Dependency Updater logo

Dependency Updater

OrganizationPopular
softaworks
dependency-updater

Smart dependency management for any language. Auto-detects project type, applies safe updates automatically, prompts for major versions, diagnoses and fixes dependency issues.

Overview

Publishersoftaworks
Repositoryagent-toolkit
Skill namedependency-updater
Stars
2.5K
Forks
226
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by softaworks on GitHub. Read the source before you install it.

Installation

Install the Dependency Updater AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/softaworks/agent-toolkit.git /tmp/agent-toolkit
mkdir -p .claude/skills
cp -r /tmp/agent-toolkit/skills/dependency-updater .claude/skills/dependency-updater
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dependency Updater in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Dependency Updater on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Dependency Updater is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Dependency Updater

Smart dependency management for any language with automatic detection and safe updates.


Quick Start

update my dependencies

The skill auto-detects your project type and handles the rest.


Triggers

TriggerExample
Update dependencies"update dependencies", "update deps"
Check outdated"check for outdated packages"
Fix dependency issues"fix my dependency problems"
Security audit"audit dependencies for vulnerabilities"
Diagnose deps"diagnose dependency issues"

Supported Languages

LanguagePackage FileUpdate ToolAudit Tool
Node.jspackage.jsontazenpm audit
Pythonrequirements.txt, pyproject.tomlpip-reviewsafety, pip-audit
Gogo.modgo get -ugovulncheck
RustCargo.tomlcargo updatecargo audit
RubyGemfilebundle updatebundle audit
Javapom.xml, build.gradlemvn versions:*mvn dependency:*
.NET*.csprojdotnet outdateddotnet list package --vulnerable

Quick Reference

Update TypeVersion ChangeAction
FixedNo ^ or ~Skip (intentionally pinned)
PATCHx.y.zx.y.ZAuto-apply
MINORx.y.zx.Y.0Auto-apply
MAJORx.y.zX.0.0Prompt user individually

Workflow

User Request
┌─────────────────────────────────────────────────────┐
│ Step 1: DETECT PROJECT TYPE                         │
│ • Scan for package files (package.json, go.mod...) │
│ • Identify package manager                          │
├─────────────────────────────────────────────────────┤
│ Step 2: CHECK PREREQUISITES                         │
│ • Verify required tools are installed               │
│ • Suggest installation if missing                   │
├─────────────────────────────────────────────────────┤
│ Step 3: SCAN FOR UPDATES                            │
│ • Run language-specific outdated check              │
│ • Categorize: MAJOR / MINOR / PATCH / Fixed         │
├─────────────────────────────────────────────────────┤
│ Step 4: AUTO-APPLY SAFE UPDATES                     │
│ • Apply MINOR and PATCH automatically               │
│ • Report what was updated                           │
├─────────────────────────────────────────────────────┤
│ Step 5: PROMPT FOR MAJOR UPDATES                    │
│ • AskUserQuestion for each MAJOR update             │
│ • Show current → new version                        │
├─────────────────────────────────────────────────────┤
│ Step 6: APPLY APPROVED MAJORS                       │
│ • Update only approved packages                     │
├─────────────────────────────────────────────────────┤
│ Step 7: FINALIZE                                    │
│ • Run install command                               │
│ • Run security audit                                │
└─────────────────────────────────────────────────────┘

Commands by Language

Node.js (npm/yarn/pnpm)

bash
# Check prerequisites
scripts/check-tool.sh taze "npm install -g taze"

# Scan for updates
taze

# Apply minor/patch
taze minor --write

# Apply specific majors
taze major --write --include pkg1,pkg2

# Monorepo support
taze -r  # recursive

# Security
npm audit
npm audit fix

Python

bash
# Check outdated
pip list --outdated

# Update all (careful!)
pip-review --auto

# Update specific
pip install --upgrade package-name

# Security
pip-audit
safety check

Go

bash
# Check outdated
go list -m -u all

# Update all
go get -u ./...

# Tidy up
go mod tidy

# Security
govulncheck ./...

Rust

bash
# Check outdated
cargo outdated

# Update within semver
cargo update

# Security
cargo audit

Ruby

bash
# Check outdated
bundle outdated

# Update all
bundle update

# Update specific
bundle update --conservative gem-name

# Security
bundle audit

Java (Maven)

bash
# Check outdated
mvn versions:display-dependency-updates

# Update to latest
mvn versions:use-latest-releases

# Security
mvn dependency:tree
mvn dependency-check:check

.NET

bash
# Check outdated
dotnet list package --outdated

# Update specific
dotnet add package PackageName

# Security
dotnet list package --vulnerable

Diagnosis Mode

When dependencies are broken, run diagnosis:

Common Issues & Fixes

IssueSymptomsFix
Version Conflict"Cannot resolve dependency tree"Clean install, use overrides/resolutions
Peer Dependency"Peer dependency not satisfied"Install required peer version
Security Vulnnpm audit shows issuesnpm audit fix or manual update
Unused DepsBloated bundleRun depcheck (Node) or equivalent
Duplicate DepsMultiple versions installedRun npm dedupe or equivalent

