ronRon is a skeptical reviewer who finds what's wrong — in code, reasoning, diagnoses, analysis, and decisions. Activate Ron when you want a code review, a seco...
Install via ClawdBot CLI:
clawdbot install nicolasgrasset/ronGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Oct 28, 2026
A coding agent invokes Ron before declaring a bug fix complete. Ron ignores the agent's summary, reads the actual diff and logs, checks whether the stated root cause cites real evidence or just 'should work', and flags adjacent instances of the same bug in parallel routes. The agent receives a numbered list of issues and must resolve them before delivery.
An analyst agent produces a market or technical synthesis and calls Ron as a second opinion. Ron checks whether conclusions are proportional to the evidence, hunts for overconfident claims that turned single data points into 'patterns', and identifies selectively read contradicting evidence before the report reaches stakeholders.
Before a cron change or infra fix goes live, the agent asks Ron to audit it. Ron inspects CloudWatch logs and config files directly rather than trusting the agent's account, verifying that the change addresses the actual sync failure and that no unverified assumption lurks in the rollout plan.
An agent drafts a financial plan or client proposal, and Ron is invoked to stress-test it. Ron traces each projection back to its source data, flags unstated assumptions, and checks whether the confidence language matches the strength of the underlying numbers before the document is shared.
As a standard practice, agents invoke Ron before sending any significant deliverable—a diagnosis, an analysis, a deployed fix. Ron's skeptical lens catches early-victory declarations and blind spots, giving the agent a chance to correct issues before the user ever sees the work.
Ron is bundled as a reusable skill inside agent platforms and internal agent frameworks, invoked by either users or agents before deliverables ship. Its value is catching agent failure modes at the point of delivery, making it a natural add-on to any agent product that wants higher output trust.
Teams expose Ron as a callable review endpoint that agents or humans invoke on code, analyses, and plans. Customers pay per review call or via a monthly plan, with usage scaling as agents invoke Ron more frequently across larger deliverables.
Organizations deploy Ron as a mandatory review gate in their AI-assisted workflows—engineering, research, finance—to reduce costly errors from premature 'done' declarations. Sold as an enterprise license with governance and audit reporting.
💬 Integration Tip
Ron is a prompt-driven reviewer with no setup beyond making available the same tools (file reads, logs, search) the agent already uses—just register it as an invocable skill and instruct agents to call it before delivering significant work, ensuring source material is reachable so Ron can verify rather than trust summaries.
Scored Oct 28, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.