Scoring Checks is a Quality skill for Claude Code, published by caliber-ai-org in ai-setup.
Scoring Checks adds new deterministic checks in src/scoring/checks/ that evaluate AI agent config quality. Use it when adding or modifying scoring criteria, ensuring checks follow the Check[] return pattern and point constants from src/scoring/constants.ts.
Scoring Checks is cataloged under Quality on DirSkills. Scoring Checks comes from a repository tagged agent-config, ai-agents, anthropic, claude-code and claude-md.
Documentation
Add a new deterministic check that evaluates a single aspect of AI agent config quality. All checks must be filesystem-based with no network calls or LLM inference.
This is the opening of the README. Read the full README on GitHub.
Scoring Checks is one of 8 skills that DirSkills catalogs from caliber-ai-org/ai-setup, the repository it ships in. Its siblings there include Adding a Command, Caliber Setup and Caliber Testing. Each one is a separate skill with its own page in this directory, installs the same way Scoring Checks does, and is maintained by caliber-ai-org in that same repository. The rest of the collection is listed on the caliber-ai-org/ai-setup page.
Scoring Checks ranks #729 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 Scoring Checks against them. Open each page to compare what they document and how they install.
Scoring Checks is one of 8 skills cataloged on DirSkills from caliber-ai-org/ai-setup.
Scoring Checks is one of 1354 Quality skills cataloged on DirSkills, ranked #729 by stars among them.