Light Experiment Coding is a Quality skill for Claude Code, published by Light0305 in Light-skills.
Light Experiment Coding implements frozen research plans as minimal, test-first experiment code with controls for leakage and reproducibility. Use it to build or review training, preprocessing, and evaluation runs with raw artifacts for result analysis.
Light Experiment Coding is cataloged under Quality on DirSkills. Light Experiment Coding comes from a repository tagged academic-writing, agent-skills, ai-agent, ai-skills and claude-code.
Documentation
任务不是“写出能跑的 notebook”，而是把上游冻结计划逐行实现成可证伪、可复跑、可审计的实验。优先级：
先完整阅读 references/experiment-coding-resource-map.md。工具机制见
references/tools.md，TDD/调试红旗见
references/tdd_redflags.md 与
references/debug_protocol.md。
开始写码前读取并 hash：
This is the opening of the README. Read the full README on GitHub.
Light Experiment Coding is one of 23 skills that DirSkills catalogs from Light0305/Light-skills, the repository it ships in. Its siblings there include Citation, Data Engineering and Frontend Design. Each one is a separate skill with its own page in this directory, installs the same way Light Experiment Coding does, and is maintained by Light0305 in that same repository. The rest of the collection is listed on the Light0305/Light-skills page.
Light Experiment Coding ranks #1178 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 Light Experiment Coding against them. Open each page to compare what they document and how they install.
Light Experiment Coding is one of 23 skills cataloged on DirSkills from Light0305/Light-skills.
Light Experiment Coding is one of 1354 Quality skills cataloged on DirSkills, ranked #1178 by stars among them.