Remote OpenClaw
Menu
SkillsMCPPluginsFree guideDigestSubmit MCPSkillPluginMCPMCP, plugin, or skillAdvertise
Remote OpenClaw
SkillsMCPPluginsFree guideDigestSubmit MCPSkillPluginMCPMCP, plugin, or skillAdvertise

Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Turn any website into LLM-ready data with Firecrawl logoTurn any website into LLM-ready data with Firecrawl

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits plus 10% off through our link.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Turn any website into LLM-ready data with Firecrawl logoTurn any website into LLM-ready data with Firecrawl

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits plus 10% off through our link.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Turn any website into LLM-ready data with Firecrawl logoTurn any website into LLM-ready data with Firecrawl

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits plus 10% off through our link.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
Skills/paulrberg/agent-skills/bump-deps
bump-deps logo

bump-deps

paulrberg/agent-skills
2K installs62 stars
Run it on Hostinger →up to 70% off + an extra 10% with code ZACAARON10Free API →

Installation

npx skills add https://github.com/paulrberg/agent-skills --skill bump-deps

Summary

Use for dependency updates: update/bump deps, npm/pnpm/yarn/bun package upgrades, outdated checks, package.json updates, or taze.

SKILL.md

Bump Dependencies Skill

Update Node.js dependencies using taze CLI with smart prompting: auto-apply MINOR/PATCH updates, prompt for MAJOR updates individually, skip fixed-version packages.

For projects with a package-manager minimum-age policy, pass Taze's maturity-period flags so Taze filters out too-new releases before writing manifests.

When package names are provided as arguments (e.g. /bump-deps react typescript), scope all taze commands to only those packages using --include.

When --dry-run is passed (e.g. /bump-deps --dry-run or /bump-deps --dry-run react), scan for updates and present a summary table without applying any changes. See Dry Run Mode below.

Prerequisites

Before choosing commands, check whether the target project has either:

  • bun.lock or bun.lockb plus bunfig.toml with [install].minimumReleaseAge
  • pnpm or Yarn minimum-age settings

If present, follow Minimum Release Age Mode.

Before starting, verify taze is installed by running:

scripts/run-taze.sh

If exit code is 1, stop and inform the user that taze must be installed:

  • Global install: npm install -g taze
  • One-time: npx taze

Minimum Release Age Mode

Use this mode for projects that configure a package-manager minimum-age policy.

Taze calls this maturityPeriod:

  • --maturity-period [days] filters out package versions newer than the given number of days
  • --maturity-period-exclude <packages> excludes packages from that filter, when supported by the installed Taze version
# 7-day cooldown
taze major -r --maturity-period 7

For Bun minimumReleaseAge, convert seconds to whole days using a ceiling division. Example: 604800 seconds becomes --maturity-period 7. If the configured seconds are not a whole number of days, round up so Taze is not weaker than the package manager policy.

Taze v19.13.0+ auto-infers maturity periods from pnpm and Yarn workspace config, but not from Bun bunfig.toml. For Bun projects, pass --maturity-period explicitly.

When the package manager config has an exclude list, pass matching Taze excludes if available:

taze major -r --maturity-period 7 --maturity-period-exclude react,webpack

Append the same maturity flags to every Taze scan and write command in the workflow. After Taze writes manifests, run the project package manager install as usual; the package manager remains the final enforcement layer for direct and transitive resolution.

Update Workflow

Step 1: Scan for Updates

Run the taze script to discover available updates. The script auto-detects monorepo projects (workspaces in package.json or pnpm-workspace.yaml) and enables recursive mode automatically.

scripts/run-taze.sh

Step 2: Parse and Categorize Updates

From the taze output, categorize each package update:

CategoryVersion ChangeAction
FixedNo ^ or ~ prefix (e.g., "1.0.0")Skip entirely
PATCHx.y.z → x.y.Z (e.g., 1.0.0 → 1.0.1)Auto-apply
MINORx.y.z → x.Y.0 (e.g., 1.0.0 → 1.1.0)Auto-apply
MAJORx.y.z → X.0.0 (e.g., 1.0.0 → 2.0.0)Prompt user

If package arguments were provided, filter to only those packages.

