By sitapix
Automerge Swift CRDT skills, commands, and hooks — Document API, Codable mapping, sync protocol, auditing, and guardrails
Use this agent when the user wants to audit their Automerge Swift code for anti-patterns, or when reviewing code that uses the automerge-swift package. Automatically scans for the initial data problem, String-vs-Text misuse, missing error handling, sync protocol issues, and ObjId mismanagement — prevents merge garbage, silent data loss, and hard-to-debug runtime errors. <example> user: "Can you check my Automerge code for issues?" assistant: [Launches automerge-auditor agent] </example> <example> user: "Review my CRDT code for best practices" assistant: [Launches automerge-auditor agent] </example> <example> user: "Audit my collaborative editing implementation" assistant: [Launches automerge-auditor agent] </example> <example> user: "My merges are producing garbage, can you scan my code?" assistant: [Launches automerge-auditor agent] </example> <example> user: "Check if I'm using Automerge correctly" assistant: [Launches automerge-auditor agent] </example> Explicit command: Users can also invoke this agent directly with `/automerge:audit`
Look up Automerge Swift APIs, Document operations, Codable mapping, collaborative text, sync protocol, and schema patterns.
Use when working with Automerge Swift, automerge-swift package, CRDTs in Swift, collaborative/real-time data, Document merge/fork/sync, or any code importing Automerge. Routes to specialized sub-skills for core API, Codable mapping, sync protocol, and API reference. Even if the task seems simple, check this skill first - Automerge has non-obvious patterns that differ from typical Swift data handling.
Use when synchronizing Automerge documents between peers, implementing sync protocols over network/WebSocket, forking and merging documents, tracking change history, reading historical values, using patches for UI updates, or working with SyncState, ChangeHash, Change, Patch, or PatchAction types. Also use when asking 'how do I sync automerge documents', 'how do merges work', or 'how do I get notified of changes'.
Use when working with collaborative text editing in Automerge — AutomergeText, Cursor, Position, Mark, ExpandMark, spliceText, updateText, text marks/formatting, or building a collaborative text editor with Automerge. Also use when asking 'how do I do concurrent text editing', 'how do marks work', or 'AutomergeText vs String'.
Use when encoding/decoding Swift Codable types to/from Automerge documents, working with AutomergeEncoder or AutomergeDecoder, using AutomergeText for collaborative text fields, using Counter for concurrent counters, choosing SchemaStrategy, or deciding between Codable layer vs core API. Also use when you see 'automerge encoder', 'automerge decoder', 'AutomergeText', or schema strategy questions.
Use when creating Automerge documents, navigating with ObjId, reading/writing maps/lists/text using the core Document API, working with ScalarValue or Value types, or needing fine-grained control over document mutations. Use this instead of the Codable skill when you need performance (high-frequency updates) or when working with the low-level document structure directly.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Deep Automerge Swift CRDT expertise for AI coding assistants. Covers the Document API, Codable mapping, collaborative text, sync protocol, schema design, and troubleshooting.
Automerge Swift gives AI coding assistants focused guidance on the Automerge Swift CRDT library — Document creation and navigation, model encoding, real-time sync, collaborative text editing, and merge conflict resolution.
Status: Automerge Swift is in active development. Some routes or packaging paths may still be incomplete. If you hit a bug or something looks off, please open an issue.
# Add marketplace
/plugin marketplace add sitapix/automerge-swift-skills
# Install plugin
/plugin install automerge-swift@automerge-swift-marketplace
Add to your MCP config:
{
"mcpServers": {
"automerge-swift": {
"command": "npx",
"args": ["-y", "automerge-swift-mcp"]
}
}
}
Client-specific paths (VS Code, Cursor, Claude Desktop, Gemini CLI) are in the MCP setup guide.
Skills activate automatically based on your questions. Just ask:
"How do I create an Automerge Document and add nested data?"
"What's the right way to encode my model with AutomergeEncoder?"
"How do I sync two documents across devices?"
"My merge is producing garbage — help me debug it"
"What methods are available on Document?"
You can also use commands directly:
/automerge-swift:ask your question here
/automerge-swift:audit # scan code for anti-patterns
/skill automerge-swift-modeling # schema design, initial data problem
/skill automerge-swift-diag # debug errors and merge problems
8 skills organized into 3 lightweight entry points and 1 domain agent. Entry-point skills load inline for routing and quick answers. The domain agent handles deep API lookups in isolated context — the full reference runs in a separate agent and only the focused answer comes back.
Full documentation, skill catalog, and MCP server setup at sitapix.github.io/automerge-swift-skills.
Contributor setup, validation, and release notes live in .github/CONTRIBUTING.md.
npx claudepluginhub sitapix/automerge-swift-skills --plugin automerge-swiftSkills for SQLiteData by Point-Free: @Table models, @FetchAll/@FetchOne/@Fetch wrappers, GRDB-backed queries, migrations, and CloudKit SyncEngine.
Skills for Apple's text-editing stack: TextKit 1 and 2, UITextView, NSTextView, AttributedString, Core Text, Writing Tools, and the iOS 26 SwiftUI TextEditor.
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.
Memory compression system for Claude Code - persist context across sessions
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.