cjl-autoresearch-ccOptimize skills, prompts, articles, workflows, or systems via single-step iterative edits with testing and scoring to keep improvements and discard regressions.
Install via ClawdBot CLI:
clawdbot install 0xcjl/cjl-autoresearch-ccGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/karpathy/autoresearchAudited Apr 17, 2026 · audit v1.0
Generated May 12, 2026
A customer support team uses the skill to iteratively improve their Claude-based support agent skill. Each round makes a small change, tests against sample tickets, and keeps only changes that improve resolution accuracy.
A marketing agency uses autoresearch to refine prompts that generate ad copy. The skill tests variations, scores them on engagement metrics, and converges on the highest-performing prompt.
A technical writer uses the skill to polish API documentation. Each iteration improves clarity and conciseness, with the system verifying that technical accuracy is preserved.
A DevOps engineer optimizes deployment workflows by iterating on small changes—like step ordering or error handling—testing each against a set of integration tests.
Offer the autoresearch capability as a premium add-on for Claude Code users. Monthly subscription with tiered usage limits for automated refinement rounds.
Consultants use the skill to optimize clients' custom prompts, skills, and workflows. Bill hourly or per project for iterative improvement sessions.
Embed the skill into CI/CD pipelines as an automated reviewer for prompt and skill changes. License to companies for use in their development workflows.
💬 Integration Tip
Integrate with version control by having the skill commit each accepted change automatically, allowing easy rollback if a series of changes degrades performance.
Scored May 12, 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.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.
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.