lpantano / lpantano/myself

[Scientists] A Lab-Scale Pipeline Factory: Agentic Infrastructure for Nextflow Development

Open
#82 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

audience:scientists stage:social-media-ready
Dominant language
Astro
Stars
0
Forks
0
PR merge metrics
No merged PRs in 30d

Description

Topic Overview

Architecture walkthrough from Nextflow Summit 2026. How one bioinformatician used AI agents (Trinity orchestrator + sub-agents) to eliminate pipeline development bottlenecks in a lab where one person handles every role.

Key Points to Cover

  • Three-tier architecture: agents, skills, commands
  • Trinity's 6-phase flow with parallelism and sequential gates
  • docker-resolve skill (3-check container lookup)
  • Memory system (.memory/ files encoding lab conventions)
  • Hard rules learned from failures (never pre-supply container, spawn once, context is the product)
  • Permissions / blast radius bounding

Potential Sources

  • Nextflow Summit 2026 presentation
  • Anthropic Claude Agent SDK docs

Target Publication Date

2026-05-01

Notes

Content is social-media-ready. Folder: content-workflow/social-media-ready/2026-05-01-agentic-nextflow-pipeline-factory/

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Work in content-workflow/social-media-ready/2026-05-01-agentic-nextflow-pipeline-factory/. Start by reviewing the Nextflow Summit 2026 presentation and Anthropic Claude Agent SDK docs, then cover the listed architecture, workflow, memory, container lookup, and permissions topics. Done means the social-media-ready content is complete for the 2026-05-01 publication date.

Written by the indexing model from the issue text.

Assessment

Domain
content
Issue type
Documentation
Difficulty
3/5
Estimated time
1-2 days
Activity status
Quiet
Clarity
Clearly specified
Newbie friendliness
52/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.