openclaw-self-eval

Audit OpenClaw agent foundational state and generate Markdown and JSON reports.

1|3|Updated Feb 20, 2026

Search Tags:#audit #drift #openclaw #agent-setup #self-eval #soul-file

Ready to run

npx skills add https://github.com/midnghtsapphire/revvel-standards --skill openclaw-self-eval

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: openclaw-self-eval
Source: https://github.com/midnghtsapphire/revvel-standards/tree/main/skills/openclaw-self-eval
Command: npx skills add https://github.com/midnghtsapphire/revvel-standards --skill openclaw-self-eval

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

OpenClaw Self-Eval audits the agent's foundational setup to surface missing components, misconfigurations, and drift before they impact operation.

Core Features & Use Cases

Soul audit: verifies the soul file exists, is non-empty, and recently updated.
Memory audit: checks reachability and freshness of memory stores and reports staleness.
Agent manifest audit: confirms AGENTS.md or per-agent manifest lists this agent and matches the persona.
Skill files audit: ensures each registered skill directory has SKILL.md and corresponding skill.yml and registry alignment.
Installers audit: verifies platform install scripts exist and are readable.
Persona audit: confirms persona presence and basic fields.
Vault/secrets audit: resolves references without exposing secret values.
Drift audit: reports deviations from last snapshot.

Quick Start

Run the OpenClaw Self-Eval against your agent root to produce a markdown report and a JSON summary.

Frequently Asked Questions about openclaw-self-eval

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I audit my agent setup for misconfigurations and drift?▼

An agent setup audit checks foundational state including soul files, memory stores, manifests, skills, and persona to surface misconfigurations and drift. It validates presence and alignment, then flags gaps with actionable fixes in a readable report.

What does a soul file audit check for in an OpenClaw agent?▼

A soul file audit verifies the soul file exists, is non-empty, and has been recently updated. This ensures the agent's foundational configuration maintains freshness and prevents operational staleness before issues impact performance.

Can I resolve secret references in a vault audit without exposing values?▼

Yes, vault and secrets audits resolve references without exposing actual secret values. All checks run in read-only mode, validating configuration security while generating reports that maintain strict confidentiality of sensitive credentials.

How do I verify my agent manifest and skill registry alignment?▼

Verifying agent manifest and skill registry alignment confirms AGENTS.md lists the agent and matches the persona. It ensures each registered skill directory contains SKILL.md and skill.yml files with proper registry alignment.

What is the best way to report configuration drift in an agent deployment?▼

Reporting configuration drift involves comparing the current agent state against a last snapshot. The audit generates a human-readable Markdown report plus a machine-readable JSON sidecar, detailing deviations for quick actionable resolution.

Does the agent self-eval audit modify any files during the check?▼

No, the self-eval audit runs entirely in read-only mode. It checks reachability, freshness, and alignment of memory stores, installers, and persona without modifying files, emitting results as a Markdown report and JSON sidecar.