Skip to content

Latest commit

 

History

History
 
 

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 
 
 
 
 

README.md

coder-eval — Claude Code plugin

Author, run, and analyze Coder Eval suites from inside Claude Code — including whether your own Claude Code skills actually trigger.

Coder Eval runs a real coding agent in a sandbox against declarative YAML tasks and scores the files and commands it actually produced. This plugin puts the authoring, running, and analysis loop behind six slash commands.

Install

/plugin marketplace add UiPath/coder_eval
/plugin install coder-eval@coder-eval

The first command registers this repository as a plugin marketplace; the second installs the plugin from it. (Marketplace and plugin share the name coder-eval, hence the coder-eval@coder-eval.)

Prerequisite

The skills drive the coder-eval CLI, which is not bundled with the plugin. Install it once:

uv tool install coder-eval    # or: pip install coder-eval

You do not have to do this in advance. init, task and skill-check check coder-eval --version before doing any work and, if it is missing, offer to install it and ask first — they never install unprompted, and they verify it worked before continuing. Running a suite also needs credentials for whichever agent the tasks use (e.g. ANTHROPIC_API_KEY for the default claude-code agent). lint-tasks needs neither the CLI nor credentials — it only reads files.

The six skills

Command What it does
/coder-eval:init Scans the repo for what is worth evaluating (skills, an MCP server, a CLI), then scaffolds a task directory with one real task.
/coder-eval:skill-check Generates and runs an activation suite for one of your skills — does the agent engage it when it should, and leave it alone when it shouldn't?
/coder-eval:task Turns a natural-language description into a task YAML with the right success criteria.
/coder-eval:lint-tasks Reviews task YAML you already have and reports criteria that cannot fail, prompts that give away the answer, and fixtures with no cleanup. Read-only.
/coder-eval:analyze Reads a finished run directory and reports systemic failure patterns, per-task findings, and concrete fixes.
/coder-eval:ci Emits a GitHub Actions workflow that runs your suite as a CI gate (or on a schedule, to catch skill drift).

init and ci are explicit-invocation only. skill-check, task, lint-tasks, and analyze can also be reached by the agent on its own when a request clearly calls for them.

Bundled reference

reference/ travels with the plugin so the skills work with no access to this repository:

  • criteria.md — every success-criterion type and its fields, generated from the SuccessCriterion model union (regenerated by make plugin-reference; do not hand-edit).
  • task-rubric.md — the adversarial task-quality checklist ("could this pass for the wrong reason?", fixture lifecycle, scope match) that task and lint-tasks both apply.
  • cli-setup.md — the missing-CLI policy the CLI-driving skills follow: offer, ask, verify.
  • run-layout.md — the on-disk run-directory contract that analyze reads: what is inside a run directory.
  • repo-layout.md — how every skill finds where your eval tree is: discovered by content (task_id: files, run.json), never assumed to be tasks/ and runs/.
  • templates/ — the canonical activation suite skill-check copies into your repo.

Links