Chengkun Rao
Community@lllllllama · China
ohh
Agent Skills by Chengkun Rao
Showing 11 vetted skills indexed across 1 GitHub repositories.
lllllllamarun-train
Execute deep learning training commands and record progress evidence in train_outputs.
lllllllamaminimal-run-and-audit
Capture and normalize execution evidence from short non-training commands into structured repro_outputs bundles.
lllllllamaai-research-reproduction
Coordinate auditable reproduction workflows for AI research repositories.
lllllllamapaper-context-resolver
Resolve reproduction gaps between README guidance and primary papers.
lllllllamasafe-debug
Diagnose deep-learning errors from tracebacks and symptoms into structured diagnostic files.
lllllllamaanalyze-project
Map entrypoints, model structure, and config relationships in deep learning repositories.
lllllllamaexplore-run
Plan and summarize isolated exploratory deep learning experiment runs.
lllllllamaenv-and-assets-bootstrap
Translate top-level environment files into a conda-first bootstrap flow with asset manifests.
lllllllamaai-research-explore
Orchestrate auditable research campaigns with isolated branches and evaluation contracts.
lllllllamaexplore-code
Isolate exploratory code changes on dedicated branches with traceable mappings.
lllllllamarepo-intake-and-plan
Scans READMEs and project files to extract documented commands and classify them into inference, evaluation, or training categories.