skill-sync
Synchronizes documentation and configuration rules between different AI coding assistants for consistent development guidance.
Install
mkdir -p .claude/skills/skill-sync && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/302" && unzip -o skill.zip -d .claude/skills/skill-sync && rm skill.zipInstalls to .claude/skills/skill-sync
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Syncs Claude Skills with other AI coding tools like Cursor, Copilot, and Codeium by creating cross-references and shared knowledge bases. Invoke when user wants to leverage skills across multiple tools or create unified AI context.Key capabilities
- →Map instruction sets across AI platforms
- →Create cross-tool configuration files like .cursorrules
- →Maintain unified project context
- →Reference Claude Skills in other AI assistants
- →Standardize coding styles across tools
How it works
It maps existing Claude Skills into tool-specific configuration formats to ensure consistent guidance across different AI coding assistants.
Inputs & outputs
When to use skill-sync
- →Create .cursorrules for project context
- →Sync AI instructions across editors
- →Standardize coding styles across tools
- →Maintain shared project knowledge
About this skill
Skill Sync - Cross-Tool Knowledge Sharing
You are an expert at syncing Claude Skills with other AI coding assistants (Cursor, GitHub Copilot, Codeium, etc.) to create a unified knowledge base. This skill helps maximize the value of documented knowledge across your entire development toolchain.
What is Skill Sync?
Skill Sync enables:
- Sharing skill knowledge with other AI tools
- Creating cross-references in tool configs
- Maintaining unified project context
- Reducing duplicate documentation
- Ensuring consistent guidance across tools
When to Use This Skill
Invoke this skill when the user:
- Wants to share skills with Cursor, Copilot, or other tools
- Asks to create .cursorrules or similar configs
- Needs unified AI context across multiple assistants
- Wants to reference skills in other tools
- Asks about cross-tool integration
- Needs to sync project knowledge between AI assistants
Supported Tools
1. Cursor
Configuration Method: .cursorrules file
Cursor reads .cursorrules in the project root for context and instructions.
Capabilities:
- Markdown-based instructions
- Project-specific context
- Code style guidelines
- Framework preferences
2. GitHub Copilot
Configuration Method: Inline comments and project structure
Copilot learns from:
- Existing code patterns
- Comments and docstrings
- File organization
- README and documentation
Limitations:
- No dedicated config file (as of 2025)
- Context comes from open files
- Less explicit guidance than Cursor
3. Codeium
Configuration Method: Project documentation
Codeium uses:
- README.md and docs/
- Code comments
- Existing patterns
4. Continue.dev
Configuration Method: .continuerc.json or config.json
Continue supports:
- Custom context providers
- Documentation references
- Project-specific prompts
5. Tabnine
Configuration Method: Inline patterns
Tabnine learns from:
- Codebase patterns
- Team standards (enterprise)
Sync Strategies
Strategy 1: Reference-Based (Recommended)
Concept: Other tools reference Claude Skills without duplicating content.
Benefits:
- Single source of truth (Claude Skills)
- Easy to maintain
- No duplication
- Clear ownership
Implementation:
# .cursorrules
This project uses Claude Skills for detailed technical guidance.
## Framework Guidance
For Textual TUI development patterns, see:
- `.claude/skills/textual/SKILL.md` - Core concepts and patterns
- `.claude/skills/textual/quick-reference.md` - Quick lookups
When suggesting Textual code:
1. Follow patterns in `.claude/skills/textual/`
2. Use semantic color variables ($primary, $error, etc.)
3. Prefer composition over inheritance
4. Use reactive attributes for state
## Git Hook Management
For git hook configuration with hk, see:
- `.claude/skills/hk/SKILL.md` - Setup and patterns
- `.claude/skills/hk/reference.md` - Detailed options
## Testing Patterns
For pytest conventions, see:
- `.claude/skills/pytest-patterns/` (if exists)
Strategy 2: Summary-Based
Concept: Create condensed summaries of skills for other tools.