Dry Run Mode

If --dry-run was passed, stop here — do not apply any updates. Instead, present a single markdown table summarizing all available updates and exit. The table must include every discovered package (including fixed-version packages, shown as skipped):

| Package | Current | Available | Type | Action |
|---------|---------|-----------|------|--------|
| @types/node | ^20.0.0 | ^22.0.0 | major | prompt |
| typescript | ^5.3.0 | ^5.4.0 | minor | auto-apply |
| eslint | ^8.56.0 | ^8.57.0 | patch | auto-apply |
| lucide-react | ^3.0.0 | ^4.0.0 | major | auto-apply |
| lodash | 4.17.21 | 4.18.0 | minor | skip (fixed) |

Column definitions:

  • Package — package name
  • Current — version string as it appears in package.json (with range prefix)
  • Available — new version string (preserving range prefix)
  • Type — major, minor, or patch
  • Action — what the normal (non-dry-run) workflow would do:
  • auto-apply — MINOR/PATCH updates and auto-skip major packages (e.g. lucide-react)
  • prompt — MAJOR updates that would be prompted to the user
  • skip (fixed) — fixed-version packages that would be skipped

Sort the table by action priority: prompt first, then auto-apply, then skip (fixed). Within each group, sort alphabetically by package name.

After presenting the table, print a one-line summary: N updates available (M major, P minor, Q patch, F fixed-skipped) and stop. Do not proceed to Step 3 or beyond.

Identifying fixed versions: In package.json, fixed versions have no range prefix:

  • Fixed: "lodash": "4.17.21" → skip
  • Ranged: "lodash": "^4.17.21" → process

Step 3: Apply MINOR/PATCH Updates

Apply all non-major updates automatically without prompting:

# All packages
taze minor --write

# Specific packages only (when args provided)
taze minor --write --include react,typescript

The script auto-detects monorepo mode, but when running taze directly, detect it yourself: check for workspaces in package.json or pnpm-workspace.yaml and add -r if present.

Report the packages that were updated.

Step 4: Prompt for MAJOR Updates

Auto-skip packages: Never prompt for these packages—auto-apply their major updates:

  • lucide-react (icon library with frequent major bumps, backward-compatible in practice)

For each remaining package with a major update available, use AskUserQuestion to ask the user individually:

Package: <package-name>
Current: <current-version>
Available: <new-version>

Update to major version?

Question format:

  • header: Package name (max 12 chars, truncate if needed)
  • options: "Yes, update" / "No, skip"
  • multiSelect: false

Collect all approved major updates.

Step 5: Apply Approved MAJOR Updates

After collecting user approvals, apply the approved major updates:

taze major --write --include <pkg1>,<pkg2>,<pkg3>

Add -r if monorepo was detected.

Step 6: Update Bun Catalogs

After applying all updates, check the root package.json for Bun workspace catalogs. Bun monorepos can centralize dependency versions using catalog and catalogs fields inside the workspaces object:

{
  "workspaces": {
    "packages": ["packages/*"],
    "catalog": {
      "react": "^19.0.0"
    },
    "catalogs": {
      "testing": {
        "jest": "^30.0.0"
      }
    }
  }
}

Workspace packages reference these with "react": "catalog:" (default catalog) or "jest": "catalog:testing" (named catalog).

Skip this step if neither workspaces.catalog nor workspaces.catalogs exists in the root package.json.

For each package that was updated in Steps 3/5:

  1. Check if it appears in workspaces.catalog — if so, update the version there
  2. Check each named catalog in workspaces.catalogs — if the package appears, update the version there

Preserve the existing range prefix (^, ~, or none) from the catalog entry. For example, if the catalog has "react": "^19.0.0" and taze bumped react to 19.1.0, update the catalog to "react": "^19.1.0".

Use Edit to apply the version changes directly to the root package.json.

Step 7: Install Dependencies

After all updates are applied, run ni to install dependencies. It auto-detects the package manager.

Taze Output Interpretation

Taze displays updates grouped by type. Example output:

@types/node  ^20.0.0  →  ^22.0.0   (major)
typescript   ^5.3.0   →  ^5.4.0    (minor)
eslint       ^8.56.0  →  ^8.57.0   (patch)

The rightmost column indicates update type (major/minor/patch).

Packages shown with --include-locked that have no ^ or ~ are fixed versions—skip these entirely.

Script Reference

ScriptPurpose
scripts/run-taze.shRun taze in non-interactive mode, check installation

Important Notes

  • Fixed-version dependencies (no ^ or ~) indicate intentional pinning—never modify these
  • MAJOR updates may contain breaking changes—always prompt the user
  • MINOR/PATCH updates are backward-compatible by semver convention—safe to auto-apply
  • The --include flag accepts comma-separated package names or regex patterns
  • Monorepo detection is automatic—no flag needed
  • Bun catalogs (workspaces.catalog / workspaces.catalogs) are the source of truth for workspace packages using the catalog: protocol—always update catalog entries alongside regular deps

Score

0–100
63/ 100

Grade

C

Popularity15/30

1,653 installs — growing adoption.

