workspace-reviewAudit workspace structure and memory files against OpenClaw conventions. Use when asked to "review workspace", "audit files", "check structure", or during periodic self-maintenance. Helps catch drift from standard patterns.
Install via ClawdBot CLI:
clawdbot install ortegarod/workspace-reviewA self-audit process to verify workspace files follow OpenClaw conventions and haven't drifted into non-standard patterns.
Verify expected files exist in correct locations:
~/.openclaw/workspace/
āāā AGENTS.md ā Operating instructions (REQUIRED)
āāā SOUL.md ā Persona/tone (REQUIRED)
āāā USER.md ā User profile (REQUIRED)
āāā IDENTITY.md ā Agent name/vibe/emoji (REQUIRED)
āāā TOOLS.md ā Local tool notes (REQUIRED)
āāā HEARTBEAT.md ā Heartbeat checklist (optional)
āāā MEMORY.md ā Curated long-term memory (optional)
āāā BOOT.md ā Runs on gateway restart (optional, boot-md hook)
āāā BOOTSTRAP.md ā One-time first-run ritual (delete after use)
āāā memory/ ā Daily logs + reference docs (vector-indexed)
ā āāā YYYY-MM-DD.md
āāā skills/ ā Workspace-specific skills (optional)Note on BOOT.md vs BOOTSTRAP.md:
BOOT.md ā Persistent; runs every gateway restart (if boot-md hook enabled)BOOTSTRAP.md ā One-time; agent follows it on first run, then deletes itCheck: Run ls -la on workspace root. Flag missing required files.
Each file has ONE job. Check for scope creep:
| File | Should Contain | Should NOT Contain |
|------|----------------|-------------------|
| AGENTS.md | Operating instructions, memory workflow, behavior rules | Personal memories, daily logs, tool configs |
| SOUL.md | Persona, tone, boundaries, identity philosophy | Task lists, technical details, credentials |
| USER.md | User profile, preferences, how to address them | Agent memories, system config |
| IDENTITY.md | Name, emoji, vibe, external identities (wallets, handles) | Instructions, memories |
| TOOLS.md | Environment-specific notes (camera names, SSH hosts, voices) | Skill instructions, operating procedures |
| HEARTBEAT.md | Short checklist for periodic checks | Long procedures, full documentation |
| MEMORY.md | Curated lessons, key context, important people/projects | Daily logs, raw notes |
| memory/*.md | Daily logs, raw notes, session summaries | Long-term curated memories |
Check: Skim each file. Flag content in wrong location.
YYYY-MM-DD.md or YYYY-MM-DD-slug.md formatsession-memory hook creates YYYY-MM-DD-slug.md) reviewed periodicallyproject-notes.md, api-guide.mdAutomatic Memory Flush: OpenClaw triggers a silent agent turn before session compaction to write durable memories. The agent receives a prompt to flush important context to memory/YYYY-MM-DD.md. This is automatic ā no action needed, but be aware your context WILL be compacted after ~180k tokens.
MEMORY.md and memory/*/.md are indexed by defaultYYYY-MM-DD.md; reference docs use descriptive namesmemory/ can be indexed via memorySearch.extraPaths in configSession Memory (Experimental): If memorySearch.experimental.sessionMemory = true, session transcripts are also indexed and searchable via memory_search.
ā ļø This workspace is PRIVATE. Never push to GitHub or any public remote.
cd ~/.openclaw/workspace && git statusLook for files that don't fit the standard layout:
ls -la ~/.openclaw/workspace/Flag anything that:
Note: Only MEMORY.md and memory/*/.md are vector-indexed. Files outside memory/ can be added via memorySearch.extraPaths in config.
Bootstrap files should be lean (loaded every session):
wc -l AGENTS.md SOUL.md USER.md IDENTITY.md HEARTBEAT.md TOOLS.md MEMORY.md 2>/dev/nullIf skills/ exists:
After review, report:
## Workspace Review ā YYYY-MM-DD
### ā
Passing
- [list what's correct]
### ā ļø Warnings
- [list minor issues]
### ā Issues
- [list things that need fixing]
### š Recommendations
- [specific actions to take]Generated Mar 1, 2026
A team building custom AI agents for clients uses the Workspace Review skill to ensure each agent's workspace adheres to OpenClaw conventions before deployment. This helps maintain consistency, avoid drift, and catch issues like missing required files or misaligned memory structures during weekly audits.
A large corporation deploys internal AI assistants across departments and runs periodic workspace reviews to verify compliance with security policies, such as checking for sensitive data in memory files and ensuring no public Git remotes. This skill aids in governance and reduces risks from non-standard patterns.
A solo consultant managing multiple AI agent projects for small businesses uses the skill to audit workspace structures after client updates or reorganizations. It helps catch scope creep in files like AGENTS.md and ensures memory hygiene, optimizing performance and maintaining clean, efficient workspaces.
An R&D lab experimenting with AI agents for scientific analysis employs the Workspace Review skill during heartbeat maintenance cycles to check vector search alignment and file sizes. This ensures bootstrap files remain lean and memory indexing functions correctly for efficient data retrieval.
A company using AI agents for automated customer support runs workspace reviews after major changes to tools or user profiles. The skill verifies that TOOLS.md and USER.md are up-to-date and free of irrelevant content, ensuring agents operate smoothly and adhere to defined conventions.
Offer a service where clients pay a monthly fee for ongoing workspace audits and maintenance using the Workspace Review skill. This includes periodic checks, issue resolution, and updates to ensure compliance with OpenClaw conventions, reducing client overhead and improving agent reliability.
Provide a fixed-price package for conducting comprehensive workspace reviews for clients setting up or restructuring AI agents. This includes generating reports with recommendations, fixing issues like rogue files or memory misalignment, and ensuring optimal performance based on the skill's guidelines.
License the Workspace Review skill as a built-in feature for AI development platforms or tools. This allows platform users to automatically audit their workspaces, with revenue generated through platform subscriptions, enterprise licenses, or premium feature add-ons for advanced analytics.
š¬ Integration Tip
Integrate the skill into automated workflows, such as CI/CD pipelines or scheduled cron jobs, to run periodic audits without manual intervention, ensuring continuous compliance and early issue detection.
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack š¦
Use the ClawdHub CLI to search, install, update, and publish agent skills from clawdhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawdhub CLI.
Clawdbot documentation expert with decision tree navigation, search scripts, doc fetching, version tracking, and config snippets for all Clawdbot features
Interact with Moltbook social network for AI agents. Post, reply, browse, and analyze engagement. Use when the user wants to engage with Moltbook, check their feed, reply to posts, or track their activity on the agent social network.
OpenClaw CLI wrapper ā gateway, channels, models, agents, nodes, browser, memory, security, automation.
MoltGuard ā runtime security plugin for OpenClaw agents by OpenGuardrails. Helps users install, register, activate, and check the status of MoltGuard. Use wh...