Benefits:
- Self-contained for each tool
- No file path dependencies
- Works with limited context windows
Implementation:
# .cursorrules
## Textual TUI Framework
This project uses Textual for building terminal UIs.
### Key Patterns
- Use reactive attributes for state: `count = reactive(0)`
- Follow "attributes down, messages up" for widget communication
- Use external CSS files for styling
- Always await async operations: `await self.mount(widget)`
### Common Mistakes to Avoid
- Don't modify reactives in __init__ (use on_mount)
- Always use `await pilot.pause()` in tests
- Don't block the event loop (use @work decorator)
For comprehensive guidance: `.claude/skills/textual/`
[More condensed summaries...]
Strategy 3: Shared Documentation
Concept: Create a central docs/ directory that all tools reference.
Benefits:
- Clear documentation structure
- Easy for humans to read
- Tools can reference same files
- Good for team onboarding
Structure:
docs/
├── frameworks/
│ ├── textual.md # Extracted from Claude Skill
│ └── pytest.md
├── patterns/
│ ├── testing.md
│ └── async.md
└── conventions/
├── code-style.md
└── git-workflow.md
.cursorrules # References docs/*
.claude/skills/ # Detailed skills
Implementation Guides
Creating .cursorrules
Basic Template:
# Project: [Project Name]
## Overview
[Brief project description]
## Tech Stack
- **Framework**: Textual (TUI framework)
- **Testing**: pytest with async support
- **Tools**: hk (git hooks), ruff (linting)
## AI Guidance Sources
This project maintains detailed knowledge in Claude Skills (`.claude/skills/`).
For comprehensive guidance on:
- **Textual framework**: `.claude/skills/textual/`
- **Git hooks (hk)**: `.claude/skills/hk/`
- **[Other skills]**: `.claude/skills/[name]/`
## Key Patterns
### Textual Development
1. **Widget Structure**
```python
class MyWidget(Widget):
count = reactive(0)
def compose(self) -> ComposeResult:
yield ChildWidget()
-
Testing Pattern
async with app.run_test() as pilot: await pilot.click("#button") await pilot.pause() # Critical! -
CSS Styling
- Use semantic colors:
$primary,$error,$success - FR units for flexible sizing:
width: 1fr; - Dock for fixed elements:
dock: top;
- Use semantic colors:
Code Quality
- Run
hk checkbefore committing - All tests must pass
- Type hints required
- Use ruff for formatting
Common Mistakes
- ❌ Don't modify reactives in
__init__ - ❌ Don't forget
await pilot.pause()in tests - ❌ Don't block the event loop
- ✅ Use
@workdecorator for async operations - ✅ Use
set_reactive()for init-time values
Project Structure
src/
├── app.py # Main app
├── screens/ # Screen classes
├── widgets/ # Custom widgets
└── business_logic/ # Separate from UI
Additional Context
For detailed explanations, examples, and troubleshooting:
- Check relevant skill in
.claude/skills/ - Refer to framework documentation
- See examples in existing codebase
### Integrating with Cursor AI
**Step 1: Create .cursorrules**
```bash
# Generate .cursorrules from skills
cat > .cursorrules << 'EOF'
# [Content from template above]
EOF
Step 2: Test Integration
- Open project in Cursor
- Ask Cursor: "How should I create a Textual widget?"
- Verify it references patterns from .cursorrules
Step 3: Maintain Sync
When updating skills:
# Update .cursorrules with key changes
# Keep it concise - full details stay in .claude/skills/
Integrating with GitHub Copilot
Copilot learns from context, so:
Step 1: Add Context Comments
# This project uses Textual TUI framework
# Follow patterns in .claude/skills/textual/
# Key principle: "attributes down, messages up"
from textual.app import App
from textual.widget import Widget
Step 2: Create Documentation File
# docs/COPILOT_CONTEXT.md
## Development Context for AI Assistants
This file provides context for GitHub Copilot and similar tools.
