Bare Eval is an AI Engineering skill for Claude Code, published by yonatangross in orchestkit.
Bare Eval runs `claude -p --bare` for isolated evaluation, trigger testing, and LLM grading without plugin or hook interference. Use it when benchmarking prompts, scoring outputs, or checking skill matches in a clean non-interactive call.
Bare Eval is cataloged under AI Engineering on DirSkills. Bare Eval comes from a repository tagged agent-orchestration, agents, ai-agents, ai-development and anthropic.
Documentation
Run claude -p --bare for fast, clean eval/grading without plugin overhead.
CC 2.1.81 required. The --bare flag skips hooks, LSP, plugin sync, and skill directory walks.
-p call that doesn't need pluginsThis is the opening of the README. Read the full README on GitHub.
Bare Eval is one of 25 skills that DirSkills catalogs from yonatangross/orchestkit, the repository it ships in. Its siblings there include AI UI Generation, API Design and Accessibility. Each one is a separate skill with its own page in this directory, installs the same way Bare Eval does, and is maintained by yonatangross in that same repository. The rest of the collection is listed on the yonatangross/orchestkit page.
Bare Eval ranks #2529 by stars among the 2793 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. 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 Bare Eval against them. Open each page to compare what they document and how they install.
Bare Eval is one of 25 skills cataloged on DirSkills from yonatangross/orchestkit.
Bare Eval is one of 2793 AI Engineering skills cataloged on DirSkills, ranked #2529 by stars among them.