Workspace Review

Audit 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.

This skill appears to be what it says: a local workspace auditor with a small helper script. Before installing/running: 1) Inspect the included scripts yourself (scripts/workspace-status.sh) and run them locally to see the output; they are simple read-only checks. 2) Verify there are no secrets in your workspace (MEMORY.md, memory/*.md, .env) — the script already greps for 'sk-' tokens and .env. 3) Be aware the docs describe automatic memory-flush behavior (agent writes to memory/YYYY-MM-DD.md during compaction); if you have concerns about automatic memory writes, review your agent's compaction/memoryFlush config. 4) If you enable autonomous invocation, restrict when the agent may run workspace audits (require explicit user confirmation) because the skill's instructions could be invoked repeatedly. Overall the package is coherent and low-risk, but always review included code before granting execution rights.

Type: OpenClaw Skill Name: workspace-review Version: 1.0.2 The skill bundle is designed for a self-audit of the OpenClaw workspace, checking for adherence to conventions and potential security issues. All instructions in `SKILL.md` and commands in `scripts/workspace-status.sh` (e.g., `ls`, `git status`, `wc -l`) are standard and directly relevant to an audit. The `scripts/workspace-status.sh` includes a `grep -r -l "sk-"` command to identify potential API keys in markdown files, which is a security-conscious check to prevent data leaks, not an attempt at exfiltration. The documentation (`references/*.md`) consistently reinforces security best practices, such as keeping the workspace private and not committing secrets. There is no evidence of malicious intent, unauthorized data access, or prompt injection designed to subvert the agent's purpose.