Agent skill · software engineering · aiskillstore
safe-edit
Automatically backs up files, saves diffs, uses agents/skills, and ensures modular code (<200 lines) before any implementation. Use this skill for ALL code changes to ensure safe, reversible, and clean implementations.
Why this skill is useful
Adds a comprehensive automation script for safe code implementation with backup, diff tracking, and modularization that the AI cannot generate on its own.
What it needs
Requires bash installed locally. About 4k tokens when loaded. Last updated 2026-08-07. 405 stars on the source repository.
What this skill does
Safe Edit Skill Overview Comprehensive workflow automation for safe, reversible, and clean code implementations. This skill ensures every code change follows best practices: automatic backups, diff tracking, agent utilization, and modular architecture enforcement. When to Use ALWAYS activate this skill before ANY code implementation: Any file modification (create, update, delete) Feature implementation Bug fixes Refactoring UI/UX changes API changes Database schema updates User triggers (automatic activation): Any implementation request without explicit backup mention "implement", "add", "create", "fix", "update", "change" Any code-related task Core Workflow Phase 1: Pre-Implementation Analysis Phase 2: Backup & Safety Phase 3: Implementation Phase 4: Verification Backup Management Directory Structure Backup Naming Convention Diff Naming Convention Automatic Modularization When File Exceeds 200 Lines Detection: Count lines before implementation Predict final size after changes Warn if approaching 200 lines Action Plan: 1. Analyze component responsibilities 2. Identify extractable logic 3. Create modular structure 4. Implement in separate files 5. Update imports/exports Example Refactoring: Agent & Skill Utilization Automatic Agent Selection Analysis Tasks: Explore - Codebase exploration general-purpose - Complex analysis Implementation Tasks: frontend-developer - UI components backend-api-developer - API endpoints database-architect - Schema design ux-ui-designer - Design specs Skill Integration: supabase-manager - Database operations safe-edit (this skill) - All implementations Decision Matrix Task Type Agent/Skill Why ----------- ------------- ----- UI Component frontend-developer Design system + implementation API Endpoint backend-api-developer Best practices + patterns DB Schema database-architect Normalization + indexing Bug Analysis Explore Deep analysis + reasoning File Changes safe-edit (always) Backup + rollback safety Implementation Rules Rule 1: Always Ba …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aiskillstore/safe-edit