Eval Harness

Eval Harness is a Quality skill for Claude Code, published by sangrokjung in claude-forge.

806 stars175 forkson sangrokjung/claude-forgeAdded 2026/08/22Repository updated 2026/08/21

agentsai-assistantai-codingai-frameworkai-pair-programminganthropicautomationclaude-codeclaude-code-agentscli-toolsdeveloper-experiencedeveloper-toolsdotfileshooksllmmacosproductivityshellslash-commandsworkflow

Install in seconds

Install Eval Harness

Copy Eval Harness into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/sangrokjung/claude-forge/tree/main/skills/eval-harness ~/.claude/skills/eval-harness

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/sangrokjung/claude-forge.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/eval-harness/SKILL.md in sangrokjung/claude-forge
Installs to: ~/.claude/skills/eval-harness
Collection: One of 25 skills cataloged from this repository
Category: Quality — 1354 skills

What Eval Harness does

Eval Harness defines capability, regression, and human-review evals for Claude Code sessions. Use it to plan work before coding, run checks during implementation, and report pass@k results.

Eval Harness is cataloged under Quality on DirSkills. Eval Harness comes from a repository tagged agents, ai-assistant, ai-coding, ai-framework and ai-pair-programming.

Documentation

README

Excerpt

Eval Harness Skill

A formal evaluation framework for Claude Code sessions, implementing eval-driven development (EDD) principles.

Philosophy

Eval-Driven Development treats evals as the "unit tests of AI development":

Define expected behavior BEFORE implementation
Run evals continuously during development
Track regressions with each change
Use pass@k metrics for reliability measurement

Eval Types

Capability Evals

Test if Claude can do something it couldn't before:

[CAPABILITY EVAL: feature-name]
Task: Description of what Claude should accomplish
Success Criteria:
  - [ ] Criterion 1
  - [ ] Criterion 2
  - [ ] Criterion 3
Expected Output: Description of expected result

This is the opening of the README. Read the full README on GitHub.

Commands Eval Harness provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/eval

Frequently asked about Eval Harness

What else does sangrokjung publish alongside Eval Harness?
Eval Harness is one of 25 skills that DirSkills catalogs from sangrokjung/claude-forge, the repository it ships in. Its siblings there include BigCode Evaluation Harness, Blind Spot Pass and Build System. Each one is a separate skill with its own page in this directory, installs the same way Eval Harness does, and is maintained by sangrokjung in that same repository. The rest of the collection is listed on the sangrokjung/claude-forge page.
How does Eval Harness compare to other Quality skills?
Eval Harness ranks #947 by stars among the 1354 Quality skills in this catalog. The most-starred ones next to it are Benchmark, Benchmark Optimization Loop and API Design Patterns. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Eval Harness against them. Open each page to compare what they document and how they install.