BKit Evals

by popup-studio-ai

BKit Evals is a Quality skill for Claude Code, published by popup-studio-ai in bkit-claude-code.

592 stars152 forkson popup-studio-ai/bkit-claude-codeAdded 2026/08/25Repository updated 2026/08/17

View source on GitHub Download repo ZIP

ai-agentsai-driven-workai-native-developmentbkitclaude-codemulti-languagepdcapipelineplugin-repo

Install in seconds

Install BKit Evals

Copy BKit Evals 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/ww-w-ai/bkit-claude-code/tree/main/skills/bkit-evals ~/.claude/skills/bkit-evals

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/ww-w-ai/bkit-claude-code.git

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

In this catalog

Source file: skills/bkit-evals/SKILL.md in popup-studio-ai/bkit-claude-code
Installs to: ~/.claude/skills/bkit-evals
Collection: One of 25 skills cataloged from this repository
Category: Quality — 1354 skills

What BKit Evals does

BKit Evals runs a skill's eval suite through evals/runner.js, validates the skill name, captures output, and saves structured results. Use it to list eval-enabled skills or check a skill's evaluation output and pass/fail counts.

BKit Evals is cataloged under Quality on DirSkills. BKit Evals comes from a repository tagged ai-agents, ai-driven-work, ai-native-development, bkit and claude-code.

Documentation

README

Excerpt

bkit Evals — Skill Quality Evaluation Runner

v2.1.11 Sprint β FR-β2. Wraps evals/runner.js with input validation, result persistence, and structured reporting. Replaces the bare node evals/runner.js <skill> invocation that previously required users to remember argv structure and ignored timeout / sandbox concerns.

Arguments

Argument	Description	Example
`run <skill>`	Execute the eval suite for one skill	`/bkit-evals run gap-detector`
`list`	List all skills that have an `eval.yaml` definition	`/bkit-evals list`

If no argument is provided, render the same output as list.

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

Commands BKit Evals provides

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

/bkit-evals
/control
/code-review
/bkit

Frequently asked about BKit Evals

What else does popup-studio-ai publish alongside BKit Evals?
BKit Evals is one of 25 skills that DirSkills catalogs from popup-studio-ai/bkit-claude-code, the repository it ships in. Its siblings there include Audit, BKIT and BKit Explore. Each one is a separate skill with its own page in this directory, installs the same way BKit Evals does, and is maintained by popup-studio-ai in that same repository. The rest of the collection is listed on the popup-studio-ai/bkit-claude-code page.
How does BKit Evals compare to other Quality skills?
BKit Evals ranks #1142 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 BKit Evals against them. Open each page to compare what they document and how they install.