All authors
Claude Skills by OpenPerfAgent
github.com/OpenPerfAgent9 skills0 installs1 views
- Clean UpDeliver a finished optimization run as a branch the user can merge. Cherry-pick the commits that changed the workload onto the base, hardcode the A/B flags, re-verify on the shipped code, strip the checkpoint calls in a last commit, and leave the user standing on that branch with a handover.Votes: 0GitHub stars: 3
- Convert To Benchmark ScriptTurn the script a user really runs into a benchmark script an optimization loop can run over and over. Same shape as the real job, a few minutes long, repeatable, and leaving nothing behind. It produces the script and a table of what changed, and it does not run it.Votes: 0GitHub stars: 3
- DiagnoseProfile the job defined in contract.md, name the one thing it loses most time to, and propose a single fix with a measured number behind it. It stops at the first finding. optimize is this same work repeated until nothing worth doing is left.Votes: 0GitHub stars: 3
- Extract Computation GraphRead a PyTorch job's code into two files in the workspace’s records/ directory. records/computation_graph.json says what is computed: the module tree down to op level, with a code anchor and a repeat count on every entry. records/execution_schedule.json says when and where it is computed and what moves between devices: phases, the data path onto the GPU, host to device copies and their sync points, the collectives between GPUs, and which overlaps are intended. It reads code and runs nothing. ...Votes: 0GitHub stars: 3
- InitWork with the user to pin down which PyTorch job gets optimized, write contract.md, and put the correctness instrumentation in place. The optimize skill later reads the contract.md written here and optimizes on its own. Every piece of alignment with the user happens in init, all of it.Votes: 0GitHub stars: 3
- OptimizeOptimize the torch job defined in contract.md with no further input. Profile, edit, and check correctness in a loop, then hand back one clean optimized branch.Votes: 0GitHub stars: 3
- Publish PrWrite the pull request description and one issue for a finished campaign into proposed-pr-description.md and proposed-issue.md, for the user to review and post. Says what the PR may claim, what goes in each section and in what order, and how it is worded. Fills template/pr-description.md and template/issue.md; the filled examples are the .example.md files next to them. It pushes nothing and opens nothing.Votes: 0GitHub stars: 3
- Setup BaselineBuild the starting point both diagnose and optimize measure everything else against: a worktree, a workspace, the computation graph and execution schedule, and the base commit measured for speed, memory and correctness and profiled in full. It arms nothing, so the caller decides what happens next.Votes: 0GitHub stars: 3
- Torch ProfileProfile a PyTorch job, training or inference, with torch.profiler. Analyse the profile, read the surface symptoms, chase each root cause down to a file:line, and hand back a diagnosis. This skill produces no patch.Votes: 0GitHub stars: 3