defragmenter
Structural knowledge defragmentation for OpenClaw workspaces. Finds information, rules, and operational facts that are spread across the wrong files or embedded in the wrong layer, then rewrites them into the proper files without deleting source material. Use when the workspace feels fragmented, logic is embedded in cron/jobs instead of flow files, preferences are scattered, or facts exist but are not assembled into one coherent working structure.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/balukov/defragmenterDefragmenter
defragmenter is a structural reorganization skill for OpenClaw workspaces.
It does not behave like a cleaner, trash collector, or memory compressor. It does not delete information.
Its job is to find knowledge that already exists, but is fragmented across the wrong places, and reassemble it into the correct structural locations.
What It Does
Defragmenter looks for situations like:
- logic living inside a cron message instead of a flow file
- operational facts existing in chat or notes but not in
CONTAINER_STATE.md - preferences mentioned in conversation but not recorded in the right preference file
- workflow rules spread across multiple files without a clear source of truth
- facts that exist, but are not assembled into one coherent working structure
Then, after user confirmation, it:
- copies or rewrites that knowledge into the proper file (from the Allowed Targets list only)
- preserves the existing information rather than deleting it
- makes the workspace more structurally coherent
Core Principle
Reorganize, not destroy.
Defragmenter may:
- move logic to the correct file
- duplicate essential context into the correct source-of-truth file
- rewrite instructions into a cleaner structure
- connect fragmented pieces of working knowledge
Defragmenter does not:
- delete source material by default
- prune history
- compress memory for brevity
- behave like a cleanup/trash skill
Typical Use Cases
Use this skill when:
- the workspace feels architecturally messy
- the right information exists, but in the wrong place
- a workflow is half in chat, half in cron, half in files
- operational state has drifted away from documentation
- multiple files describe the same process, but no file is the clear source of truth
Examples
Example 1: Cron logic is too smart
A cron message contains detailed workflow logic.
Defragmenter should:
- extract that logic into a flow file
- reduce the cron to a simple trigger
- preserve the intent without deleting history
Example 2: Operational facts are stranded
A container repair decision exists in chat or daily notes, but not in CONTAINER_STATE.md.
Defragmenter should:
- rewrite the important fact into
CONTAINER_STATE.md - add or update restore instructions if appropriate
Example 3: Preferences are scattered
Food, browser, or workflow preferences exist in conversation history but not in their proper file.
Defragmenter should:
- gather them into the correct preference/source-of-truth file
Allowed Targets
Defragmenter may only reorganize knowledge into files within the current workspace that match these patterns:
MEMORY.mdmemory/*.mdCONTAINER_STATE.mdflows/*.md- preference files within the current workspace root
Defragmenter must not modify:
- Any file under
skills/or anySKILL.mdfile (including its own) - Shell scripts, executables,...
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-balukov-defragmenter": {
"enabled": true,
"auto_update": true
}
}
}