Review Dependencies logo

Review Dependencies

Community
tobihagemann
review-dependencies

Detect package managers and CI action pins, then discover outdated or vulnerable dependencies. Returns structured findings without upgrading. Use when the user asks to "review dependencies", "check for outdated packages", "check dependencies", "scan dependencies", "dependency review", "check for outdated GitHub Actions", or "are my workflow actions up to date".

Overview

Publishertobihagemann
Repositoryturbo
Skill namereview-dependencies
Stars
417
Forks
32
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Review Dependencies 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.
    https://github.com/tobihagemann/turbo/tree/main/claude/skills/review-dependencies
  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/tobihagemann/turbo.git /tmp/turbo
mkdir -p .claude/skills
cp -r /tmp/turbo/claude/skills/review-dependencies .claude/skills/review-dependencies
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Review Dependencies 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 Review Dependencies 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 Review Dependencies 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.

Review Dependencies

Detect package managers and CI action pins, then discover outdated or vulnerable dependencies. Analysis only. Does not upgrade.

Step 1: Detect Package Managers

Identify which package managers are in use by searching for config files:

Config filePackage managerLockfileEcosystem
package.jsonnpm / yarn / pnpmpackage-lock.json / yarn.lock / pnpm-lock.yamlNode.js
Package.swift, *.xcodeprojSwift Package ManagerPackage.resolvedSwift
pyproject.toml, requirements.txt, setup.pypip / poetry / uvpoetry.lock, uv.lockPython
Cargo.tomlcargoCargo.lockRust
go.modGo modulesgo.sumGo
GemfileBundlerGemfile.lockRuby
pom.xmlMaven—Java
build.gradle, build.gradle.ktsGradlegradle.lockfileJava/Kotlin
.github/workflows/*.yml / .yaml, action.yml / .yamlGitHub Actions—CI

Swift dependencies can live in Package.swift or be configured directly in the Xcode project file (.xcodeproj/.xcworkspace). For Xcode-managed dependencies, inspect the project's package references.

Detection steps:

  1. Search for config files in the project root and subdirectories (exclude vendored directories)
  2. If a lockfile exists, use the corresponding package manager variant (e.g., yarn.lock → yarn, pnpm-lock.yaml → pnpm)
  3. When the repo declares a dependency automation config (.github/dependabot.yml / .yaml, renovate.json, .github/renovate.json), read it and add every ecosystem it declares to the set found by the config-file search
  4. When the repo has a GitHub remote, list open dependency PRs with gh pr list --author app/dependabot (or app/renovate), and mark each upgrade one of them already proposes
  5. If multiple instances of the same package manager found (e.g., monorepo with several package.json files): use AskUserQuestion to let the user choose which to review (multiSelect allowed)
  6. If multiple package managers found: use AskUserQuestion to let the user choose which to review. Exclude the CI ecosystem from that choice and review it alongside whichever the user picks
  7. If none found across every step above: inform user and stop

Step 2: Discovery

Run the appropriate discovery command to find available updates:

Package managerDiscovery commandNotes
npmncu --format groupRequires npm-check-updates. Suggest npm install -g npm-check-updates if missing.
yarnncu --format group or yarn upgrade-interactive
pnpmncu --format group or pnpm outdated
Swift PMCheck resolved versions in Package.resolved against latest releases via WebSearchNo built-in outdated command. Read Package.swift or inspect the Xcode project to identify dependencies and their current version constraints.
pippip list --outdated
poetrypoetry show --outdated
uvuv pip list --outdated
cargocargo outdatedRequires cargo-outdated. Fall back to comparing Cargo.toml versions via WebSearch.
Go modulesgo list -m -u all
Bundlerbundle outdated
Mavenmvn versions:display-dependency-updates
Gradlegradle dependencyUpdatesRequires com.github.ben-manes.versions plugin.
GitHub Actionsgh api repos/<owner>/<repo>/releases/latest --jq .tag_name, compared against each uses: refNo outdated command. Take <owner>/<repo> from the ref's first two path segments. Read a SHA-pinned ref's version from its trailing comment (uses: <owner>/<action>@<sha> # v1.2.3). Compare only the components the ref pins, so @v7 is current against v7.0.1. Fall back to repos/<owner>/<repo>/tags when the release 404s or its tag namespace differs from the ref's, and to WebSearch when the action is not hosted on GitHub. Exclude local (./…), <repo-relative> ($/…), and Docker (docker://…) refs, which pin no release.

Categorize updates:

  • Major (breaking changes) — requires migration research
  • Minor (new features, backward compatible)
  • Patch (bug fixes)

Step 3: Report Findings

If the discovery tool is not installed, suggest the installation command (see Step 2 notes column). If no tool exists for the ecosystem, fall back to manual version checking via WebSearch.

If no updates are available, report that dependencies are up to date. Otherwise, report each update in the output format below, followed by the Overall Verdict.

Then use the TaskList tool and proceed to any remaining task.

Output Format

Format each finding as:

### [P<N>] <title (imperative, <=80 chars)>

**Package:** `<name>` <current> -> <latest>
**Manager:** <npm/pip/cargo/etc.>
**Proposed:** <open automation PR already covering this upgrade, when one exists>

<one paragraph: why this matters, known vulnerabilities if any, major version gap>

After all findings, add:

## Overall Verdict

**Dependencies:** <up to date | updates available>

<summary with counts: N major, N minor, N patch>

Priority Levels

  • P0 — Known security vulnerability (CVE) in the current version
  • P1 — Multiple major versions behind (e.g., React 17 → 19)
  • P2 — One major version behind or significantly outdated minor versions
  • P3 — Minor or patch updates available

Frequently asked questions

What does the Review Dependencies AI skill do?

Detect package managers and CI action pins, then discover outdated or vulnerable dependencies. Returns structured findings without upgrading. Use when the user asks to "review dependencies", "check for outdated packages", "check dependencies", "scan dependencies", "dependency review", "check for outdated GitHub Actions", or "are my workflow actions up to date".

Why use Review Dependencies on TypingMind?

Because you install it once and use it with any model. Review Dependencies 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 Review Dependencies in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/tobihagemann/turbo/tree/main/claude/skills/review-dependencies. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Review Dependencies?

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 Review Dependencies?

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

Is the Review Dependencies AI skill free?

Yes. It is published on GitHub by tobihagemann 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 👇