Skill UI

Provides patterns and techniques for building robust evaluation loops for AI agents. This skill guides the implementation of self-critique, evaluator-optimizer pipelines, and test-driven refinement workflows. Use it to significantly enhance the accuracy and quality of complex outputs like code, reports, and analyses by implementing structured, iterative improvement cycles (Generate → Evaluate → Critique → Refine).

This guide outlines the process and mandatory structure for documenting defects found during an Oracle-to-PostgreSQL migration. It details how to write actionable bug reports, covering required elements like Severity, Root Cause, Scenario, and Solution. It emphasizes treating Oracle as the source of truth and handling data layer nuances (e.g., NULL vs. empty string) to ensure accurate defect tracking and remediation.

Three-layer verification pipeline that extracts verifiable claims from AI output, searches the web for supporting or contradicting sources, flags hallucinations, and builds structured reports for human review.

This skill transforms unstructured, messy bug input—such as raw error logs, screenshots, voice dictations, and rough notes—into clean, actionable, and professional GitHub issue templates. It extracts necessary details like reproduction steps, expected vs. actual behavior, impact severity, and context, ensuring developers receive perfectly formatted reports ready for immediate action.

Automates GA4 reporting and property management via Composio’s Rube MCP, covering account/property discovery, standard/batch/pivot/funnel reports, and key event workflows so analysts can run repeatable queries without manual UI steps.

This tool helps developers run comprehensive test suites using pytest and generates detailed code coverage reports. It identifies specific lines of code that have not been covered by tests, guiding developers to improve test quality until 100% coverage is achieved. Use it to ensure robust and reliable software.

Analyzes and generates a self-contained, explorable HTML report detailing usage metrics for Claude Code sessions. It tracks token consumption (input/output), subagent usage, skill calls, and cache efficiency across specified time ranges. This tool helps developers visualize resource waste and pinpoint areas for workflow optimization, ensuring cost-effective and efficient AI development cycles.

Automates updating Azure Verified Modules referenced in Bicep files to their latest released versions, guiding scan, version comparison, documentation checks, and validation workflows while limiting reports to non-breaking changes.

Scans specified files or folders to infer existing syntax, writes a project coding standards or contribution doc using configurable templates, and optionally reports or fixes inconsistencies before saving to the first available standard filename.

This skill outlines the principle of mandatory, evidence-based verification before declaring any work (such as a feature, bug fix, or task) complete or successful. It mandates that assertions of success must be backed by repeatable evidence, such as passing test outputs, clean build logs, or successful execution reports. It is critical for PR reviews, task closure, and maintaining high engineering rigor.