Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Build Tools

ASecurity

Drive build systems and package managers, Maven, Gradle, npm, pnpm, yarn, and Cargo, through the devtools-mcp backends without drowning in output. Use to build/test a project, inspect its dependency tree and SUBDEPENDENCIES (versions, depth, conflicts), synchronize/resolve/install deps, run a security audit, find outdated packages, or list runnable tasks/scripts. One verb vocabulary across every language; output is a bounded summary + a queryable Polars frame.

9 stars
0 votes
0 copies
0 views
Added 9/27/2026
ai-agentsrustgojavareactnodebackendsecurity

Works with

terminalmcp

Security Analysis

A100/100

Scanned 9/27/2026

$npx -y skills add Ugbot/ai-grind --skill build-tools --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Build Tools?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Build Tools
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ugbot-build-tools/badge)](https://www.skillsdirectory.com/skills/ugbot-build-tools)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: build-tools
description: >
  Drive build systems and package managers, Maven, Gradle, npm, pnpm, yarn, and
  Cargo, through the devtools-mcp backends without drowning in output. Use to
  build/test a project, inspect its dependency tree and SUBDEPENDENCIES (versions,
  depth, conflicts), synchronize/resolve/install deps, run a security audit, find
  outdated packages, or list runnable tasks/scripts. One verb vocabulary across
  every language; output is a bounded summary + a queryable Polars frame.
---

# Build systems & package managers (devtools-mcp)

Six backends, `maven`, `gradle`, `npm`, `pnpm`, `yarn`, and `cargo`, share **one
verb vocabulary**, so the same `tool` means the same thing everywhere; only the
backend implementation differs. `binary` = the **project directory** (with the
`pom.xml` / `build.gradle` / `package.json` / `Cargo.toml`). Maven/Gradle prefer a
`mvnw`/`gradlew` wrapper, else the global tool.

## The shared verbs

| tool | meaning | maven | gradle | npm/pnpm/yarn | cargo |
|---|---|---|---|---|---|
| `deps` | dependency tree + **subdependencies** | `dependency:tree` | `dependencies` | `ls`/`list --json` | `tree` |
| `sync` | resolve / install / refresh / fetch | `dependency:resolve` | `--refresh-dependencies` | `install` | `fetch` |
| `build` | compile / package | `package` | `build` | `run build` | `build` |
| `test` | run tests (→ JUnit/libtest) | `test` | `test` | `test` | `test` |
| `audit` | security advisories | OSV.dev over dep tree¹ | OSV.dev over dep tree¹ | `audit --json` | `audit` |
| `outdated` | newer versions available | `versions:…updates`² | `dependencyUpdates`³ | `outdated` | `outdated`⁴ |
| `tasks` | runnable goals/tasks/scripts | n/a | `tasks --all` | package.json scripts | n/a |
| `check` | verify without full package | `verify` | `check` | n/a | `check` |

**JVM extras** (maven + gradle only):

| tool | meaning | maven | gradle |
|---|---|---|---|
| `insight` | why is X here / who wins the version, needs `args=["<artifact>"]` | `dependency:tree -Dincludes=X` | `dependencyInsight --dependency X`, multi-module: `args=["X", ":module"]` |
| `projects` | module / reactor listing → modules frame | reactor build order | `projects` |

Gradle `deps`/`sync`/`audit` run a devtools-registered all-projects report task
(via `--init-script`), so a multi-module root yields the **full tree of every
module**. Plain `gradle dependencies` at the root would be empty.

¹ audit parses the dep tree, then batch-queries OSV.dev, so no plugin injection,
works under Gradle dependency verification; needs network at audit time.
² fully-qualified `versions-maven-plugin` goal, which runs against any pom untouched.
³ ben-manes versions plugin injected via a devtools-shipped `--init-script`,
project files untouched; first run downloads the plugin (needs network).
⁴ needs `cargo install cargo-outdated`; yarn `outdated` is classic-only (berry
lacks the command).

```
devtools_run(suite="npm",   tool="deps", binary="C:/code/app")          # JS dep tree
devtools_run(suite="cargo", tool="deps", binary="C:/code/crate")        # Rust dep tree
devtools_run(suite="maven", tool="deps", binary="C:/code/svc")          # Java dep tree
```

## Seeing subdependencies

`deps` returns the **full transitive tree** as a frame with
`group, artifact, version, requested, resolved, scope, depth, conflict, omitted`
(`function` = the package coord). `depth == 1` is direct; deeper rows are
transitive subdependencies.

```
devtools_run(suite="npm", tool="deps", binary="C:/code/app")   # e.g. 2140 nodes, depth 11
devtools_analyze(run_id="...", function_pattern="react")       # everything pulling react
devtools_analyze(run_id="...", sort_by="depth")                # deepest transitive deps
devtools_analyze(run_id="...")                                  # then filter conflict == true
```

The summary already reports node/distinct/direct counts, max depth, and version
conflicts (`requested → resolved`).

## Common jobs

- **"What's pulling in package X / why this version?"** → `deps`, filter to X;
  `requested` vs `resolved` shows who won (Maven `(omitted for conflict with …)`,
  Gradle/npm `requested → resolved`). On JVM projects, `insight` answers it
  directly: `devtools_run(suite="gradle", tool="insight", args=["guava"], ...)`.
- **"Re-sync / install dependencies"** → `sync`.
- **"Any vulnerabilities?"** → `audit` (every backend) → severity-ranked
  frame; `devtools_analyze(run_id, kind_pattern="critical|high")`.
- **"What can I run?"** → `tasks` (Gradle tasks / npm scripts). Any Gradle task
  or Maven goal runs via the passthrough: `tool="build", args=[":module:anyTask"]`.
- **Build/test failures** → `build`/`test`; the summary carries the error lines /
  failing `class.method`, and the full log is on disk (`devtools_raw` or the
  [[devtools-visualizer]] terminal).

## Notes

- `audit`/`outdated` exit non-zero "by design" when they find something, and the
  backends treat them as informational, not failures.
- Multi-module / workspaces: pass `-pl :module` (Maven), `:module:task` (Gradle),
  or workspace flags via `extra_args`.
- Per-tool detail + accumulated project quirks live in the **live skills**
  `gradle-commands`, `maven-commands`, `cargo-commands`, `npm-commands`,
  `pnpm-commands`, `yarn-commands`. Keep their verb tables in sync when verbs
  change here.
- Overall workflow + the no-token-flood principle: [[devtools-mcp-usage]].

Attribution

UgbotUgbot
View sourceSee grades on GitHubMore from Ugbot →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →