modelsChoose AI models for coding, reasoning, and agents with cost-aware, task-matched recommendations.
Install via ClawdBot CLI:
clawdbot install ivangdavila/modelsGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Mar 21, 2026
Agencies building custom applications can use the orchestration pattern: frontier models for architecture planning, mid-tier models for implementation, and cheap models for parallel subtasks. This reduces costs while maintaining quality, especially for code review and debugging phases.
Firms handling complex data analysis and report generation benefit from using frontier models for extended reasoning on hard math problems and cheaper models for high-volume simple queries. Batch APIs and prompt caching help manage costs for long documents and non-real-time workloads.
Platforms generating articles or marketing materials can use mid-tier models for general assistance and cheap models for bulk content, avoiding overpayment. They should track actual costs per workflow and reassess model choices quarterly to adapt to shifting capabilities.
Organizations processing patient records or research documents can leverage large-context models to handle long documents without chunking, reducing costs. Open-source models ensure data privacy and cost predictability for custom fine-tuning on sensitive datasets.
Offer basic features with cheap models for high-volume simple queries, then charge for premium tiers using mid-tier or frontier models for complex tasks like coding or reasoning. This aligns costs with user needs and encourages upgrades based on task complexity.
Provide services that design AI pipelines using the orchestration pattern, recommending specific models for planning, execution, and review phases. Revenue comes from reduced client costs and improved accuracy, with ongoing reassessment to adapt to model updates.
Build a platform that uses batch/async APIs for non-real-time workloads, passing 50% discounts to users. Focus on industries like finance or media where long documents and high-volume queries benefit from cost-aware model selection and prompt caching.
💬 Integration Tip
Integrate by setting up a pipeline that defaults to mid-tier models, escalates to frontier models when quality drops, and includes verification steps to catch errors, ensuring cost efficiency and reliability.
Scored Apr 22, 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.