yzailab/Large-Discovery-Models
Skill Claude CodeCodex
Collect, render, augment, audit, and validate LDM fine-tuning data through the repository's ldm-2.0 pipeline. Use when enabling data collection for an LDM task run, verifying or adding a DataCollectionSink task hook, converting accepted teacher actions into IR or LlamaFactory Alpaca rows, generating expert reasoning…
yzailab/Large-Discovery-Models
Skill Claude CodeCodex
Scaffold, implement, register, scientifically qualify, and production-check an LDM domain task in this repository. Use when adding or repairing a task adapter, task manifest, experiment.json benchmark contract, proposal-provider capabilities, metric roles, qualification evidence, official evaluation budget, campaign…
yzailab/Large-Discovery-Models
Skill Claude CodeCodex
Validate, configure, dry-run, smoke-test, execute, monitor, and summarize an existing manifest-registered LDM task through this repository's config runner. Use when asked to run LDM, run a task config or suite, test an existing task, perform a minimal first real run, verify an OpenAI-compatible served model before LDM…