Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

DNAnexus Integration

Gives Claude Code verified know-how for running DNAnexus genomics data, apps, and workflows via the dx CLI and dxpy.

AutomationAdvanced★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

Turns Claude Code into a careful DNAnexus operator with correct, version-checked platform semantics:

  • dx CLI: login, project selection, uploads/downloads including Upload/Download Agent for large files
  • dxpy Python SDK: object search (find_data_objects with name_mode="glob"), job chaining with get_output_ref(), error handling
  • dxapp.json authoring plus an offline validator script, applet/app build and publication
  • Job and analysis monitoring (dx watch, dx find executions), retries, and --cost-limit controls
  • Native workflows, WDL/CWL through dxCompiler, and Nextflow imports

The standout is the Operating Contract: start read-only, confirm before billable or destructive actions, never print DX_SECURITY_CONTEXT or API tokens, and respect PHI/TRE and org policies.

Who it's for

  • Bioinformaticians and platform engineers running genomics pipelines on DNAnexus
  • Teams building and publishing internal applets/apps
  • Regulated-data teams that must avoid accidental deletion, runaway spend, or token leakage
  • Anyone porting WDL/CWL/Nextflow pipelines onto the platform

Examples

  1. Data inventory: "List closed BAM files under /results in project-xxxx with their archival state" → produces a correct dxpy.find_data_objects() call with glob name mode and bounded limits.
  2. App development: "Validate this dxapp.json and modernize it for Ubuntu 24.04" → runs the offline validator, flags deprecated runSpec.systemRequirements, and moves settings into regionalOptions.
  3. Operations: "Find jobs that failed in the last 2 hours, show logs, then rerun with a $25 cap" → dx find jobs --state failed, dx watch, then dx run --cost-limit 25 after explicit confirmation.

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/dnanexus-integration folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/dnanexus-integration/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/dnanexus-integration ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and clone the skills repository: 
    git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  2. Create the Claude Code skills folder and copy this skill in: 
    mkdir -p ~/.claude/skills
cp -r scientific-agent-skills/skills/dnanexus-integration ~/.claude/skills/
  3. Install the DNAnexus toolkit (Python 3.11+ required): 
    uv tool install "dxpy==0.410.0"   # or: pip install dxpy
dx --version
  4. Authenticate and pick your working project: 
    dx login
dx whoami && dx select
  5. Restart Claude Code and try a read-only prompt such as "list the files in my DNAnexus project" to confirm the skill loads.
  6. Never paste API tokens into chat or logs; in automation, inject the token from a secret manager environment variable only.
View source on GitHub ↗License: MIT