- Home
- Skills
- Workflow Automation
- dependency upgrade
dependency upgrade
Generates a risk-aware dependency upgrade plan by analyzing lockfile graphs and transitive blast radius.
$5
Works with the AI tools you already use
dependency upgrade
Example session with this skill installed
Analyze my package-lock.json and outdated.json to create a safe upgrade plan. Identify duplicates and high-risk packages.
- Read your context and instructions
- Compiled the dependency upgrade
Plan generated
- Batch 1 (Patches): 12 packages. Low risk.
- Batch 2 (Minors): 4 packages (e.g., lodash).
- Batch 3 (Majors): 2 packages. Isolation recommended.
Found 3 duplicates for 'react-is'. Most entangled: 'webpack' (Blast radius: 42).
Connects securely to your tools. The creator never sees your data.
What you get
About this skill
The problem
Running a standard outdated check tells you what needs updating, but not how to do it safely. Blindly upgrading everything at once leads to broken builds, while manual triage wastes hours checking dependency graphs and changelogs.
What it does
- Analyzes lockfiles to build a full transitive dependency graph and compute the blast radius for every package.
- Groups upgrades into three distinct batches based on SemVer risk levels: patch, minor, and major.
- Identifies duplicate transitive versions that cause bloated bundles and state-management bugs.
- Calculates which packages are most "entangled" to prioritize isolated testing for high-impact changes.
Frameworks & tools
Supports Node.js (package-lock.json v1, v2, v3) and Python (requirements.txt). Built with Python 3.8+ using standard library only.
Why this beats prompting it yourself
General LLMs cannot accurately parse large, complex JSON lockfiles to calculate transitive dependencies or identify graph cycles without hallucinating connections. This tool performs deterministic graph analysis to ensure your upgrade plan is based on the actual architecture of your project, not a guess.
Use cases
- Planning a quarterly dependency maintenance sprint for a large monorepo.
- Identifying and collapsing duplicate library versions to reduce bundle size.
- Determining the safest order of operations for a major framework migration.
- Reviewing a security audit to see which CVE fixes carry the highest breaking risk.
Known limitations
Python requirements.txt analysis lacks graph data, so blast radius calculations are unavailable for that format. The graph analysis requires a lockfile to function offline.
How to install
Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.
- 1
Download the ZIP
Free skills download straight away. Paid skills unlock right after purchase.
- 2
Unzip into your skills folder
Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.
- 3
Ask your agent to use it
Restart the agent if it was already running. It picks the skill up automatically - no config needed.
Skills folder by agent
Click the path to copy it. Create the folder if it does not exist yet.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean 1 month ago
- Passed all security checks, Safe to install