Skip to main content
skillsFirst-partyReview first Safety · Privacy ·

OpenClaw Operator Capability Pack Skill

Expert OpenClaw operator capability skill for secure deployment, policy governance, tool boundaries, and production observability.

by JSONbored·added 2026-04-10·373,140 source repo stars·
Claude CodeCodexWindsurfGeminiCursorCLI
HarnessClaude CodeCodexWindsurfGeminiCursorCLI
Level:expertType:capability-packVerified:validated
Review first review before installing

Open the source and read safety notes before installing.

Prerequisites

  • OpenClaw environment access
  • Policy/security requirements
  • Monitoring and alerting platform

Schema details

Install type
package
Reading time
9 min
Difficulty score
87
Troubleshooting
Yes
Breaking changes
No
Source repository stats
Scope
Source repo
Stars
373,140 source repo stars
Forks
77,409
Updated
2026-05-19T11:43:27Z
Package metadata
Package verified
Yes
SHA-256
d67f69f050a67f21b64fd103dc9a901b46624621d7aaae84606ba3f657c12749
Skill and platform metadata
Skill type
capability-pack
Skill level
expert
Verification
validated
Verified at
2026-04-10
Retrieval sources
https://github.com/openclaw/openclawhttps://github.com/openclaw/openclaw/blob/main/README.mdhttps://github.com/openclaw/openclaw/blob/main/CONTRIBUTING.md
Tested platforms
ClaudeCodexOpenClawCursorWindsurfGemini
PlatformSupportInstall path
claude-codeNative.claude/skills/<skill-name>/SKILL.md
codexNative.agents/skills/<skill-name>/SKILL.md
windsurfNative.windsurf/skills/<skill-name>/SKILL.md
geminiNative.gemini/skills/<skill-name>/SKILL.md or .agents/skills/<skill-name>/SKILL.md
cursorAdapter.cursor/rules/<skill-name>.mdc
cliManualAGENTS.md or tool-specific context file
Full copyable content
# Trigger
"Use the OpenClaw operator capability pack for this environment."

# Required output
1) Deployment and trust-boundary map
2) Tool and permission policy matrix
3) Observability and SLO plan
4) Incident and recovery procedures

About this resource

Knowledge Freshness

This capability pack is pinned to documentation verified on 2026-04-10. When upstream docs change, refresh endpoint contracts, examples, and constraints before using this skill for production changes.

Retrieval Sources

Always prefer direct retrieval from official docs/API references over model memory for limits, endpoint signatures, and behavior guarantees.

Core Workflow

  1. Confirm target version/runtime and pull latest official docs for the task scope.
  2. Build an execution plan with explicit read-only discovery before any mutation.
  3. Validate contracts, permissions, and safety constraints before applying changes.
  4. Execute with deterministic checkpoints and rollback criteria.
  5. Produce a verification report with evidence, caveats, and next actions.

Overview

This capability pack teaches agents to operate OpenClaw in production responsibly. It covers governance, privilege boundaries, runtime controls, and incident readiness.

Capability Scope

  • Runtime architecture and isolation
  • Tool governance and approval workflows
  • Cost/latency/reliability controls
  • Auditability and compliance-ready logs
  • Incident containment and recovery

Compatibility

Native

  • Claude Code / Claude: native skill usage via SKILL.md.
  • Codex/OpenAI workflows: compatible with Agent Skills-style SKILL.md content as reusable workflow instructions.

Manual Adaptation

  • Gemini CLI: native skill usage via .gemini/skills/<skill-name>/SKILL.md or .agents/skills/<skill-name>/SKILL.md where supported.
  • Cursor: use the generated .cursor/rules/*.mdc adapter for project rules.
  • OpenClaw and similar agents: use the same skill content as a reusable prompt/workflow file when native skill import is unavailable.

Production Rules

  • Treat agent tool access as privileged surface.
  • Prefer explicit approvals for high-impact actions.
  • Segment environments and secrets by risk.
  • Keep response plans tested and documented.

Troubleshooting

Issue: Agents exceed intended permission scope
Fix: Move to strict allowlists with per-tool approvals.

Issue: Hard to diagnose cross-agent failures
Fix: Add trace IDs and event correlation across all agent actions.

Issue: Cost spikes during autonomous runs
Fix: Add budget limits and route heavy tasks to cheaper model/tool paths.

Output Contract

  1. Provide an implementation plan ordered by risk and dependency.
  2. Provide exact production-ready config/commands with no placeholders.
  3. Call out secrets, permissions, and least-privilege requirements.
  4. Include rollback and recovery guidance for each risky step.

Validation Checklist

  • Verify all referenced docs/versions before applying changes.
  • Run regression checks for core user flow and error paths.
  • Confirm observability/logging is enabled for changed components.
  • Confirm security controls (auth, rate limits, input validation) still pass.
  • Record final known limitations and follow-up actions.
#openclaw#ai-agents#operations#security#capability-pack

Source citations

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.