Completeness27/30

Documented: full SKILL.md body, description, one-line install. Missing: category/license metadata.

Trust15/25

Community skill with a public GitHub source repository you can review.

Freshness6/15

No update timestamp is tracked for this skill in our catalog.

Scored automatically from popularity, completeness, trust, and freshness — computed only from data in our catalog, never fabricated.

Proud of your score? Add this badge to your README.

Paste a snippet into your GitHub README. The badge updates automatically and links back to this page.

Bump Deps skill score badge previewScore badge

Markdown

[![Bump Deps skill](https://www.remoteopenclaw.com/skills/paulrberg/agent-skills/bump-deps/badges/score.svg)](https://www.remoteopenclaw.com/skills/paulrberg/agent-skills/bump-deps)

HTML

<a href="https://www.remoteopenclaw.com/skills/paulrberg/agent-skills/bump-deps"><img src="https://www.remoteopenclaw.com/skills/paulrberg/agent-skills/bump-deps/badges/score.svg" alt="Bump Deps skill"/></a>

Bump Deps FAQ

How do I install the Bump Deps skill?

Run “npx skills add https://github.com/paulrberg/agent-skills --skill bump-deps” in your terminal. The skill is added to your agent's skills directory and picked up automatically on the next run — no restart or extra configuration needed.

What does the Bump Deps skill do?

Use for dependency updates: update/bump deps, npm/pnpm/yarn/bun package upgrades, outdated checks, package.json updates, or taze. The full SKILL.md on this page shows the exact instructions the skill gives your agent.

Is the Bump Deps skill free?

Yes. Bump Deps is a free, open-source skill published from paulrberg/agent-skills. As with any third-party skill, review the source repository before installing it into an agent with sensitive access.

Does Bump Deps work with Claude Code and OpenClaw?

Yes. Skills use the portable SKILL.md format, so Bump Deps works with Claude Code, OpenClaw, Codex, Hermes, and any other agent that reads SKILL.md skills.

Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Turn any website into LLM-ready data with Firecrawl logoTurn any website into LLM-ready data with Firecrawl

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits plus 10% off through our link.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Turn any website into LLM-ready data with Firecrawl logoTurn any website into LLM-ready data with Firecrawl

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits plus 10% off through our link.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Turn any website into LLM-ready data with Firecrawl logoTurn any website into LLM-ready data with Firecrawl

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits plus 10% off through our link.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →

Categories

Command Execution
View on GitHub

Recommended skills

Browse all →
find-skills logo

find-skills

vercel-labs/skills

2.7M installsInstall
frontend-design logo

frontend-design

anthropics/skills

720K installsInstall
grill-me logo

grill-me

mattpocock/skills

701K installsInstall
agent-browser logo

agent-browser

vercel-labs/agent-browser

596K installsInstall
grill-with-docs logo

grill-with-docs

mattpocock/skills

594K installsInstall
vercel-react-best-practices logo

vercel-react-best-practices

vercel-labs/agent-skills

591K installsInstall

Browse

Skills by category

Frontend250Git198Data154Testing120Design105Docs103Security96Automation87Backend76Devops37Productivity29Mcp23

Related guides

Hand-picked reading to help you choose, install, and use agent skills.

GuideBest Openclaw Skills 2026GuideHow To Evaluate Openclaw Skill Before InstallingGuideOpenclaw Skills Complete Guide

Remote OpenClaw

AI agent skills directory, marketplace, and workflow hub for OpenClaw, Hermes Agent, Claude Code, Codex, and MCP-powered operator stacks.

The Agent Stack: weekly agent tooling digest, free.

Explore

  • Home
  • Skills Directory
  • Claude Code Skills
  • Codex Skills
  • MCP Clients
  • Marketplace
  • Hermes Ecosystem
  • Free guide
  • Learn
  • OpenClaw for Creators
  • OpenClaw for Founders
  • Blog
  • The Agent Stack (Digest)

More

  • Submit a Tool
  • Advertise
  • Playbook
  • Free Tools
  • API
  • Shipping
  • Contact
  • Terms
  • Privacy

Know a company that should advertise here? Refer them and earn 10% — up to $300 per referral.

© 2026 Remote OpenClaw
Fazier badgeFeatured on Twelve ToolsFeatured on Wired BusinessRemote OpenClaw - Featured on AI Agents DirectoryListed on Turbo0Featured on Uneed