← all publishers

MusserLab

@musserlab source repo

Report this profile Claim this profile

• 26 skills
• 0 followers
• 1 week ago last updated

1. ▌
   Cleanup Scripts · musserlab

   Session-scoped script cleanup for data science projects. Checks scripts/scratch/ for working files that need consolidation into .qmd scripts, flags numbered non-.qmd files in scripts/, and verifies script-output directory correspondence. Use when finishing a coding session, when scripts/scratch/ has accumulated files, or when the user says "clean up scripts", "consolidate scratch", or "check script conventions". Lightweight and fast — reads files, no expensive computation.
   0 installs
2. ▌
   Git Conventions · musserlab

   Git commit practices and conventions. Use when committing changes, writing commit messages, creating branches, or making PRs.
   0 installs
3. ▌
   Plugin Feedback · musserlab

   File a suggestion, bug report, or new-skill idea about the lab-claude-skills plugin as a GitHub issue on MusserLab/lab-claude-skills. Use when the user hits a limitation in a lab skill, says a skill did something wrong or didn't activate, wants to suggest a skill improvement or a new skill, or says "file a plugin issue", "report this skill", "suggest a skill", or invokes /plugin-feedback. Also invoked when Claude offers to capture skill friction per the general-reminders standing instruction. Do NOT load for the student-feedback / feedback-walkthrough advisor-feedback workflow, or for filing issues on a user's own project repo (use gh directly for those).
   0 installs
4. ▌
   Tree Formatting · musserlab bundle

   Phylogenetic tree visualization and formatting with ggtree (R) or iTOL (web). Use when rendering a phylogenetic tree as a figure, choosing tree layout, coloring branches or labels by taxonomy, collapsing clades, displaying support values, or adding overlays to a tree. Do NOT load for tree inference (use protein-phylogeny skill) or domain annotation (future separate skill).
   0 installs
5. ▌
   Pipeline Diagram · musserlab bundle

   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 input files -> key params/decisions -> output files). Use when the user wants to diagram, visualize, map, or document an analysis/processing pipeline or multi-script workflow; create a pipeline figure / schematic / flow diagram; or show/communicate the steps, key decisions, and input/output files of a pipeline. Spec-driven by design (you write a short YAML, not auto-parsed from code). Do NOT load for the analysis RESULT figures themselves (networks, heatmaps, trees), for generic flowcharts unrelated to a data pipeline, or for Quarto/script scaffolding (use script-organization).
   0 installs
6. ▌
   Expression Report · musserlab bundle

   Generate single-cell gene expression report scripts (.qmd) with barplots, heatmaps, and cross-analysis. Use when creating expression reports for gene sets across cell types, visualizing gene expression patterns in single-cell data, or when the user says "expression report", "gene expression barplots", "expression heatmap", or wants to visualize how a gene list is expressed across cell types. Covers both categorical gene groupings (pathway components, functional categories) and data-driven groupings (taxonomy, coexpression modules). Currently Python/scanpy/matplotlib only. Do NOT load for differential expression testing, marker gene discovery, or clustering — those are upstream analyses that produce gene lists this skill consumes.
   0 installs
7. ▌
   Protein Phylogeny · musserlab

   Protein (gene) phylogeny inference pipeline: generates a .qmd analysis script that performs alignment, optional trimming, and tree building. Use when building phylogenetic trees from protein sequences, aligning protein families, running IQ-TREE or MAFFT for phylogenetics, or when the user says "gene tree" or "protein tree." Covers single domains, whole proteins, and multi-domain proteins across deep evolutionary distances (sponges, animals, eukaryotes). Do NOT load for nucleotide-only phylogenies, species trees from concatenated matrices, or tree visualization (use tree-formatting skill for that).
   0 installs
8. ▌
   Quarto Book Setup · musserlab

   Initialize a new Quarto book project with GitHub Pages. Use when creating a new documentation site, tutorial, or book.
   0 installs
9. ▌
   Script Organization · musserlab

