galaxyproject

Carry an existing Galaxy workflow's tests forward as a regression baseline and augment them for a change-set's deltas, emitting a Galaxy test plan.

Triage failing Galaxy run outputs; classify the failure surface and capture evidence before recommending repairs.

Synthesize a Galaxy workflow test plan from a free-form summary and the Galaxy design briefs.

Assemble Galaxy workflow test fixtures and assertions.

Execute a workflow's tests via Planemo; emit structured pass/fail and outputs.

Convert one nf-core module dir into a Galaxy tool wrapper (tool.xml + macros.xml + _provenance.yml + remote-URL <test> blocks).

Path from a CWL Workflow to a Galaxy gxformat2 workflow — orchestrates the Foundry skills of the CWL → GALAXY pipeline in order, in a per-run working directory.

Interview-driven path to a Galaxy gxformat2 workflow through the shared freeform-summary handoff — orchestrates the Foundry skills of the INTERVIEW → GALAXY pipeline in order, in a per-run working directory.

Use when authoring a Galaxy User-Defined Tool (UDT) -- a `class: GalaxyUserTool` YAML definition that wraps a container and command into a tool a non-admin user creates and runs (e.g. via Galaxy MCP create_user_tool / run_user_tool, or POST /api/unprivileged_tools). Not for classic XML/ToolShed tool wrappers.

Use this skill when asked to create, draft, or write a Galaxy workflow report template for the Workflow Editor's Report tab. Triggers on requests like "create a report for this workflow", "draft a workflow report template", "write a Galaxy report for workflow <id/url>".

Galaxy Collection Transformation Command - transform Galaxy dataset collections reproducibly using Galaxy's native tools. Use when asked to filter, sort, relabel, restructure, flatten, nest, merge, or otherwise manipulate Galaxy collections.

Galaxy MCP server tools reference for histories, datasets, tools, and workflows

Router for Galaxy MCP, JupyterLite notebooks, and BioBlend automation

Building UCSC Track Hubs (track hubs and assembly hubs) — bigBed/bigChain/bigMaf format requirements, composite-track rules, hub.txt / genomes.txt / trackDb.txt structure. Use when emitting a UCSC hub from Galaxy outputs, wrapping a hub-publishing tool, or debugging hubCheck failures.

Galaxy tool development reference — creating new tools, testing, IUC review preparation, and updating existing tools. Use when authoring or modifying Galaxy tool wrappers for tools-iuc.

Generate a tool selection flowchart diagram (PNG) for a Galaxy tool suite from a JSON definition. Use when creating visual guides that help users pick the right tool in a multi-tool suite.

Generate Galaxy-branded workflow visualization SVGs for IWC workflows. Creates static diagrams matching Galaxy's workflow editor style with bezier connections, node cards, and proper terminal positioning. Use when creating visual diagrams for workflows in this repository.

Use when cutting a release of galaxyproject/galaxy-mcp -- bumping the version and publishing the galaxy-mcp package to PyPI. Triggers include "cut a galaxy-mcp release", "release galaxy-mcp", "ship galaxy-mcp X.Y.Z", or /release.

Use when cutting a release of galaxyproject/loom -- tagging a new version that publishes the @galaxyproject/loom npm package and builds the Orbit desktop installers. Triggers include "cut a release", "ship 0.x", "release loom", or /release.

Convert Scribe markdown export into a tutorial page under /learn/getting-started. Use when the user pastes Scribe-exported markdown and wants it turned into a site page.

Cut a pulsar-relay server and/or pulsar-relay-client release. Drives the top-level Makefile (release-* targets) to bump the relevant pyproject(s), draft the CHANGELOG entry, open the release-prep PR, then fire the matching tag(s) to publish via PyPI trusted publishing and (for the server) push the multi-arch image to ghcr.io. Supports both lockstep releases (server + client at the same version) and component-only releases. Use when the user asks to "cut a release", "release X.Y.Z", or "ship a server/client patch".

Review a Foundry site's rendered content pages against their source files for capture/render fidelity, metadata surfacing, clean markup, and working links — checking each page reads well for BOTH humans and agents. NOT a content-correctness review. Use when reviewing changed content, a named page, or a URL.