdm) or modern (rich) style.
stellarshenson/claude-code-plugins
Skill Claude CodeCodex
Apply rich output styling standards to a notebook or script - fix colors, formatting, print patterns.
stellarshenson/claude-code-plugins
Skill Claude CodeCodex
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 opts into.
stellarshenson/claude-code-plugins
Skill Claude CodeCodex
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.
stellarshenson/claude-code-plugins
Skill Claude CodeCodex
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 spec and re-rendered from…
stellarshenson/claude-code-plugins
Skill Claude CodeCodex
Fix a notebook to comply with all standards - structure, styling, progress bars, header narrative.
stellarshenson/claude-code-plugins
Skill Claude CodeCodex
Port an existing project to copier-data-science standards or update an existing copier project.
stellarshenson/claude-code-plugins
Skill Claude CodeCodex
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.
stellarshenson/claude-code-plugins
Skill Claude CodeCodex
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 experiment…
stellarshenson/claude-code-plugins
Skill Claude CodeCodex
Create a new data science project from copier template.
stellarshenson/claude-code-plugins
Skill Claude CodeCodex
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…
stellarshenson/claude-code-plugins
Skill Claude CodeCodex
Create a new Jupyter notebook with proper structure, styling, and progress bars.
stellarshenson/claude-code-plugins
Skill Claude CodeCodex
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. Use whenever a source is cited in a design / experiment / hypothesis /…
stellarshenson/claude-code-plugins
Skill Claude CodeCodex
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 empirical claim…
stellarshenson/claude-code-plugins
Skill Claude CodeCodex
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.
stellarshenson/claude-code-plugins
Skill Claude CodeCodex
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.
stellarshenson/claude-code-plugins
Skill Claude CodeCodex
Review a notebook or script for compliance with data science standards.
stellarshenson/claude-code-plugins
Skill Claude CodeCodex
Update a prompt, system instruction, or agent definition by applying a research-backed prompt engineering technique.