Skill UI

Diagnoses full-stack failure modes in agent and LLM applications, including wrapper regressions, memory contamination, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings and code-first fixes for production agent systems.

This library provides a comprehensive framework for managing bounded AI workflows (loops). Users can analyze existing codebases or work histories to discover opportunities for repeating, automated agent processes. It guides the user through finding published templates, auditing and repairing weak agents, adapting parameters, or crafting entirely new, robust automation designs, ensuring clear triggers, verification, and mandatory stopping conditions.

Diagnoses full-stack failure modes in agent and LLM applications, including wrapper regressions, memory contamination, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings and code-first fixes for production agent systems.

This skill automates the Test-Driven Development (TDD) repair loop. Given a failing unit test, it spawns a bounded, headless LLM agent to automatically modify the source code until the test passes. It closes the development loop by treating the test's pass/fail status as the definitive fitness function, ideal for CI failure triage and local TDD workflows.

This skill audits and repairs repository hygiene across artifacts, dependencies, CI, docs, Git state, and code-quality signals. It is used for repository maintenance, cleanup, health checks, or pre-release hardening. It ensures repository health through authorized repairs and protected workflows, validating changes before publishing via pull requests to maintain security and stability.