delphine-l-claude-global

You are helping to reorganize a Galaxy export workflow to make it more visually clear and user-friendly.

Prepare a Galaxy workflow for IWC submission (release version, cleanup, validation)

Switch to a VGP workflow directory and branch. Usage: /switch-workflow VGP8

Smart backup system with skill integration. Setup on first run, then daily/milestone backups with intelligent cleanup.

Reference file for the `/backup` command. Contains the full `backup_project.sh` script template generated during setup.

Reference file for the `/backup` command. Covers execute mode details, expected output format, error handling, and integrations.

Reference file for the `/backup` command. Covers the documentation created during setup and the confirmation message.

End-of-project cleanup - removes working documentation and condenses verbose READMEs for files changed in current git branch

Show help and documentation for Claude Code commands. Usage: /command-help [command-name]

Consolidate session notes, update project status, and archive processed notes with AI-powered analysis

Use Python to read, analyze, and extract information from session notes:

```python

- Executive summary of project progress

```python

Deprecate files by moving them to deprecated/ folder, recursively handling dependencies, and updating MANIFESTs

Python code for detecting file dependencies during deprecation. This module identifies files that were used to create the target file, organized by file type.

Find and update affected MANIFESTs after moving files to deprecated/.

```bash

Templates created when the `deprecated/` directory is first initialized.

Code for checking whether dependencies are still used by active files, and building the deprecation tree.

Collaborative design and planning workflow for complex tasks. Brainstorm approaches, create a structured implementation plan, then execute. Use for new tools, analysis strategies, major refactors — anything that benefits from thinking before doing.

Generate or update MANIFEST.md file inventories for project navigation and context efficiency

List all available skills in $CLAUDE_METADATA with descriptions

Smart session startup - read MANIFEST, select a task, load relevant context for current work

Save session notes to Obsidian, update skills with session knowledge, then clear context to continue working

Supporting file for `/safe-clear` command. Contains detailed interaction examples.

Supporting file for `/safe-clear` command. Contains detailed Obsidian setup, note templates, and file creation logic.

Supporting file for `/safe-clear` command. Contains command flags, error handling, and integration details.

Safely end Claude Code session with backup and Obsidian session summary prompts

> Supporting file for `/safe-exit` command. See `commands/global/safe-exit.md` for the main workflow.

> Supporting file for `/safe-exit` command. See `commands/global/safe-exit.md` for the main workflow.

> Supporting file for `/safe-exit` command. See `commands/global/safe-exit.md` for the main workflow.

Plan and set up the best Python environment type (venv or conda) for the current project

Set up Claude Code skills for a new project

Prepare organized project package for sharing with collaborators, reviewers, or repositories. Creates clean copies at different levels (Summary/Reproducible/Full).

**ONLY execute this step if `ABRIDGE_MODE=true`** (user selected 'yes' in Step 2)

```bash

**NEW WORKFLOW: Flexible file organization with MANIFEST intelligence**

**This step runs ONLY if MANIFEST files exist** (`HAVE_MANIFESTS=true`)

**CRITICAL:** After copying files, verify that all file references in notebooks point to the correct locations in the sharing package structure.

1. **Run full analysis** to ensure everything works

```python

Sync project with $CLAUDE_METADATA - detect new skills/commands to symlink

**Use these indicators to recommend skills:**

