# Tessl Skills Clinic - Nnenna Ndukwe from Qodo

## Executive summary

The session demonstrates how automated AI agent skills can be rigorously tested and improved using Tessl's review process against Anthropic's best practices. By applying human-guided refinements—particularly enhancing the skill description with natural trigger phrases and optimizing structure—the Qodo PR Resolver skill score jumped from 78% to 89%. This highlights that while AI generation is powerful, manual validation and refinement are crucial for achieving high-quality, reliable agent performance in production workflows.

## Key takeaways

- Skill Description is Critical for Agent Triggering: The skill's description metadata is identified as the single biggest factor determining if an agent will use it. Improving this by adding natural trigger phrases (e.g., 'coding issues,' 'code reviews') significantly increases discoverability and usage likelihood.
- Human Refinement Boosts Skill Quality: Research suggests that while AI-generated skills are useful, validated and refined skills (human intervention) show a significant performance uplift. The average jump observed was approximately 14% for human-written skills.
- The Importance of Post-Fix Verification: It is a best practice to include a validation step (e.g., running linters and static analysis) after an agent has applied fixes, ensuring the code remains compliant even after automated changes.

## Technical details

- Qodo PR Resolver Skill: This skill is an AI code review tool that automatically runs against pull requests (PRs). It identifies issues and can loop through to fix them, pushing the summary and changes back to the original PR.
- Tessl Automated Review Process: The Tessl agent runs tests on a skill's definition (e.g., in `SKILL.md`) to score its adherence to Anthropic's best practices, providing actionable feedback and suggesting improvements.
- Skill Improvement Metrics: The initial review score for Qodo PR Resolver was 78%. After applying fixes and optimizing the description, the score increased to 89%, demonstrating a substantial improvement in adherence to best practices.
- Internal Use Case (Qodo): Qodo uses skills internally for 'shift left' code quality. They utilize Qodo Get Rules to provide their coding agent with context regarding specific standards, such as requiring docstrings for every Python method.

## Practical implications

- Integrate automated skill reviews (like Tessl) into CI/CD pipelines to maintain and improve agent quality over time.
- Treat the skill description metadata as a critical piece of documentation, ensuring it contains natural language trigger phrases for maximum agent discoverability.
- Establish mandatory validation steps (linting, type checking, static analysis) immediately following any automated code changes made by an agent.

## Topics

AI Agent Development, Code Quality Assurance, Build Engineering, LLM Workflow Optimization, CI/CD Best Practices, Tessl, Qodo AI / Qodo Skills Repositories

Source: https://www.youtube.com/watch?v=Imw9nfuiKmc