skill-upEvaluate and evolve Agent Skills

Measure Skill quality, then turn failures into automatic eval fixes and the next iteration.

Eval-to-Evolution with skill-upper

Create evals through natural conversation, then let skill-upper diagnose failures, repair or expand cases, and rerun skill-up until the suite evolves.

Learn more

Declarative Eval Config

Define evaluation environment, engine, model, and cases through YAML (eval.yaml + cases/*.yaml).

Configuration reference

Multi-Engine Support

Works with Qoder CLI, Claude Code, and Codex as Agent Engines.

Flexible Judging

Supports rule_based, script, and agent_judge evaluation strategies.

Grading strategies

Structured Reports

Outputs Anthropic-compatible grading.json, benchmark.json, plus result.json, JUnit XML, and HTML reports.

Output layout

Anthropic Compatible

Import evals.json via skill-up import, or auto-detect with --auto.

Migration guide

CI-Ready

Designed for local development and continuous integration pipelines.

Exit codes

Overview

skill-up combines evaluation and evolution for Agent Skills. It makes quality measurable through declarative YAML evals, isolated multi-engine runs, flexible judges, and structured reports. Then skill-upper turns failures into progress: it can automatically repair or expand the eval suite and rerun the loop with you.

The same workflow runs locally or in CI, supports Anthropic evals.json imports, and emits JSON, JUnit, and HTML reports.

How skill-up evaluates and evolves Agent Skills through automatic eval repair and iteration