```

```

Quick-update existing MANIFEST.md files preserving user content - faster than full regeneration

Comprehensive Jupyter notebook maintenance - updates figures, verifies references, updates TOC, checks coherence

Supporting file for the `update-notebook` command. Contains Steps 7-9: interactive update menu, executing updates, and post-update validation.

Supporting file for the `update-notebook` command. Contains Steps 10-11: saving the notebook, generating a summary, plus token efficiency tips, example usage, safety features, and usage guidance.

Supporting file for the `update-notebook` command. Contains Steps 5-6: table of contents update and figure legend validation.

Supporting file for the `update-notebook` command. Contains Steps 2-4: pre-update analysis, figure reference validation, and data coherence checks.

Review session and suggest skill updates to $CLAUDE_METADATA

Check status of all VGP workflows

Debug failed workflows for a species

Analyze and optimize Claude Code token usage

Set up cron job for automated workflow monitoring

Review session and suggest skill updates

Publication-quality bioinformatics figures - phylogenetic trees, genome browsers, iTOL datasets, and data presentation

Best practices for using Claude Code in team environments. Covers skill management, knowledge capture, version control, and collaborative workflows.

Best practices for session documentation - incremental summaries, fix reports, and audit trails

Expert guide for managing Claude Code global skills and commands. Use when creating new skills, symlinking to projects, updating existing skills, or organizing the centralized skill repository.

Structured 4-phase debugging methodology. Use when encountering any bug, test failure, unexpected behavior, or pipeline error — before proposing fixes. Enforces root cause investigation first.

Token optimization best practices for cost-effective Claude Code usage. Automatically applies efficient file reading, command execution, and output handling strategies. Includes model selection guidance (Opus for learning, Sonnet for development/debugging). Prefers bash commands over reading files.

Enforces evidence-based completion claims. Use before claiming work is done, tests pass, or bugs are fixed. Requires running verification commands and confirming output before any success claims.

HackMD collaborative markdown - slide presentations, embedded SVG diagrams, and real-time editing best practices

Best practices for data aggregation, recalculation, and category management in scientific analyses. Covers when to recalculate vs reuse aggregated data, handling category changes, and ensuring analytical accuracy.

Best practices for creating clear, accurate scientific visualizations with matplotlib, seaborn, and other Python plotting libraries. Covers common pitfalls, optimization techniques, publication-quality figure generation, and Claude API image size constraints.

Organize research project documentation - structure working files, prepare sharing packages, maintain clean project layout

Best practices for creating comprehensive Jupyter notebook data analyses with statistical rigor, outlier handling, and publication-quality visualizations. Includes Claude API image size helpers.

Best practices for iterative refinement of publication-quality scientific figures. Covers systematic improvement workflows, layout optimization, and ensuring all figure elements are publication-ready.

Prepare organized packages of project files for sharing at different levels - from summary PDFs to fully reproducible archives. Creates copies with cleaned notebooks, documentation, and appropriate file selection. After creating sharing package, all work continues in the main project directory.

Smart automated backup system with skill integration. Detects project type (notebooks, data files, HackMD docs) and applies appropriate cleanup before backup. Rolling daily backups, compressed milestones, and CHANGELOG tracking.

Core bioinformatics concepts including SAM/BAM format, AGP genome assembly format, sequencing technologies (Hi-C, HiFi, Illumina), quality metrics, and common data processing patterns. Essential for debugging alignment, filtering, pairing issues, and AGP coordinate validation.

Phylogenetic tree analysis, visualization, annotation management, and iTOL troubleshooting

Unified Python interface to 40+ bioinformatics services (UniProt, KEGG, ChEMBL, Reactome, PSICQUIC). Best for cross-database analysis, ID mapping, and multi-service workflows. For quick single-database lookups use gget.

Fast CLI/Python queries to 20+ bioinformatics databases. Gene info, BLAST, AlphaFold structures, enrichment analysis, single-cell data, disease associations. Best for interactive exploration and quick lookups. For batch/multi-database Python workflows use bioservices.

Query gnomAD (Genome Aggregation Database) for population allele frequencies, variant constraint scores (pLI, LOEUF), and loss-of-function intolerance via GraphQL API. Essential for variant pathogenicity interpretation, rare disease genetics, and identifying loss-of-function intolerant genes.

BioBlend and Planemo expertise for Galaxy workflow automation. Galaxy API usage, workflow invocation, status checking, error handling, batch processing, and dataset management. Essential for any Galaxy automation project.

Expert in Galaxy tool wrapper development, XML schemas, Planemo testing, and best practices for creating Galaxy tools

Expert in Galaxy Training Network (GTN) tutorial development. GTN markdown syntax, special boxes, tool references, snippets, YAML front matter, and best practices for writing and updating training materials in the galaxyproject/training-material repository.

Expert in Galaxy workflow development, testing, and IWC best practices. Create, validate, and optimize .ga workflows following Intergalactic Workflow Commission standards.

Expert in building and testing conda/bioconda recipes, including recipe creation, linting, dependency management, and debugging common build errors

Best practices for organizing project folders, file naming conventions, and directory structure standards for research and development projects

Best practices for managing development environments including Python venv and conda. Always check environment status before installations and confirm with user before proceeding.

Integration with Obsidian vault for managing notes, tasks, and knowledge when working with Claude. Supports adding notes, creating tasks, and organizing project documentation. Updated with 2025-2026 best practices including MOCs, properties, practical organization patterns, and Obsidian CLI (1.12+).

Access and navigate GenomeArk AWS S3 bucket - VGP assemblies, QC data, and species directory structure

VGP assembly pipeline - Galaxy workflow selection, execution patterns, QC checkpoints, and batch orchestration