Skill UI

A systematic workflow designed to significantly improve the reliability and performance of existing AI agents. It covers detailed performance analysis, including gathering metrics (e.g., task success rate, latency), classifying failure modes, and advanced prompt engineering techniques (like Chain-of-Thought and Constitutional AI). The process culminates in structured A/B testing and controlled deployment, ensuring measurable, robust improvements.

This meta-skill is designed to guide and execute structured developmental workflows, enabling continuous skill improvement and knowledge transfer. It is applicable when a task requires following a defined developmental process. Users must ensure all necessary inputs, permissions, and success criteria are provided, and must treat the output as a guide, supplementing professional validation.

A comprehensive guide applying Kaizen (continuous improvement) and Poka-Yoke (error proofing) principles to software development. Use this skill when you need to enhance code quality, refactor large systems incrementally, validate designs, or optimize development processes by focusing on prevention rather than fixing bugs.

Enables Claude to monitor and analyze application CPU usage, detect hotspots, inefficient loops and regexes, and offer optimization strategies such as asynchronous processing or algorithmic improvements to boost performance.

An advanced skill for Scrum Masters that uses Python scripts to analyze raw sprint data exported from tools like Jira. It provides comprehensive insights including Monte Carlo velocity forecasting, a multi-dimensional team health score (0-100), and tracking of action items and recurring themes from retrospectives. Ideal for process improvement, sprint planning, and stakeholder reporting.

A comprehensive runbook for handling critical incidents related to Windsurf AI features, service outages, or production bugs caused by generated code. It guides teams through triage, mitigation (including Git reverting), root cause analysis, and post-incident reporting to ensure rapid recovery and process improvement.

This guide details the architectural framework for continuous skill improvement within makepad-skills. It covers hooks-based auto-triggering, context detection for skill routing, and a structured process for developers to identify, classify, and integrate new patterns or solutions into the skill set, ensuring the library remains current and accurate during ongoing development.

This skill provides a systematic methodology for iteratively improving complex skill documentation. By utilizing a reviewer agent, it identifies and categorizes issues (Critical, Major, Minor) in a structured loop. The process ensures that the skill meets high standards of quality, reliability, and functional completeness before deployment, moving beyond simple manual edits.

A comprehensive, canonical workflow for defining, writing, and improving complex AI skills. It guides users through a structured, multi-step process, including resolving targets, synthesizing information, enforcing depth gates, authoring artifacts, optimizing descriptions, and conducting thorough evaluation and validation.

This skill automates the scholarly process of refining a generated academic paper. It executes an iterative loop (Review → Fix → Recompile) using advanced LLMs (like GPT-5.5) over multiple rounds. It is designed not for primary research, but specifically for polishing writing quality, correcting theoretical inconsistencies, improving presentation, and enhancing narrative flow after the initial draft is complete. It helps elevate a paper from a draft to a polished submission.

This skill automates the research improvement process by creating a closed loop: Review -> Implement Fixes -> Re-review. It leverages any OpenAI-compatible LLM API to iteratively refine research work until a positive assessment is reached or a maximum round limit is hit. Ideal for academic or technical project refinement.

This skill provides comprehensive tracking and visualization for Security Operations Center (SOC) performance. It calculates critical metrics such as Mean Time to Detect (MTTD), Mean Time to Respond (MTTR), and alert quality ratios using SIEM data. Ideal for SOC leadership, compliance auditing, and continuous process improvement initiatives needing quantifiable security posture reporting.