   Script organization for data science analysis projects with numbered scripts, data/outs/ directories, and reproducibility conventions. Use when creating new analysis scripts in projects that follow data science conventions (numbered XX_ prefix scripts, outs/ directories, BUILD_INFO.txt). Do NOT load for documentation projects (Quarto books), infrastructure repos, or projects without data/outs/ directory structure.
   0 installs
10. ▌
    Feedback Walkthrough · musserlab

    Walk a student through feedback their advisor left on their project — pedagogically, one item at a time, so the student understands and acts on it themselves. Use when a student wants to go through advisor/PI feedback, work through a feedback issue (a GitHub issue labelled `feedback`) or a feedback doc (docs/feedback/*.md), or says "walk me through the feedback", "go through Jacob's feedback", or "help me with my feedback". This is the student side; the advisor authors it with the student-feedback skill.
    0 installs
11. ▌
    Deep Research Reports · musserlab bundle

    Process deep research report outputs for scRNAseq cell type annotation and non-metazoan gene characterization. Use when the user invokes /process-deep-research or asks to clean, convert to PDF/HTML, parse, or compile deep research reports from ChatGPT or Claude. Handles artifact removal, PDF/HTML generation, YAML header extraction, and summary table maintenance. Supports five report types detected from query.report_type: cluster-level cell-type-annotation, legacy family cell-type-annotation, family_report1 (WGCNA-module family-level pipeline), family_report2 (per-triage-group cluster-level), and nonmetazoan characterization. Works on both local macOS and HPC cluster (auto-detects quarto path and LaTeX availability).
    0 installs
12. ▌
    Hpc · musserlab bundle

    Use for the Musser Lab's Yale YCRC HPC clusters (McCleary, Bouchet, Misha) when writing SLURM batch scripts, configuring job resources, or for ANY question about cluster storage — quotas, PI/project/scratch/home space, shared data or database folders, Palmer vs Gibbs, /vast vs /gpfs vs /nfs, or purge policy. Also use when running bioinformatics tools on HPC, setting up Snakemake pipelines, managing the cluster software environment (module load vs conda, conda envs, renv on HPC), transferring data to or from the cluster (rsync, scp, Globus, between-cluster transfer), or retrieving YCGA sequencing data (ycgaFastq, URLFetch, archived/Glacier fastq retrieval, the -p ycga partition). Also use when connecting to the cluster remotely or running Claude Code on a compute node (SSH setup, Positron/VS Code Remote SSH, interactive sessions, "Claude Code on the cluster", Duo 2FA + ControlMaster connection multiplexing, Windows/WSL vs macOS/Linux remote setup). Covers lab-specific storage paths, partition tables, and tool
    0 installs
13. ▌
    Done · musserlab

    Use when ending a session, wrapping up work, or when the user says "done", "wrap up", "let's commit", or "end of session". Summarizes work, updates docs, and commits.
    0 installs
14. ▌
    Handoff · musserlab bundle

    Coordinate handoff between local (macOS) and cluster (Bouchet) Claude Code sessions for the same project. Use when the user mentions switching machines ("continuing locally", "switching to cluster", "back on the laptop", "I'll work on the other one"), pastes a `git status` from the other side, or when Claude is about to give cross-machine instructions involving rsync, `git push`+`git pull`, `/sync-project`, or `/sync-cluster`. Enforces a strict departure → gate → arrival sequence with multi-chat awareness — pending work in the working tree or unpushed commits may belong to other parallel chats and must NOT be silently swept up. Always write an explicit "DO NOT start work on arrival side yet" gate before any arrival instructions. Do NOT load for single-machine work, regular `/done` wrap-ups within one machine, or git questions unrelated to cross-machine coordination.
    0 installs
15. ▌
    New Plan · musserlab

