A local-first development skill that audits codebases for robust error paths, input boundaries, timeout configurations, structured logging, and operation idempotency.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install review-error-handling
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install review-error-handling using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Review Error Handling?
The review error handling skill is a standalone development tool designed to audit codebases for critical failure states, input boundaries, timeout configurations, and operation idempotency. Operating entirely locally on the code or content provided, it requires no external connections to run, making it an excellent addition to Openclaw Skills repositories focused on code quality and security.
By systematically evaluating how code handles structural errors and boundaries, this skill ensures that system behavior remains predictable during failures. It empowers developers and AI agents to enforce architectural standards directly within their development workflows without leaking context to external APIs.
Review Error Handling Use Cases
- Reviewing pull requests to ensure new external or I/O calls have explicit, typed error handling paths instead of silent failures.
- Validating input boundaries for proper shape, range, and tenant scope enforcement prior to processing.
- Verifying that outbound network operations utilize timeouts and bounded retries with exponential backoff.
- Auditing logs and metrics to ensure that system failures emit sufficient contextual data for seamless engineering triage.
- Checking that data-mutating operations are properly designed to be idempotent under retry conditions.
How Review Error Handling Works
- Analyze Code Context: The agent reads the target files or codebase surface provided in the local workspace environment.
- Evaluate Audit Checklist: The skill systematically audits the code against five core principles: explicit error paths, boundary validation, timeouts/retries, structured logging, and operation idempotency.
- Identify & Map Gaps: Any discovered architecture gaps, swallowed rejections, or missing timeouts are recorded with their explicit file and line locations.
- Knowledge Capture (Optional): If reusable architectural decisions or durable conventions are uncovered, the skill structures this data into an Open Knowledge Format (OKF) markdown note with the user's explicit approval.
- Output Recommendations: A final review summary is generated, clearly separating confirmed resilient code blocks from identified technical debt.
Review Error Handling Setup
This skill operates as a self-contained, local-first tool that does not require mandatory setup or active third-party connections. To fully unlock optional cloud-based team synchronization, shared workspace recommendations, and advanced context discovery, you can configure the underlying CLI engine:
npm install -g @ritualai/cli
ritual init
ritual status
Review Error Handling Data Schema & Taxonomy
When the skill uncovers reusable patterns or technical debt conventions, it can structure and serialize this metadata using the Open Knowledge Format (OKF). With explicit user authorization, files are saved directly to the workspace repository.
Generated Metadata Schema
| File Path | Format / Frontmatter | Purpose |
|---|---|---|
knowledge/engineering/<slug>.md |
Markdown + YAML frontmatter (type, title, description, resource, tags, timestamp) | Captures durable conventions, system risks, and rollout patterns for future agent consumption. |
Markdown Content Sections
- Summary: A concise, 1-2 line description of the reusable rule.
- Applies to: Definition of the codebase surfaces where the rule holds true.
- Evidence: References to the specific files or observations from which the knowledge was derived.
- Use in future agent work: Clear instructions guiding how future automated workflows should action this knowledge.
Review Error Handling Advanced Features
- Local-First Privacy: Runs securely within your local execution framework without invoking external tools or uploading code snippets to private third-party services.
- Open Knowledge Format (OKF) Integration: Generates highly portable, versionable markdown notes embedded with YAML frontmatter to continuously educate your AI repository context over time.
- Ritual Cloud Upgrades: Connects optionally to advanced workspace tracking to cross-reference failure policies against downstream consumers, historical incident reports, and multi-service conventions.
- Structured Decision Frameworks: Transforms basic code reviews into an active exploration, producing comprehensive recommendations covering fail-open versus fail-closed strategies.
SKILL.md
Loading
Related Openclaw Skills
GoCreative Compliance
An on-demand, pay-per-call compliance toolkit enabling AI agents to screen entities against global watchlists, sanctions, and PEP databases instantly.
Review Loading, Error, Empty States
A local-first development skill to audit and ensure proper loading, error, empty, partial, and retry states across UI surfaces.
GoCreative Enrichment
A pay-per-call B2B enrichment skill for AI agents that extracts firmographics, work emails, domain intelligence, and social profile data using x402 auto-payment.
Court Records, Case Law & Litigation Search
An AI-native legal research and litigation search skill that retrieves real-time US court opinions and case law via CourtListener with zero setup or API keys.
Review Accessibility
A local-first development skill to check keyboard accessibility, screen-reader semantics, contrast, focus states, and dynamic announcements on any UI surface.
React Component Review
A local-first development skill designed to review React and TypeScript components for correctness, hook safety, prop modeling, and accessibility with minimal, precise changes.
Featured*
