config-backup
Use when users want to save, backup, copy, export, or version control their Claude Code configuration files (commands, skills, agents) from ~/.claude/ to another directory. Triggered by phrases like "save my claude settings", "backup my claude config", "sync claude configuration", "copy ~/.claude to somewhere", "export my commands and skills", or "archive claude settings before making changes".
What this skill does
# Config Backup Skill
This skill helps users backup their Claude Code configuration files from `~/.claude/` to a specified target directory. It copies the `commands/`, `skills/`, and `agents/` directories with options for selective backup.
## What Gets Backed Up
By default, this skill backs up three directories from `~/.claude/`:
- **commands/** - All slash command definitions
- **skills/** - All agent skills and their resources
- **agents/** - All subagent definitions
These are the user-created configurations that define custom Claude Code behavior.
## When to Use This Skill
Use this skill when users want to:
- Backup Claude configurations before making changes
- Copy configurations to another machine or project
- Share custom setup with others
- Migrate to a new system
- Version control configurations
## Backup Workflow
Follow this workflow when performing a backup:
### 1. Confirm Target Directory
Always confirm the target directory, even though the default is the current working directory. Ask like this:
```
"Target directory: [current-working-directory]
Is this correct, or would you like to specify a different location?"
```
Wait for user confirmation before proceeding.
### 2. Select Directories to Backup
Ask the user which directories to include. Present this interactive prompt:
```
"Which directories would you like to backup?
- commands/
- skills/
- agents/
Backup all three, or specify which ones to include?"
```
If the user doesn't specify, backup all three. If they specify a subset, only backup those.
### 3. Execute the Backup Script
Use the backup script located at `scripts/backup.sh` within this skill directory. Execute it with appropriate parameters:
```bash
~/.claude/skills/config-backup/scripts/backup.sh [target-dir] [directories...]
```
Parameters:
- `target-dir`: Target directory (default: current directory if not specified)
- `directories...`: Space-separated list of directories to backup (commands, skills, agents)
The script will:
- Create target directory if it doesn't exist
- Use `rsync` if available (efficient copying), otherwise fallback to `cp -r`
- Overwrite existing files without prompting
- Preserve directory structure
- Exit with error if source `~/.claude/` doesn't exist
### 4. Report Results
After the backup completes, show the user a detailed list of what was copied:
```
✅ Backup complete!
Copied directories:
- commands/ (15 files)
- skills/ (8 directories, 42 files)
- agents/ (23 files)
Target: /path/to/target/directory
```
If any errors occurred during the backup (permission errors, missing source, etc.), report them clearly to the user.
## Error Handling
The backup script handles these scenarios:
### Target Directory Doesn't Exist
Creates the directory automatically. No user action needed.
### Source Directory Missing
If `~/.claude/` doesn't exist, the script exits with error message:
```
❌ Error: Source directory ~/.claude/ not found
```
### No Write Permissions
If target directory isn't writable, shows:
```
❌ Error: Permission denied writing to [target-dir]
```
### rsync Not Available
Automatically falls back to `cp -r` command. User sees:
```
⚠️ rsync not available, using cp instead
```
## Examples
### Example 1: Backup All Directories to Current Location
User: "save my claude settings"
Assistant: "I'll backup your Claude configurations.
Target directory: /Users/choi/work/claude-config
Is this correct, or would you like to specify a different location?
Which directories would you like to backup?
- commands/
- skills/
- agents/
Backup all three, or specify which ones to include?"
[User confirms]
[Executes backup, reports results]
### Example 2: Backup Only Commands and Skills
User: "backup my commands and skills"
[Asks about target directory, then only backs up commands/ and skills/]
### Example 3: Specify Custom Target
User: "copy ~/.claude to ~/backups/claude-config"
[Asks for confirmation, then backs up to ~/backups/claude-config]
## Best Practices
- **Always confirm target directory** before copying to avoid accidental overwrites
- **Show clear feedback** about what was copied so user knows backup succeeded
- **Handle errors gracefully** with helpful error messages
- **Use rsync when available** for efficient incremental backups
- **Preserve structure** so restore is straightforward
- **Overwrite without asking** per user requirements (user should confirm target upfront)
## Technical Details
### Script Location
The backup script is at: `~/.claude/skills/config-backup/scripts/backup.sh`
### Copy Method
- Prefers `rsync -av --delete` for efficient copying with deletion of orphaned files
- Falls back to `cp -rf` if rsync unavailable
- Always preserves permissions and timestamps
- Creates target directories as needed with `mkdir -p`
### Directory Structure
The backup preserves this structure:
```
target-dir/
├── commands/
│ ├── command1.md
│ └── command2.md
├── skills/
│ ├── skill1/
│ └── skill2/
└── agents/
├── agent1.md
└── agent2.md
```
## See Also
- Troubleshooting common issues: `references/troubleshooting.md`
- Detailed backup workflow examples: `examples/backup-workflows.md`
- The backup script implementation: `scripts/backup.sh`
- Claude Code skill documentation for skill structure
- Advanced usage: Pipe backup to tar for archiving, sync to remote with rsync over ssh
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.