Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Detect package managers and discover outdated or vulnerable dependencies.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 Use when the user asks to "review dependencies", "check for outdated packages", "check dependencies", "scan dependencies", or "dependency review".
.claude/skills/tobihagemann-review-dependencies/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | -12% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 13% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -32% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 49% | 0% |
| case-21 | ✗→✓ | ▲ Improved | -32% | 0% |
Detect package managers and discover outdated or vulnerable dependencies. Analysis only. Does not upgrade.
Identify which package managers are in use by searching for config files:
| Config file | Package manager | Lockfile | Ecosystem | |---|---|---|---| | package.json | npm / yarn / pnpm | package-lock.json / yarn.lock / pnpm-lock.yaml | Node.js | | Package.swift, *.xcodeproj | Swift Package Manager | Package.resolved | Swift | | pyproject.toml, requirements.txt, setup.py | pip / poetry / uv | poetry.lock, uv.lock | Python | | Cargo.toml | cargo | Cargo.lock | Rust | | go.mod | Go modules | go.sum | Go | | Gemfile | Bundler | Gemfile.lock | Ruby | | pom.xml | Maven | — | Java | | build.gradle, build.gradle.kts | Gradle | gradle.lockfile | Java/Kotlin |
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:
yarn.lock → yarn, pnpm-lock.yaml → pnpm)package.json files): use request_user_input to let the user pick one (Codex request_user_input choices are mutually exclusive). For an "all of them" workflow, ask follow-up free-form input or run the review per instance.request_user_input to let the user pick oneRun the appropriate discovery command to find available updates:
| Package manager | Discovery command | Notes | |---|---|---| | npm | ncu --format group | Requires npm-check-updates. Suggest npm install -g npm-check-updates if missing. | | yarn | ncu --format group or yarn upgrade-interactive | | | pnpm | ncu --format group or pnpm outdated | | | Swift PM | Check resolved versions in Package.resolved against latest releases via web search | No built-in outdated command. Read Package.swift or inspect the Xcode project to identify dependencies and their current version constraints. | | pip | pip list --outdated | | | poetry | poetry show --outdated | | | uv | uv pip list --outdated | | | cargo | cargo outdated | Requires cargo-outdated. Fall back to comparing Cargo.toml versions via web search. | | Go modules | go list -m -u all | | | Bundler | bundle outdated | | | Maven | mvn versions:display-dependency-updates | | | Gradle | gradle dependencyUpdates | Requires com.github.ben-manes.versions plugin. |
Categorize updates:
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 web search.
If no updates are available, report that dependencies are up to date.
Format each finding as:
### [P<N>] <title (imperative, <=80 chars)>
**Package:** `<name>` <current> -> <latest>
**Manager:** <npm/pip/cargo/etc.>
<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>| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 6,650 | 21,476 | +223% | 1 | 1 | 0% | 1,138 | 1,397 | +23% | 0 | 0 | — |
case-02 | fail→fail | 6,220 | 7,713 | +24% | 1 | 1 | 0% | 264 | 1,249 | +373% | 0 | 0 | — |
case-03 | fail→fail | 8,689 | 3,024 | -65% | 1 | 1 | 0% | 1,498 | 1,200 | -20% | 0 | 0 | — |
case-04 | pass→fail | 4,562 | 11,347 | +149% | 1 | 1 | 0% | 733 | 1,748 | +138% | 0 | 0 | — |
case-05 | pass→pass | 5,839 | 20,929 | +258% | 1 | 1 | 0% | 917 | 3,739 | +308% | 0 | 0 | — |
case-06 | pass→fail | 19,521 | 2,653 | -86% | 1 | 1 | 0% | 3,806 | 1,232 | -68% | 0 | 0 | — |
case-07 | fail→pass | 10,032 | 2,667 | -73% | 1 | 1 | 0% | 1,648 | 1,451 | -12% | 0 | 0 | — |
case-08 | fail→pass | 7,858 | 2,823 | -64% | 1 | 1 | 0% | 1,369 | 1,541 | +13% | 0 | 0 | — |
case-09 | pass→pass | 8,050 | 2,227 | -72% | 1 | 1 | 0% | 1,360 | 1,372 | +1% | 0 | 0 | — |
case-10 | fail→fail | 13,139 | 11,210 | -15% | 1 | 1 | 0% | 2,134 | 2,444 | +15% | 0 | 0 | — |
case-11 | fail→pass | 12,671 | 2,517 | -80% | 1 | 1 | 0% | 2,165 | 1,467 | -32% | 0 | 0 | — |
case-12 | pass→pass | 2,290 | 1,703 | -26% | 1 | 1 | 0% | 374 | 1,281 | +243% | 0 | 0 | — |
case-13 | pass→pass | 7,628 | 3,912 | -49% | 1 | 1 | 0% | 1,252 | 1,662 | +33% | 0 | 0 | — |
case-14 | pass→pass | 2,587 | 1,769 | -32% | 1 | 1 | 0% | 388 | 1,275 | +229% | 0 | 0 | — |
case-15 | fail→pass | 5,784 | 1,750 | -70% | 1 | 1 | 0% | 897 | 1,333 | +49% | 0 | 0 | — |
case-16 | pass→pass | 4,825 | 2,450 | -49% | 1 | 1 | 0% | 774 | 1,463 | +89% | 0 | 0 | — |
case-21 | fail→pass | 11,075 | 4,440 | -60% | 1 | 1 | 0% | 1,891 | 1,284 | -32% | 0 | 0 | — |
case-17 | pass→pass | 2,437 | 2,374 | -3% | 1 | 1 | 0% | 346 | 1,372 | +297% | 0 | 0 | — |
case-18 | pass→pass | 4,805 | 2,201 | -54% | 1 | 1 | 0% | 830 | 1,357 | +63% | 0 | 0 | — |
case-19 | pass→pass | 3,878 | 2,899 | -25% | 1 | 1 | 0% | 603 | 1,520 | +152% | 0 | 0 | — |
case-20 | fail→fail | 9,534 | 10,238 | +7% | 1 | 1 | 0% | 1,621 | 2,711 | +67% | 0 | 0 | — |
case-22 | fail→pass | 11,535 | 3,368 | -71% | 1 | 1 | 0% | 1,792 | 1,585 | -12% | 0 | 0 | — |
case-23 | fail→pass | 10,698 | 2,850 | -73% | 1 | 1 | 0% | 1,733 | 1,608 | -7% | 0 | 0 | — |
case-24 | pass→pass | 6,597 | 2,276 | -65% | 1 | 1 | 0% | 952 | 1,309 | +38% | 0 | 0 | — |
case-25 | fail→pass | 10,488 | 1,577 | -85% | 1 | 1 | 0% | 1,650 | 1,219 | -26% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 25 cases were attempted, and 20 counted toward the lift figure. The other 5 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +24 percentage points is the difference between those two pass rates over the 20 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.