    Use when starting multi-script or multi-session work that needs tracking, or when the user invokes /new-plan. Creates a planning document and registers it in the project CLAUDE.md.
    0 installs
16. ▌
    Conda Env · musserlab

    Conda environment activation for Python commands. Use when running Python scripts, pip, or conda-dependent tools.
    0 installs
17. ▌
    New Skill · musserlab

    Create a new Claude Code skill with proper structure and effective description. Use when creating a new skill, or when the /done skill proposes a new skill and the user approves. Also use when refactoring CLAUDE.md content into a skill.
    0 installs
18. ▌
    Learn Code · musserlab

    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 reasoning as an integrated practice. Do NOT load for quick "what does this function do" questions — only for structured walkthroughs of script sections or whole scripts.
    0 installs
19. ▌
    New Project · musserlab bundle

    Use when creating a new project, setting up a project from scratch, or when the user invokes /new-project. Scaffolds directory structure, environments, git, and Claude Code configuration. Supports data science, documentation, and general project types.
    0 installs
20. ▌
    Quarto Docs · musserlab bundle

    Quarto document conventions for data science analysis scripts (.qmd). Use when creating or rendering .qmd analysis scripts in data science projects with numbered scripts, status fields, git hash capture, and BUILD_INFO.txt. Do NOT load for Quarto books, websites, or documentation projects — those use standard Quarto conventions without numbered script prefixes or BUILD_INFO.txt.
    0 installs
21. ▌
    Audit Script · musserlab bundle

    Systematic audit of data analysis scripts for bugs, analytical reasoning, data handling, style, and reproducibility. Includes domain verification phase that researches tools, file formats, and methods to catch domain-specific errors (not just code bugs). Use when auditing a script, reviewing code for correctness, checking for bugs, preparing a script for publication, or when the user says "audit this script", "review this code", "check this for bugs", or "is this script correct". Three modes: thorough (collaborative section-by-section), fast (Claude-driven with discussion), and report-only. Do NOT load for quick one-off questions about a single line or function.
    0 installs
22. ▌
    Audit Skills · musserlab bundle

    Audit Claude Code skills for bloat, trigger accuracy, structural quality, redundancy, and pruning opportunities. Use when skills feel bloated, before publishing to lab repo, after building several new skills, when reviewing a single newly-created skill before publishing, or when the user says "audit my skills", "review skills", "check skill quality", "audit this skill", or invokes /audit-skills. Covers both user-level (~/.claude/skills/) and project-level (.claude/skills/) skills, and supports both full-library scans and single-skill reviews. Do NOT load for auditing data analysis scripts (use /audit-script) or project documentation (use /audit-project).
    0 installs
23. ▌
    Sync Project · musserlab

    Sync project state when arriving at a new machine (local or cluster). Pulls git, updates conda env from environment.yml, restores renv packages, checks for memory promotion. Use when switching between local and cluster work, starting a session on a different machine, or when the user invokes /sync-project. Do NOT auto-load — this is a deliberate, user-initiated workflow.
    0 installs
24. ▌
    Audit Project · musserlab

    Periodic project health check - cross-check docs, prune conventions, find drift. Use when project documentation feels stale, before milestones, or when CLAUDE.md is getting long. Do NOT load for auditing skills (use /audit-skills) or data analysis scripts (use /audit-script).
    0 installs
25. ▌
    Data Handling · musserlab

    Data handling best practices for R and Python data science analysis scripts. Use when writing data manipulation code, analysis pipelines, or .qmd scripts that process scientific/analytical data (e.g., filtering, joining, normalizing datasets). Do NOT load for general Python scripting, infrastructure code, or configuration management.
    0 installs
26. ▌
    Security Setup · musserlab bundle

    Configure and manage Claude Code security protections for sensitive files, credentials, and data. Use when the user invokes /security-setup to set up or modify protections against unauthorized file access, credential exposure, or sensitive data leaks.
    0 installs