Stores durable facts in a categorized, plain-markdown vault on disk, alongside your agent's built-in memory.
Memory
dotfile
Try itSynchronization management with external tools. agents - Windows+WSL ~/.agents share + ~/.claude/plugins split layout [agents.md], chezmoi - dotfile template management [chezmoi.md], knowledge - session knowledge → Serena memory [knowledge.md], mcp - MCP server synchronization [mcp.md], syncthing - chezmoi Syncthing sync and diagnostics [syncthing.md]. Use when "knowledge sync", "chezmoi add", "dotfile management", "syncthing", "MCP server add", "MCP sync", "external sync", "(?d)", ".stignore", "ignored files", "stignore settings", "sync incomplete", "sync status", "DB reset", "stale cache", "syncthing diagnostics", "index reset", "rescan", "encryption consistency", "Failed to verify encryption", "receive-encrypted mismatch", "garbage encryptionPassword", "Antigravity Syncthing", "Gemini Syncthing re-register", "Windows WSL agents layout", "plugins split", "marketplace EACCES". For ClawHub-related tasks → delegate to /clawhub skill.
What it does
Manages data synchronization with external tools (Serena, chezmoi, Syncthing, etc.).
The skill document
Sync
Manages data synchronization with external tools (Serena, chezmoi, Syncthing, etc.).
Topics
| Topic | Description | Guide |
|---|---|---|
| agents | Windows+WSL multi-agent share layout (~/.agents source of truth + ~/.claude/plugins split) | agents.md |
| chezmoi | dotfile chezmoi template management | chezmoi.md |
| knowledge | Session knowledge → Serena memory sync | knowledge.md |
| mcp | MCP server sync (delegated to chezmoi) | mcp.md |
| syncthing | chezmoi source Syncthing sync and diagnostics | syncthing.md |
Quick Reference
Agents Layout (Windows + WSL)
"Windows WSL agents layout" → ~/.agents source of truth, ~/.claude/{skills,rules,agents} symlinks
"plugins split" → Why ~/.claude/plugins/ is NOT shared
"marketplace EACCES" → Recovery for plugin marketplace rename collisions
Bootstrap script: ~/.agents/skills/dotfile/scripts/link-shared-ai-configs.{sh,ps1}
- Creates symlinks from
~/.agents/{skills,rules,agents}/into Claude / Codex / Gemini / Antigravity - Idempotent + auto-backup to
.bak/-
Knowledge Sync
"knowledge sync" → Current project session → Serena memory
Chezmoi
"chezmoi add" → Add a dotfile to chezmoi
"dotfile management" → chezmoi template operations
Configurations managed by chezmoi:
~/.utcp_config.json- UTCP global config~/.claude.json,~/.cursor/mcp.json- MCP server config~/Library/.../Syncthing/config.xml- Syncthing default config
MCP server sharing:
- Single source:
.chezmoitemplates/mcp-servers.json chezmoi apply→ Automatically applied to all apps
MCP
"MCP server add" → Edit mcp-servers.json → chezmoi apply
"MCP sync" → Apply MCP config to all apps
Syncthing
"syncthing setup" → chezmoi source sync configuration
".stignore" → Ignore pattern configuration
"sync incomplete" → Per-folder status/need item diagnostics
"encryption consistency"→ Garbage encryptionPassword diagnosis & API PUT cleanup
"DB reset" → Stale index reset (delete index-v2)
Auto-generated .stignore:
.git(?d).DS_Store— Prevents orphaned.DS_Storeon remote deletion*.bak
Related skills
Generate and edit Draw.io, Mermaid, and Excalidraw diagrams from natural language using a structured JSON spec.
Join a video meeting as an AI bot with voice, avatar, and screenshare across four operating modes.
Find why your productivity system keeps failing, then apply the smallest fix — capacity math, bottleneck routing, durable local notes.
Run Git operations — commits, branches, merges, rebases, conflict resolution, and recovery — with safety rules enforced.
Write, debug, and tune Playwright specs with locator strategy, trace diagnosis, and CI-aware timeouts.
More from drumrobot
Browse all skillsRun a 4-stage research → plan → review → TDD-implement workflow for code changes with optional PR capture.
Manage Claude Code sessions: lookup, search, repair, migration, compression, and cleanup in one command surface.
Manage Git worktrees, ghq clones, SourceGit registration, and multi-account credentials with safety checks.
Diagnose agent mistakes, harden the prompt that caused them, and finish the original task.
Convert plans and code changes into GitHub issues and PRs, with auth handling, dependency tracking, and pre-publish scans.
Convert functionality into Claude Code automations (Agent, Skill, Rule, Hook, Command)