research-core

Plugin research-core from marketplace musser-lab in MusserLab/lab-claude-skills. Commands read from the repo's manifest — 19 days ago.

Skills (25)

• analysis-distillation

  Distill exploratory or complex scientific analysis into the smallest readable workflow that supports a phase review, paper, report, or durable handoff. Use when a settled phase result needs consolidation, or selected results need publication-ready code, a newcomer reproduction route, or a maintained

• analysis-review-dashboard

  Build or refresh a browser dashboard for independently reviewing a scientific analysis, from a short workflow to a branching pipeline. Organize existing evidence into a pipeline overview, scientific task pages and complete script reviews with file and object previews. Use when the user asks for an a

• audit-project

  Review project documentation, authority, navigation and workflow drift; propose careful, reversible consolidation when useful. Use for project health or documentation reconciliation, not script correctness (audit-script) or skill quality (a separate maintainer audit; use plugin-feedback for a studen

• audit-script

  Audit a scientific or data-analysis script, connected workflow, or publication producer for bugs, analytical validity, data handling, reproducibility, outputs, and readability. Use when reviewing code, preparing a substantial phase for scientific discussion, checking collaborator code, or investigat

• cleanup-scripts

  Consolidate scratch or exploratory code from the current work when its retained role is known. Use when the user asks to clean up scripts, when session-owned scratch files need disposition, or when a changed workflow has unclear helper/output ownership. Selecting and simplifying a complete publicati

• conda-env

  Conda environment activation for Python commands. Use when running Python scripts, pip, or conda-dependent tools.

• data-handling

  What to tell the user while working with their data: reporting as you go, verifying join keys, surfacing ambiguities, and which analytical choices to bring them before writing the analysis. Use when writing or editing code that filters, joins, merges, normalizes, subsets or aggregates a dataset, and

• debugging-before-patching

  Systematic debugging and error diagnosis. Use when debugging errors, fixing bugs, diagnosing problems in code or data, or when the user reports something not working.

• done

  Close a session or explicitly scoped worker task when that is the whole message's intent. Quoted wrap-up language, a finished subtask, and commit-then-continue do not trigger closeout. Complete accompanying requested work first, reconcile only affected records and dependency specifications, verify o

• figure-export

  Figure export conventions for publication-quality R figures (PDF/PNG/SVG). Use when saving plots to files, choosing figure formats, setting DPI or dimensions, or exporting ggplot2 or base R figures for manuscripts or Inkscape editing.

• file-safety

  File modification rules to prevent overwriting important files. Use when overwriting existing files, deleting files, or writing to directories that contain important data (data/, outs/). Also applies when moving or renaming files that other scripts depend on.

• git-conventions

  Git commit practices and conventions. Use when committing changes, writing commit messages, creating branches, or making PRs.

• learn-code

  Interactive walkthrough of data analysis scripts for learning. Use when a student asks to understand a script, wants code explained, says "walk me through this", "teach me this script", "explain this code", or "what does this script do". Covers coding mechanics, script organization, and analytical r

• new-plan

  Compatibility name for planning. Use when the user or an existing project instruction invokes new-plan; new references should use planning.

• new-project

  Create a new project or scaffold an empty project directory with the smallest useful structure, instructions, environment specification, Git boundary, and declared work coordination. Use when the user asks to start or set up a project. Do not use to migrate an existing project's authority or impose

• pipeline-diagram

  Generate a publication-style processing-pipeline diagram from a small YAML spec: a flowing-backbone OVERVIEW (steps down a backbone, inputs branching in from the left, key decisions as blue annotations, output files branching right) plus an optional PER-STEP DETAIL view (one card per step showing in

• planning

  Create, shape, extend, or selectively improve a registered plan for substantial work, or create a scientific/data/reference record. Use for /planning, planning consequential work, developing a phase with the user, or recording programme decisions under Plan/Hybrid coordination.

• plugin-feedback

  Draft and, after review, submit research-plugin bugs, compatibility reports or improvements. Use when the user asks to report a plugin problem, or offer a draft when a reproducible plugin failure blocks work. Do not use for advisor feedback authoring or feedback-walkthrough.

• quarto-docs

  Quarto document conventions for data science analysis scripts (.qmd). Use when creating or rendering .qmd analysis scripts in data science projects with numbered scripts and retained outputs. Do NOT load for Quarto books, websites, or ordinary documentation projects.

• r-plotting-style

  R ggplot2 plotting conventions and theme. Use when creating, modifying, or styling ggplot2 plots in R, or when adjusting plot themes, colors, labels, or formatting.

• r-renv

  R renv package management for data science projects. Use when working with renv (renv.lock, renv::restore, renv::snapshot) in R analysis projects. Do NOT load for projects that do not use R or renv.

• research-core-setup

  Help people set up Research Plugins for Claude Code or Codex, choose packages, add packages later, check what is new without changes, update installed Research Plugins, and use or remove adopted agent collaboration instructions. Use for requests such as how do I use these research plugins, set up Re

• script-organization

  Script organization for data science analysis projects: numbered scripts, data/ vs outs/, section layout, dependencies, and producing-state records. Use when creating a new analysis script, deciding where a script or its outputs belong, numbering or splitting scripts, or deciding how a retained run

• security-setup

  Review and configure native agent-client security boundaries for credentials, sensitive data, project source, and retained outputs. Use for a security setup or permissions review. Add a project-specific guard only when a concrete gap remains after native sandboxing and approvals.

• sync-project

  Synchronize an established project's Git state and declared Conda or renv environment when arriving on another workstation or compute host. Use only when the researcher deliberately requests project synchronization or a cross-machine arrival check.

Similar plugins