Back to directory

skill-up

skill-up is a CLI that evaluates Agent Skills, agents and their workspaces by running declarative test cases against an agent engine, grading the response and any workspace changes, and producing reports locally or in CI.

skill-up

skill-up is a command-line tool for evaluating Agent Skills, agents and their workspaces. It runs declarative test cases against an Agent Engine such as Qoder CLI, Claude Code or Codex, grades the response and any resulting workspace changes, and produces reports locally or in continuous integration.

Skill evaluation compares an engine's behavior with and without a given skill installed; agent evaluation runs the same cases without a skill to assess an engine on its own; and workspace evaluation checks how an agent works with files and repositories using case fixtures or an existing local workspace. A companion tool, skill-upper, inspects failures and repairs or expands the evaluation suite through conversation, and cases are defined declaratively in YAML with support for local, Docker or sandboxed runtimes and rule-based, scripted or agent-judged grading.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.