← Back to Skills Marketplace
mars2003

Workspace Governance

by Mars YANG · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
64
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install workspace-governance
Description
A methodology-first workspace governance skill for AI agents. Focuses on principles, decision framework, and safe execution patterns instead of fixed directo...
Usage Guidance
This skill appears coherent and self-contained. Before installing, review SKILL_ADAPT.yaml and any platform overlay (tools/adapt-profiles/*) to ensure the declared workspace_root, log file path, and protected/immutable lists match your expectations. Run the included local checks (bash scripts/check_*.sh or make check) in a safe environment to verify behavior. If you plan to run it non-interactively, ensure the runtime provides a safe confirmation channel (or accept that the skill will block on 'ask-user' items). Finally, confirm that logging.file in SKILL_ADAPT.yaml points to an appropriate location to avoid writing logs to sensitive directories.
Capability Analysis
Type: OpenClaw Skill Name: workspace-governance Version: 1.0.0 The workspace-governance skill bundle is a well-structured framework designed to help AI agents manage files safely. It emphasizes defensive principles such as 'plan before action,' mandatory dry runs, and explicit user confirmation for destructive operations. The configuration files (SKILL_ADAPT.yaml and platform profiles in tools/adapt-profiles/) specifically list sensitive files (e.g., .env, SSH keys, credentials) and directories to be protected from modification. The included shell scripts in the scripts/ directory are simple validation tools that use grep to ensure configuration integrity and do not contain any malicious logic or network activity.
Capability Assessment
Purpose & Capability
Name/description match the actual contents: a methodology-first governance contract plus optional per-platform overlays and validation scripts. The included platform profiles and check scripts (OpenClaw, Hermes, Cursor, Claude) are appropriate for a governance skill that adapts to different runtimes.
Instruction Scope
SKILL.md explicitly instructs the agent to read SKILL_ADAPT.yaml and platform overlay profiles (tools/adapt-profiles/*) and to scan only within a declared workspace_root. That is expected for this skill, but it does mean the agent will read repository files and may inspect environment detection signals (e.g., OPENCLAW_HOME, HERMES_HOME) to choose overlays — the user should be comfortable with local file inspection. The skill also enforces confirmation gates for destructive actions and a non-interactive 'blocked' policy, which limits risky autonomous behavior.
Install Mechanism
Instruction-only skill with no install spec. Files are repository docs and small shell validation scripts (grep/grep checks); nothing downloads or executes remote artifacts. This is the lowest-risk install posture.
Credentials
The skill declares no required environment variables or credentials. Platform profiles reference environment names only as detection signals (to decide which overlay to load), which is proportionate to a policy/adaptation role. No secret-exfiltration or credential requirements are present.
Persistence & Privilege
always:false and normal model invocation settings. The skill does not request permanent platform-wide privileges or modifications to other skills. It does propose writing governance logs (SKILL_ADAPT.yaml logging.file) — users should confirm desired log location and permissions before enabling.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install workspace-governance
  3. After installation, invoke the skill by name or use /workspace-governance
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release
Metadata
Slug workspace-governance
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Workspace Governance?

A methodology-first workspace governance skill for AI agents. Focuses on principles, decision framework, and safe execution patterns instead of fixed directo... It is an AI Agent Skill for Claude Code / OpenClaw, with 64 downloads so far.

How do I install Workspace Governance?

Run "/install workspace-governance" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Workspace Governance free?

Yes, Workspace Governance is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Workspace Governance support?

Workspace Governance is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Workspace Governance?

It is built and maintained by Mars YANG (@mars2003); the current version is v1.0.0.

💬 Comments