Generate concise experiment reports from training run artifacts and logs.
npx skills add https://github.com/gyy0592/claude-config --skill gen-report-concise
Please help me install this Agent Skill. Skill: gen-report-concise Source: https://github.com/gyy0592/claude-config/tree/main/skills/gen-report Command: npx skills add https://github.com/gyy0592/claude-config --skill gen-report-concise
This Skill automates creation of compact, reproducible experiment reports by extracting key metrics, configuration, and provenance from training run artifacts so engineers and researchers can quickly understand results and trade-offs without manual log parsing.
Generate a concise experiment report for experiment kda_680M in /nfs/ridgerzhu/flame_moonshot/exp/ by invoking the gen-report-concise skill and include logs, configs, and metrics for provenance.
High-intent search queries and answers about installing and using this skill.
Provenance-first experiment reporting tracks the exact data source by attaching file paths, line numbers, and step identifiers to every metric. This ensures reproducible analysis by mathematically defining metrics and linking them directly to training logs and artifacts.
The structured experiment report output includes four sections: takeaway, motivation, reproducibility, and results. It concludes with a final trade-off table to summarize performance comparisons across different training runs for quick handoff.
Use automated experiment reporting when you need to summarize training runs for quick handoff, postmortem, or performance comparison. It is needed when manual extraction of metrics, configs, and provenance from training logs becomes too time-consuming.
Yes, the experiment reporting skill handles CSV metrics and training toml files by reading them in parallel alongside snapshot model configs. This compatibility allows it to gather both numeric metric data and contextual configuration for the final report.
gyy0592Generate detailed 13-section markdown experiment reports from flame_moonshot training logs and metrics.
ovachieverAutomate ML experiment tracking and model registry management via the wandb API.
dogekikiParse JSON and CSV experiment files to compute performance statistics and comparative metrics.
product-on-purposeDocument UX design decisions with context, options, and trade-offs.
