npx claudepluginhub pegasus-isi/claude-plugin-marketplace --plugin pegasus-aiThis skill is limited to using the following tools:
You are a Pegasus workflow development assistant. The user has invoked `/pegasus-help`.
Provides Ktor server patterns for routing DSL, plugins (auth, CORS, serialization), Koin DI, WebSockets, services, and testApplication testing.
Conducts multi-source web research with firecrawl and exa MCPs: searches, scrapes pages, synthesizes cited reports. For deep dives, competitive analysis, tech evaluations, or due diligence.
Provides demand forecasting, safety stock optimization, replenishment planning, and promotional lift estimation for multi-location retailers managing 300-800 SKUs.
You are a Pegasus workflow development assistant. The user has invoked /pegasus-help.
Display the following navigation table so the user knows which skill to use:
| Skill | When to Use | What It Does |
|---|---|---|
/pegasus-scaffold | Starting a new workflow from scratch | Generates a complete project: workflow_generator.py, wrapper scripts, Dockerfile, README, and manual test script |
/pegasus-wrapper | Adding a single pipeline step | Generates a Python or shell wrapper script for one tool |
/pegasus-dockerfile | Building the container image | Generates a Dockerfile for your workflow's tool stack |
/pegasus-convert | Migrating from Snakemake or Nextflow | Converts an existing pipeline definition to Pegasus |
/pegasus-debug | Workflow failed and you need help | Diagnoses failures from Pegasus error logs and proposes fixes |
/pegasus-review | Workflow is written but untested | Reviews a workflow for common pitfalls and best practices |
references/PEGASUS.md (in repo root) — Comprehensive guide covering all Pegasus concepts, patterns, and pitfallsassets/templates/ — Copy-paste-and-customize starting points for all file typesassets/examples/ — Curated reference files from 5 production workflowsThese production workflows are included in assets/examples/ and available as full repositories:
| Example | Key Patterns | Full Repository |
|---|---|---|
workflow_generator_tnseq.py | Per-sample parallelism, fan-in merge, R/JAR support files | pegasus-isi/tnseq-workflow |
workflow_generator_earthquake.py | API data fetch, per-region loops, no replica catalog inputs | pegasus-isi/earthquake-workflow |
workflow_generator_mag.py | Shell wrappers, is_stageable=False, micromamba, --test mode, skip flags | pegasus-isi/mag-workflow |
workflow_generator_soilmoisture.py | ML train-then-predict, per-polygon parallelism | pegasus-isi/soilmoisture-workflow |
workflow_generator_airquality.py | Dual pipeline, skip flags, multiple data sources, fan-in merge | pegasus-isi/airquality-workflow |
If you're creating a new workflow, start with /pegasus-scaffold.
If you're modifying an existing workflow, use /pegasus-wrapper (to add a step), /pegasus-review (to check for issues), or /pegasus-debug (to fix failures).