Sandbox
@Hainrixz/skill-vault

Claude Code skill library with security checks

Skill Vault is a local catalog for Claude Code skills. You add skills, the vault classifies them into folders, and it runs a security review before saving them.

67 stars14 forksUpdated 5mo ago
Who it's for

Builders who want Claude Code to keep a searchable library of skills and flag risky ones before they save them.

What it delivers

You can collect, review, and find Claude Code skills without keeping track of them by hand.

What it does

Skill storage by category

Skills are saved as markdown files inside folders like `categories/testing/` and `categories/web-development/`.

Security analysis

Each skill is checked against a 13-point rubric and marked SAFE, CAUTION, or DANGEROUS before it is saved.

Search and recommendation commands

Claude Code commands like `/vault-search`, `/vault-recommend`, and `/vault-list` help you find the right skill for a project.

Skill discovery

The vault can find new skills from the internet with `/vault-discover` and add them to the catalog.

Reusable templates

`templates/skill-entry.md` and `templates/category-readme.md` give a standard format for new entries and folders.

How to get it

  1. 1Run
    git clone https://github.com/Hainrixz/skill-vault.git
    cd skill-vault
    claude

README

Skill Vault

Your personal library for Claude Code skills.

Lea esto en Español


What is this?

Imagine you have a big toy box, but instead of toys, it holds skills — special abilities that make Claude Code smarter.

People are sharing thousands of skills online every day. The problem? They're scattered everywhere. You find one on GitHub, another on skills.sh, another someone shared on X... and then you forget where you saved them. Or worse — some of them might be harmful.

Skill Vault is your organized, safe toy box for skills. It does three things:

  1. Saves and organizes your skills into labeled folders
  2. Checks each skill for danger before saving it (like a security guard for your computer)
  3. Helps you find the right skill when you're building something

That's it. Clone it, open it with Claude, and start collecting.


Getting Started

git clone https://github.com/Hainrixz/skill-vault.git
cd skill-vault
claude

No installs. No setup. No dependencies. Just open it and go.


How It Works

When you open this project with Claude Code, the Vault Master agent takes over. Think of it as your personal librarian who:

  • Accepts skills from anywhere — paste a URL, paste the content, or just tell it a name
  • Analyzes each skill through a 13-point security checklist and rates it: SAFE, CAUTION, or DANGEROUS
  • Files it in the right category folder automatically
  • Finds skills for you when you describe what you're building

Commands

CommandWhat it does
/vault-addSave a new skill (from URL, paste, or name)
/vault-searchSearch your vault by keyword
/vault-recommendDescribe your project, get matching skills
/vault-discoverFind new skills from the internet
/vault-listSee everything in your vault
/vault-statsVault stats + health check
/vault-removeRemove a skill

Folder Structure

Skills are saved in category folders. Each skill gets its own file with metadata, security analysis, install instructions, and the original content preserved.

categories/
├── automation/          # Browser bots, scripts, task runners
├── code-quality/        # Linting, refactoring, reviews
├── design-ui/           # UI components, design systems, CSS
├── devops-deploy/       # Docker, CI/CD, infrastructure
├── documentation/       # READMEs, API docs, changelogs
├── organization/        # Project management, planning
├── productivity/        # Text tools, meeting notes, workflows
├── research/            # Web research, data gathering
├── testing/             # Unit tests, E2E, QA
└── web-development/     # React, Next.js, Vue, APIs

Don't see a category that fits? The Vault Master creates new ones automatically.


Security

Every skill is scanned before it enters your vault. The Vault Master checks for:

  • Dangerous commands (rm -rf, pipe-to-shell execution)
  • Credential theft (reading SSH keys, AWS tokens, API keys)
  • Data exfiltration (sending your files to external servers)
  • Obfuscated code (hidden payloads in base64 or hex)
  • Overly broad permissions
  • Prompt injection attempts
RatingWhat it means
SAFEClean — no risky operations detected
CAUTIONSome risk — review the findings before using
DANGEROUSRed flag — you'll be warned before it's saved

Full methodology in security-rubric.md.


Example Workflow

You:    /vault-add https://github.com/anthropics/skills/tree/main/skill-creator
Vault:  Analyzing skill... Rating: SAFE
        Saved to: categories/productivity/skill-creator.md
        Added to catalog.

You:    /vault-recommend I'm building a Next.js e-commerce app
Vault:  From your vault, I recommend:
        - shadcn-ui (design-ui) [SAFE] — UI components
        - playwright-cli (testing) [CAUTION] — E2E testing
        - vercel-deploy (devops-deploy) [SAFE] — Deployment

You:    /vault-discover SEO optimization
Vault:  Found 3 skills on skills.sh:
        - seo-audit [SAFE] — Technical SEO analysis
        - meta-tags-generator [SAFE] — Auto meta tags
        Add any of these? (y/n)

Contributing

  1. Fork this repo
  2. Add skills with /vault-add or create entries manually in categories/ using the template at templates/skill-entry.md
  3. Submit a PR

Built by

Todo de IA by @soyenriquerocha — Building tools for the AI community.

License

MIT

Files in the repo

Repository payload9 top-level entries
  • categories
  • templates
  • .gitignore
  • catalog.md
  • CLAUDE.md
  • LICENSE
  • README.es.md
  • README.md
  • security-rubric.md

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More collections

The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞

52k
phuryn/
pm-skills
phuryn/pm-skillsCollections

PM Skills Marketplace: 100+ agentic skills, commands, and plugins — from discovery to strategy, execution, launch, and growth.

26k

Extracted system prompts from Anthropic - Claude Fable 5.1, Opus 5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-6-Astra, Codex. Google - Gemini 3.8 Flash, 3.1 Pro, Antigravity. xAI - Grok, Grok Bot, Cursor, Kimi and more! Updated regularly.

65k
1 add