### Framework: Textual
We use Textual for building terminal UIs. Key patterns:
[Include condensed patterns from skills]
For full details: `.claude/skills/textual/`
Step 3: Reference in README
# README.md
## For AI Assistants
Development guidance is available in:
- `.claude/skills/` - Comprehensive Claude Skills
- `docs/COPILOT_CONTEXT.md` - Quick reference for all AI tools
Integrating with Continue.dev
Step 1: Create Context Provider
// .continue/config.json
{
"contextProviders": [
{
"name": "skills",
"type": "file",
"params": {
"patterns": [
".claude/skills/*/SKILL.md",
".claude/skills/*/quick-reference.md"
]
}
}
]
}
Step 2: Configure Custom Commands
{
"customCommands": [
{
"name": "textual-help",
"prompt": "Refer to .claude/skills/textual/ and help with: {input}",
"description": "Get Textual framework help"
}
]
}
Sync Maintenance Workflow
When Creating a New Skill
-
Create Claude Skill (primary source)
mkdir -p .claude/skills/new-skill # Create SKILL.md, etc. -
Update .cursorrules (if needed)
## New Skill Topic Brief summary... For details: `.claude/skills/new-skill/` -
Update docs/ (if using shared docs)
# Extract key points to docs/ # Keep synchronized -
Test cross-tool
- Ask Claude and Cursor same question
- Verify consistent guidance
When Updating an Existing Skill
-
Update Claude Skill first
# Edit .claude/skills/skill-name/SKILL.md -
Review impact on other tools
- Check if .cursorrules needs updates
- Update summary content
- Sync shared docs
-
Test changes
- Verify updated guidance works
- Check for contradictions
Regular Sync Checks
Monthly:
- Review .cursorrules for accuracy
- Check shared docs are current
- Test sample queries across tools
Quarterly:
- Full audit of cross-tool consistency
- Update summaries with new patterns
- Refactor if needed
File Organization
Recommended Structure
project/
├── .cursorrules # Cursor AI context
├── .claude/
│ ├── skills/ # Primary knowledge base
│ │ ├── textual/
│ │ ├── hk/
│ │ └── ...
│ └── settings.local.json
├── docs/
│ ├── COPILOT_CONTEXT.md # Context for Copilot
│ ├── AI_GUIDANCE.md # General AI context
│ └── frameworks/ # Shared framework docs
├── README.md
---
*Content truncated.*
When not to use it
- →When project knowledge is not documented in Claude Skills
- →When the target AI tool does not support context files
Prerequisites
Limitations
- →Requires manual maintenance when skills are updated
- →Tool-specific context handling varies by platform
How it compares
Unlike manual configuration, this skill automates the synchronization of project context and standards across multiple AI tools using a single source of truth.
Compared to similar skills
skill-sync side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| skill-sync (this skill) | 12 | 9mo | Review | Intermediate |
| resolve-conflicts | 81 | 8mo | Review | Intermediate |
| openspec-onboard | 10 | 6mo | Review | Beginner |
| codex-cli-bridge | 9 | 9mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by KyleKing
View all by KyleKing →You might also like
resolve-conflicts
antinomyhq
Use this skill immediately when the user mentions merge conflicts that need to be resolved. Do not attempt to resolve conflicts directly - invoke this skill first. This skill specializes in providing a structured framework for merging imports, tests, lock files (regeneration), configuration files, and handling deleted-but-modified files with backup and analysis.
openspec-onboard
studyzy
Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.
codex-cli-bridge
alirezarezvani
Bridge between Claude Code and OpenAI Codex CLI - generates AGENTS.md from CLAUDE.md, provides Codex CLI execution helpers, and enables seamless interoperability between both tools
github-workflow-automation
ruvnet
Advanced GitHub Actions workflow automation with AI swarm coordination, intelligent CI/CD pipelines, and comprehensive repository management
git-advanced-workflows
wshobson
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
changelog-automation
wshobson
Automate changelog generation from commits, PRs, and releases following Keep a Changelog format. Use when setting up release workflows, generating release notes, or standardizing commit conventions.