safety

Git, command, Kubernetes, data, workspace, and temporary files safety rules. Use when committing, pushing, using kubectl, handling multi-repo workspaces, or performing destructive operations.

16 stars

Best use case

safety is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Git, command, Kubernetes, data, workspace, and temporary files safety rules. Use when committing, pushing, using kubectl, handling multi-repo workspaces, or performing destructive operations.

Teams using safety should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/safety/SKILL.md --create-dirs "https://raw.githubusercontent.com/diegosouzapw/awesome-omni-skill/main/skills/development/safety/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/safety/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How safety Compares

Feature / AgentsafetyStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Git, command, Kubernetes, data, workspace, and temporary files safety rules. Use when committing, pushing, using kubectl, handling multi-repo workspaces, or performing destructive operations.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Safety Rules

## Git Safety

### Absolute Rules (Cannot be broken)

- Do not commit unless explicitly requested
- Do not push unless explicitly requested
- Never commit to main/master branch unless explicitly requested
- Never run `git reset --hard` without explicit user approval

### Core Safety Guidelines

- Do not change git stage without being asked
- Do not make commits without reviews unless explicitly requested
- Always create feature branches for changes
- Use `/git-branch` command for safe branch creation
- `/commit` command automatically creates feature branch when on main/master
- Verify branch before committing
- Never commit unstaged changes without explicit request
- Always validate conventional commit format
- Create backups before destructive operations
- Show what will be committed before execution
- Never push directly to main/master
- Always create pull requests for main branch changes
- Use `/pr-create` command for safe PR creation
- Verify remote branch exists before pushing

## Command Safety

### Shell Safety

- Prefer terminal commands over GUI operations when possible

### Kubernetes Safety

- Never execute `kubectl delete` or `kubectl apply`
- Use `/k8s-check` for safe inspection
- Use `/k8s-validate` for manifest validation
- Use `/k8s-diff` for change preview

### Git Destructive Operations

- Never run `git reset --hard` without explicit approval
- Use `/git-reset` for safe reset with backup
- Always create stash before destructive operations
- Provide recovery instructions

## Data Safety

- Always create backups before destructive operations
- Use git stash for uncommitted changes
- Document recovery procedures
- Test backup restoration

## Workspace Safety

### Multi-Repository Handling

- Always check current working directory and understand repository boundaries
- Never assume single git repository when working in multi-repo workspace
- Always verify which repository operations are targeting before execution
- When working with staged changes, identify which specific repository they belong to
- Navigate to correct repository directory before running git operations
- Treat each repository as separate entity with its own git state

### Error Prevention

- Always ask for clarification when workspace structure is unclear
- Confirm target repository before running git commands
- Use non-destructive commands first (git stash, git log) to understand situation

## Temporary Files Safety

- When creating temporary files, use temporary directories (`./tmp` or system tmp)
- Automatically clean up temporary files after use
- Never commit temporary files to version control

Related Skills

type-safety-validation

16
from diegosouzapw/awesome-omni-skill

End-to-end type safety with Zod, tRPC, Prisma, and TypeScript 5.7+ patterns. Use when creating Zod schemas, setting up tRPC, validating input, implementing exhaustive switch statements, branded types, or type checking with ty.

memory-safety-patterns

16
from diegosouzapw/awesome-omni-skill

Implement memory-safe programming with RAII, ownership, smart pointers, and resource management across Rust, C++, and C. Use when writing safe systems code, managing resources, or preventing memory...

azure-ai-contentsafety-ts

16
from diegosouzapw/awesome-omni-skill

Analyze text and images for harmful content using Azure AI Content Safety (@azure-rest/ai-content-safety). Use when moderating user-generated content, detecting hate speech, violence, sexual conten...

azure-ai-contentsafety-py

16
from diegosouzapw/awesome-omni-skill

Azure AI Content Safety SDK for Python. Use for detecting harmful content in text and images with multi-severity classification.

azure-ai-contentsafety-java

16
from diegosouzapw/awesome-omni-skill

Build content moderation applications with Azure AI Content Safety SDK for Java. Use when implementing text/image analysis, blocklist management, or harm detection for hate, violence, sexual conten...

agent-safety

16
from diegosouzapw/awesome-omni-skill

Ensure agent safety - guardrails, content filtering, monitoring, and compliance

bgo

10
from diegosouzapw/awesome-omni-skill

Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.

Coding & Development

ui-ux-pro-max

16
from diegosouzapw/awesome-omni-skill

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.

ui ux

16
from diegosouzapw/awesome-omni-skill

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.

ui-ux-design

16
from diegosouzapw/awesome-omni-skill

UI/UX design reference database. 50+ styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.

ui-skills

16
from diegosouzapw/awesome-omni-skill

Opinionated constraints for building better interfaces with agents.

ui-patterns

16
from diegosouzapw/awesome-omni-skill

Plaited UI patterns for templates, behavioral elements, and styling. Use when creating bElements or FunctionalTemplates, writing stories for testing, using createStyles, building form controls, or coordinating cross-island communication.