Eval Run

Eval Run is a Quality skill for Claude Code, published by Fr-e-d in GAAI-framework.

161 stars27 forkson Fr-e-d/GAAI-frameworkAdded 2026/09/08Repository updated 2026/09/04

agentic-codingai-agentsai-codingai-developer-toolsai-governanceai-memory-systemautonomous-agentsclaude-codecodex-clicontext-engineeringcursordevtoolsgemini-cliopencodevibe-codingwindsurf

Install in seconds

Install Eval Run

Copy Eval Run 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/digipulse-engineering/GAAI-framework/tree/main/.gaai/core/skills/cross/eval-run ~/.claude/skills/eval-run

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/digipulse-engineering/GAAI-framework.git

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

In this catalog

Source file: .gaai/core/skills/cross/eval-run/SKILL.md in Fr-e-d/GAAI-framework
Installs to: ~/.claude/skills/eval-run
Collection: One of 25 skills cataloged from this repository
Category: Quality — 1897 skills

What Eval Run does

Eval Run evaluates an output file against a structured evals.yaml and produces a score report with per-assertion pass or fail results. Use it to measure output quality or check for regressions after skill changes.

Eval Run is cataloged under Quality on DirSkills. Eval Run comes from a repository tagged agentic-coding, ai-agents, ai-coding, ai-developer-tools and ai-governance.

Documentation

README

Excerpt

Eval Run

Purpose / When to Activate

Activate when:

The Discovery Agent runs the Skill Optimize protocol and needs to score a skill output
A skill's instructions have been modified and a before/after quality comparison is needed
A baseline score is being established for a skill that has never been evaluated

This skill is generic: it accepts any output file and any evals.yaml, regardless of skill domain.

It follows the GAAI principle "skills never chain" — it evaluates the output it receives; it does not invoke the skill that produced the output.

Process

Step 1 — Load inputs

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

Frequently asked about Eval Run

What else does Fr-e-d publish alongside Eval Run?
Eval Run is one of 25 skills that DirSkills catalogs from Fr-e-d/GAAI-framework, the repository it ships in. Its siblings there include Abort-Safe Handler, Ambiguity Detector and Approach Evaluation. Each one is a separate skill with its own page in this directory, installs the same way Eval Run does, and is maintained by Fr-e-d in that same repository. The rest of the collection is listed on the Fr-e-d/GAAI-framework page.
How does Eval Run compare to other Quality skills?
Eval Run ranks #1811 by stars among the 1897 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 Run against them. Open each page to compare what they document and how they install.