Optimize AI Skills with Run History Upgrader

Enhance AI Capabilities with Run History Upgrader

Unlock the full potential of your AI agent skills with the Run History Upgrader, a powerful tool designed for seamless enhancements and upgrades. This skill leverages real run evidence and user feedback to refine and optimize existing AI agent skills, ensuring they remain effective and up-to-date without creating brand-new workflows. Perfect for developers using AI coding agents like Claude Code, Cursor, and Codex.

What this skill does

• Analyzes recent runs, identifying recurring failures and outdated sources to enhance current skills.
• Reviews user feedback and validated workflow inputs to implement structural improvements.
• Adds, modifies, merges, deletes, or deprecates skill components based on concrete run history analysis.
• Supports multilingualism by writing all user-facing output in the user's language, defaulting to Chinese if undetermined.

Use cases

• A developer identifies frequent performance issues in their AI-based application and uses this skill to analyze and address the root causes.
• A team notices changes in platform behavior affecting their agent's function; this skill updates the skill's structure to accommodate new platform specifications.
• A project manager receives workflow validation feedback suggesting unnecessary skill bloat and utilizes this skill to streamline operations.

Technical details

• Agent-agnostic compatibility: Works seamlessly with Codex, Claude Code, OpenCode, OpenClaw, Hermes, and more.
• Includes comprehensive support for various components like `SKILL.md`, `references/`, `scripts/`, and `evals/` directories.
• Adjusts to different Python launchers and path separators, ensuring flexibility across diverse environments.
• Employs agent-memory and aiapplication capabilities to fully harness the potential of run-history-skill-upgrader tools.

Maximize efficiency and maintain competitiveness by ensuring your AI skills adapt and grow with your needs. Implement the Run History Upgrader today to see tangible improvements and sustained performance across your AI projects.

Source & Licence

This package is built on open-source work published by dongshuyan (dongshuyan/compass-skills) and distributed under MIT. The original licence text and copyright notice are included in your download.

Personal and commercial use, modification and redistribution are permitted, provided the original copyright and licence notice are retained.

Your purchase covers curation, licence verification, packaging, documentation and instant delivery. It does not grant exclusive rights to the underlying open-source code, which remains available under its original licence.

Delivery & Support

• Delivery: instant — a secure download link is emailed to you as soon as payment is confirmed.
• Format: ZIP archive containing the skill files, documentation and the original licence.
• Support: support@mcpcart.com — we aim to reply within 2 business days.
• Updates: updates are included only where stated on this page.

Refunds

This is a digital product delivered immediately after purchase. By completing your order you request immediate delivery and acknowledge that, once the download has been accessed, the statutory right to cancel no longer applies to the extent permitted by law. Refund requests are handled in accordance with our published Refund Policy.

Claude, Codex, Gemini and Cursor are trademarks of their respective owners. MCP Cart is an independent marketplace and is not affiliated with, endorsed by, or sponsored by any of them. Compatibility references describe interoperability only.