Executes OpenClaw tools through a two-layer security policy guard for safe automation.

Install

mkdir -p .claude/skills/openclaw && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/19186" && unzip -o skill.zip -d .claude/skills/openclaw && rm skill.zip

Installs to .claude/skills/openclaw

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

How to invoke OpenClaw tools with operator policy guards
56 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Invoke an OpenClaw tool
  • Guard tool invocation with operator policy
  • Check arguments against defined rules before execution
  • Return blocked status and reason for policy violations

How it works

This skill invokes an OpenClaw tool by passing the tool name and arguments through a two-layer guard: an operator policy and connector execution. It returns a blocked status if policy rules are violated.

Inputs & outputs

You give it
A tool name and arguments in JSON format
You get back
The result of the tool invocation or a blocked status with reason

When to use openclaw

  • Running browser automation
  • Executing restricted tools
  • Verifying tool usage against policy

About this skill

OpenClaw — Reference Skill

Authentication

  • Configured via connector
  • Connector: tesseract_operator/connectors/openclaw.py
  • Skills: tesseract_operator/skills/openclaw_skills.py
  • Policy: tesseract_operator/rules/openclaw.py

Available Skills (1 total)

SkillRiskMCPDescription
openclaw.invokeHIGHInvoke an OpenClaw tool (policy-guarded)

⚠️ CRITICAL: This skill is HIGH risk and NOT MCP-exposed. It goes through a 2-layer guard: operator policy (evaluate_openclaw_tool) + connector execution.

Usage Pattern

# Tool invocation is guarded by operator policy
result = openclaw_invoke(ctx, tool="browser", args_json='{"action": "navigate", "url": "..."}')
if result.get("blocked"):
    print(f"Blocked: {result['reason']}")

Known Gotchas

  1. OpenClaw policy rules are in tesseract_operator/rules/openclaw.py
  2. Blocked tools return {"ok": False, "blocked": True, "reason": "..."}
  3. Tool policy violations were a known mission failure cause (fixed Mar 2026)

When not to use it

  • When direct, unguarded tool invocation is desired
  • When the tool is MCP-exposed
  • When policy rules are not defined

Limitations

  • This skill is HIGH risk
  • Not MCP-exposed
  • Requires OpenClaw policy rules to be defined

How it compares

This skill adds a policy layer to OpenClaw tool invocation, ensuring that actions are checked against defined rules before execution, unlike direct, unguarded tool calls.

Compared to similar skills

openclaw side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
openclaw (this skill)01moNo flagsIntermediate
windows-ui-automation178moReviewAdvanced
linux-production-shell-scripts76moReviewIntermediate
cursor-prod-checklist410dReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

windows-ui-automation

martinholovsky

Expert in Windows UI Automation (UIA) and Win32 APIs for desktop automation. Specializes in accessible, secure automation of Windows applications including element discovery, input simulation, and process interaction. HIGH-RISK skill requiring strict security controls for system access.

17126

linux-production-shell-scripts

davila7

This skill should be used when the user asks to "create bash scripts", "automate Linux tasks", "monitor system resources", "backup files", "manage users", or "write production shell scripts". It provides ready-to-use shell script templates for system administration.

746

cursor-prod-checklist

jeremylongshore

Execute production readiness checklist for Cursor IDE setup. Triggers on "cursor production", "cursor ready", "cursor checklist", "optimize cursor setup". Use when working with cursor prod checklist functionality. Trigger with phrases like "cursor prod checklist", "cursor checklist", "cursor".

434

openevidence-prod-checklist

jeremylongshore

Production readiness checklist for OpenEvidence clinical AI deployments. Use when preparing for production launch, conducting pre-deployment reviews, or auditing OpenEvidence integration for compliance. Trigger with phrases like "openevidence production", "openevidence go-live", "openevidence checklist", "deploy openevidence", "openevidence readiness".

13

posthog-enterprise-rbac

jeremylongshore

Configure PostHog enterprise SSO, role-based access control, and organization management. Use when implementing SSO integration, configuring role-based permissions, or setting up organization-level controls for PostHog. Trigger with phrases like "posthog SSO", "posthog RBAC", "posthog enterprise", "posthog roles", "posthog permissions", "posthog SAML".

13

prowler-provider

prowler-cloud

Creates new Prowler cloud providers or adds services to existing providers. Trigger: When extending Prowler SDK provider architecture (adding a new provider or a new service to an existing provider).

13

Search skills

Search the agent skills registry