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

Prerequisites

ASecurity

Read-only report of external tools the enabled plugin fleet declares, and which of them are missing. Use when a hook says a formatter or CLI is missing, or when asking whether this machine has what the enabled plugins need. Never installs.

20 stars
0 votes
0 copies
0 views
Added 9/29/2026
ai-agentsgoshellbashnodegit

Works with

claude codeclimcp

Security Analysis

A92/100
mediumInstalls packages at runtime which could introduce malicious dependencies

Pro scans all 4 files and shows the line behind each finding

Scanned 10/4/2026

$npx -y skills add melodic-software/claude-code-plugins --skill prerequisites --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Prerequisites?

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

Security grade badge for Prerequisites
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/melodic-software-prerequisites/badge)](https://www.skillsdirectory.com/skills/melodic-software-prerequisites)

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
---
description: "Read-only report of external tools the enabled plugin fleet declares, and which of them are missing. Use when a hook says a formatter or CLI is missing, or when asking whether this machine has what the enabled plugins need. Never installs."
user-invocable: true
disable-model-invocation: false
metadata:
  workflow-stage: operator
  summary: Report external tools the enabled fleet declares missing. Never installs.
  cadence: weekly
---

## Purpose

Answer "does this host have what the enabled plugins need?" Read `prerequisites.json` in each enabled plugin, resolve each declared dependency with the shared Node checker, and print one table. Do not install, download, or run `npx`.

**Claim:** the fleet check lives here, not as a `deps` action on `plugins` and not as a machine-health category. `plugins` brings marketplace versions current and is `disable-model-invocation: true`. This question is read-only and model-invocable. Each plugin that needs an external dependency declares it in `prerequisites.json` at the plugin root, in the schema `docs/conventions/prerequisites/` owns, which this skill and the per-plugin check both read. **Basis:** [skills](https://code.claude.com/docs/en/skills), `disable-model-invocation` ("Set to `true` to prevent Claude from automatically loading this skill. ... Default: `false`."), fetched 2026-09-28. **As of:** 2026-09-28. **Recheck:** a Claude Code release adds a manifest field for external binaries, or `plugins` becomes model-invocable for a read-only action.

## Run

```bash
node "${CLAUDE_SKILL_DIR}/scripts/check-prerequisites.mjs"
```

The table columns are plugin, id, kind, need, status, the check skill, and the install hints. `missing=N present=M` is the last line. The status is `present`, `missing`, `outdated` (below its version floor), `unverified` (the version could not be read) or `agent-check` (an MCP server only the agent can see). Exit 1 means a required entry is missing or below its floor, and a missing optional entry leaves exit 0. Exit 2 means no plugin roots could be read, the listing was not JSON, or a `prerequisites.json` fails the schema.

With no arguments and a `claude` executable on PATH, the script reads the enabled set and each `installPath` from `claude plugin list --json`. That output lists installs across every project, so it keeps user and managed rows, and project or local rows only when their `projectPath` is the current project (`CLAUDE_PROJECT_DIR`, else the git toplevel); an id resolves by its most specific scope, so user-enabled and project-disabled is disabled. When `claude` is absent or prints nothing, it merges `enabledPlugins` from the settings files instead: the user settings in `~/.claude` (`CLAUDE_CONFIG_DIR` overrides that directory) and the project's `.claude/settings.json` and `settings.local.json`. A file holding any non-Boolean `enabledPlugins` value contributes none of its keys, and the managed scope is not read there. Output that is not a JSON list stops the run with exit 2 instead. Only when none of that state exists does it scan `plugins/*/prerequisites.json` in the current repository; a state with nothing enabled prints an empty table.

**Claim:** `claude plugin list --json` returns one row per install with `id`, `scope`, `enabled`, `installPath` and, for project and local rows, `projectPath`, and an id's most specific scope decides whether it is enabled. **Basis:** the `plugin list --json` output observed on Claude Code 2.1.284 (user and project rows only; a managed row was not observed), and the `enabledPlugins` precedence managed > `--settings` > local > project > user recorded in [scope-semantics.md](../plugins/context/scope-semantics.md) from the [settings](https://code.claude.com/docs/en/settings) page. **As of:** 2026-09-29. **Recheck:** a release note changes `plugin list --json` fields or its scope values, or the settings page changes the `enabledPlugins` precedence.

## Next

- A formatter or linter binary is missing: /actionlint:check, /bash-format:check, /biome-format:check, /go-format:check, /markdown-format:check, /powershell-format:check, /ruff-format:check or /typos-format:check
- Record the whole machine's facts and identity domains, not only binaries: /harness-ops:machine-profile
- The fleet's versions, a different question: /harness-ops:plugins audit

## Gotchas

Node is the only runtime this skill needs; the checker is `lib/prerequisites.mjs`, generated from the repository's canonical copy. A plugin whose `prerequisites.json` is still in the retired `tools` shape fails the schema and exits 2.

A missing row is a report, not an install. Do not run `npx`, `npm install`, or `go install` from this skill.

The table's `check` column names the skill for that row. When that skill is model-invocable, run it. When it is a setup skill (a `:setup check` command), it is human-only, so the model cannot invoke it and can only relay the command: tell the user to type it and show the row's install command. Install nothing unless the user asked.

Attribution

melodic-softwaremelodic-software
View sourceSee grades on GitHubMore from melodic-software →
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', ...

698461 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 →