workspace-org

Standardized workspace directory layout for multi-agent OpenClaw deployments. All agent-generated files go under files/ to keep root clean. Defines where agents store files, exchange deliverables, and cleanup policies. Trigger on workspace setup, file placement decisions, workspace cleanup, multi-agent convention setup, workspace compliance check.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "workspace-org" with this command: npx skills add zaixi/workspace-org

Workspace Org

Standardized directory conventions for OpenClaw multi-agent workspaces.

Layout

workspace/                          ← or any agent workspace dir
├── AGENTS.md, SOUL.md ...         ← core config (never moved)
├── skills/                        ← ClawHub skills
├── memory/                        ← long-term memory
├── files/                         ← all agent-generated content
│   ├── tmp/       disposable temp files
│   ├── notes/     working docs worth keeping
│   ├── inbox/     deliverables from other agents
│   ├── outbox/    files for owner/other agents
│   ├── archive/   inactive projects
│   └── experts/   (workspace root only) expert engagements

Rules

  • Core config files stay at workspace root. Never moved.
  • All generated files go into files/{subdir}/. No exceptions.
  • Cross-agent handoff: sender writes to files/outbox/, receiver picks from files/inbox/.

Cleanup policy

SubdirCleanup rule
files/tmp/Eligible for auto-cleanup at any time
files/notes/Keep; never auto-clean
files/archive/Manual review before removal
files/experts/Remove after expert engagement ends
files/inbox/Clear after processing deliverable

Enforcement for future work

When creating files

All generated files go into files/ subdirectories:

  • Temp/one-off scripts, patches, downloads → files/tmp/
  • Keep-worthy docs, analysis, snapshots → files/notes/
  • Cross-agent handofffiles/inbox/ or files/outbox/
  • Old projectsfiles/archive/

Periodic compliance check

# Check if current workspace has layout violations
python3 {{SKILL_DIR}}/scripts/sweep.py

# JSON output for automation
python3 {{SKILL_DIR}}/scripts/sweep.py --json

Fix existing violations

python3 {{SKILL_DIR}}/scripts/apply.py --execute

HEARTBEAT.md can include a periodic sweep to catch drift.

Scripts

scripts/apply.py

Creates files/ and sub-directories, migrates existing files into correct locations. Auto-detects workspace root vs agent workspace. Dry-run by default. Agent directories (containing AGENTS.md) are never moved.

scripts/sweep.py

Audits workspace for layout violations. Returns exit code 0 (clean), 1 (warnings), or 2 (violations).

References

  • layout.md — Full specification with agent-type variations

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Web3

Claw-Net

Ask a question in plain English, get data from 13,000+ APIs in one call. Crypto prices, social data, market intelligence. Every response is cryptographically...

Registry SourceRecently Updated
3081Profile unavailable
Web3

ClawPay-Hedera

Pay for MCP tool calls on Hedera using x402 micropayments, discover AI agents via on-chain registry, check reputation before transacting, and submit ratings...

Registry SourceRecently Updated
2210Profile unavailable
Web3

Governance Inheritance

Hierarchical policy inheritance system for OpenClaw agents. Enables policies to be defined at organization, team, project, and session levels with automatic...

Registry SourceRecently Updated
2430Profile unavailable
Web3

oudated-noa

Citizen skill for the Nation of Agents — authenticate with your Ethereum wallet, communicate via Matrix, trade and collaborate with other AI agents.

Registry SourceRecently Updated
2290Profile unavailable