Versioned migration procedures for upgrading blueprint structure between format versions
Migrates blueprint structures between format versions with safe file operations and user confirmation.
/plugin marketplace add laurigates/claude-plugins/plugin install blueprint-plugin@lgates-claude-pluginsThis skill is limited to using the following tools:
migrations/v1.0-to-v1.1.mdmigrations/v1.x-to-v2.0.mdmigrations/v2.x-to-v3.0.mdExpert skill for migrating blueprint structures between format versions. This skill is triggered by /blueprint:upgrade and handles version-specific migration logic.
.claude/blueprints/.manifest.json for current version1. Read current manifest version
2. Compare with target version (latest: 3.0.0)
3. Load migration document for version range
4. Execute migration steps sequentially
5. Confirm each destructive operation
6. Update manifest to target version
7. Report migration summary
| From | To | Document |
|---|---|---|
| 1.0.x | 1.1.x | migrations/v1.0-to-v1.1.md |
| 1.x.x | 2.0.0 | migrations/v1.x-to-v2.0.md |
| 2.x.x | 3.0.0 | migrations/v2.x-to-v3.0.md |
# Read manifest version - check both v3.0 and legacy locations
if [[ -f docs/blueprint/.manifest.json ]]; then
cat docs/blueprint/.manifest.json | jq -r '.format_version'
elif [[ -f .claude/blueprints/.manifest.json ]]; then
cat .claude/blueprints/.manifest.json | jq -r '.format_version'
fi
# Detect v1.0 (no format_version field)
if ! jq -e '.format_version' .claude/blueprints/.manifest.json > /dev/null 2>&1; then
echo "v1.0.0"
fi
For detecting modifications to generated content:
# Generate SHA256 hash of file content
sha256sum path/to/file | cut -d' ' -f1
# Compare with stored hash in manifest
jq -r '.generated.skills["skill-name"].content_hash' .claude/blueprints/.manifest.json
When executing migrations:
If migration fails:
| Operation | Command |
|---|---|
| Check version | jq -r '.format_version' .claude/blueprints/.manifest.json |
| Hash file | sha256sum file | cut -d' ' -f1 |
| Safe move | cp -r source target && rm -rf source |
| Check empty dir | [ -z "$(ls -A dir)" ] |
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.