OpenAgentSkill Registry Manifest
Skill: agentic-eval
Slug: github-agentic-eval
Category: design-creative
Description: Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when:
- Implementing self-critique and reflection loops
- Building evaluator-optimizer pipelines for quality-critical generation
- Creating test-driven code refinement workflows
- Designing rubric-based or LLM-as-judge evaluation systems
- Adding iterative improvement to agent outputs (code, reports, analysis)
- Measuring and improving agent response quality

Agent fit:
- Decision: 100/100 Production-ready
- Primary fit: Coding agents
- Role: Primary pick

Supply profile:
- Track: Coding and developer agents
- Scenario: Coding agents
- Applicable agents: Claude Code, CLI, Codex, Cursor
- Maintenance: 4d since push
- Risk: Safe to try

Trust:
- Trust score: 86/100 Production candidate
- Audit: 90/100 Safe to try

Attribution:
- Status: Registry indexed
- Source: github fast track
- Creator: github
- Claim URL: https://www.openagentskill.com/skills/github-agentic-eval#claim-this-skill

Install:
npx skills add github/awesome-copilot --skill agentic-eval

URLs:
- Web: https://www.openagentskill.com/skills/github-agentic-eval
- API: https://www.openagentskill.com/api/agent/skills/github-agentic-eval
- Install API: https://www.openagentskill.com/api/skills/github-agentic-eval/install
- Repository: https://github.com/github/awesome-copilot/tree/main/skills/agentic-eval