Emergency Fixes

bash
# Node.js - Nuclear reset
rm -rf node_modules package-lock.json
npm cache clean --force
npm install

# Python - Clean virtualenv
rm -rf venv
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt

# Go - Reset modules
rm go.sum
go mod tidy

Security Audit

Run security checks for any project:

bash
# Node.js
npm audit
npm audit --json | jq '.metadata.vulnerabilities'

# Python
pip-audit
safety check

# Go
govulncheck ./...

# Rust
cargo audit

# Ruby
bundle audit

# .NET
dotnet list package --vulnerable

Severity Response

SeverityAction
CriticalFix immediately
HighFix within 24h
ModerateFix within 1 week
LowFix in next release

Anti-Patterns

AvoidWhyInstead
Update fixed versionsIntentionally pinnedSkip them
Auto-apply MAJORBreaking changesPrompt user
Batch MAJOR promptsLoses contextPrompt individually
Skip lock fileIrreproducible buildsAlways commit lock files
Ignore security alertsVulnerabilitiesAddress by severity

Verification Checklist

After updates:

  • Updates scanned without errors
  • MINOR/PATCH auto-applied
  • MAJOR updates prompted individually
  • Fixed versions untouched
  • Lock file updated
  • Install command ran
  • Security audit passed (or issues noted)

The skill auto-detects project type by scanning for package files:

File FoundLanguagePackage Manager
package.jsonNode.jsnpm/yarn/pnpm
requirements.txtPythonpip
pyproject.tomlPythonpip/poetry
PipfilePythonpipenv
go.modGogo modules
Cargo.tomlRustcargo
GemfileRubybundler
pom.xmlJavaMaven
build.gradleJava/KotlinGradle
*.csproj.NETdotnet

Detection order matters for monorepos:

  1. Check current directory first
  2. Then check for workspace/monorepo patterns
  3. Offer to run recursively if applicable

Prerequisites

bash
# Install taze globally (recommended)
npm install -g taze

# Or use npx
npx taze

Smart Update Flow

bash
# 1. Scan all updates
taze

# 2. Apply safe updates (minor + patch)
taze minor --write

# 3. For each major, prompt user:
#    "Update @types/node from ^20.0.0 to ^22.0.0?"
#    If yes, add to approved list

# 4. Apply approved majors
taze major --write --include approved-pkg1,approved-pkg2

# 5. Install
npm install  # or pnpm install / yarn

Auto-Approve List

Some packages have frequent major bumps but are backward-compatible:

PackageReason
lucide-reactIcon library, majors are additive
@types/*Type definitions, usually safe

Semantic Versioning

MAJOR.MINOR.PATCH (e.g., 2.3.1)

MAJOR: Breaking changes - requires code changes
MINOR: New features - backward compatible
PATCH: Bug fixes - backward compatible

Range Specifiers

SpecifierMeaningExample
^1.2.3Minor + Patch OK>=1.2.3 <2.0.0
~1.2.3Patch only>=1.2.3 <1.3.0
1.2.3Exact (fixed)Only 1.2.3
>=1.2.3At leastAny >=1.2.3
*AnyLatest (dangerous)

Recommended Strategy

json
{
  "dependencies": {
    "critical-lib": "1.2.3",      // Exact for critical
    "stable-lib": "~1.2.3",       // Patch only for stable
    "modern-lib": "^1.2.3"        // Minor OK for active
  }
}

Node.js Conflicts

Diagnosis:

bash
npm ls package-name      # See dependency tree
npm explain package-name # Why installed
yarn why package-name    # Yarn equivalent

Resolution with overrides:

json
// package.json
{
  "overrides": {
    "lodash": "^4.18.0"
  }
}

Resolution with resolutions (Yarn):

json
{
  "resolutions": {
    "lodash": "^4.18.0"
  }
}

Python Conflicts

Diagnosis:

bash
pip check
pipdeptree -p package-name

Resolution:

bash
# Use virtual environment
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt

# Or use constraints
pip install -c constraints.txt -r requirements.txt

Script Reference

ScriptPurpose
scripts/check-tool.shVerify tool is installed
scripts/run-taze.shRun taze with proper flags

Related Tools

ToolLanguagePurpose
tazeNode.jsSmart dependency updates
npm-check-updatesNode.jsAlternative to taze
pip-reviewPythonInteractive pip updates
cargo-editRustCargo dependency management
bundler-auditRubySecurity auditing

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Dependency Updater AI skill do?

Smart dependency management for any language. Auto-detects project type, applies safe updates automatically, prompts for major versions, diagnoses and fixes dependency issues.

Why use Dependency Updater on TypingMind?

Because you install it once and use it with any model. Dependency Updater is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Dependency Updater in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/softaworks/agent-toolkit/tree/main/skills/dependency-updater. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Dependency Updater?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Dependency Updater?

As many as you like. As long as a model supports skills, you can use Dependency Updater with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Dependency Updater AI skill free?

Yes. It is published on GitHub by softaworks under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