Kineto Release Agent Skill

Update the third_party/kineto submodule in PyTorch to the latest commit from this kineto repo and commit the change. Use when updating the kineto submodule hash for a release.

574 tokens

context cost

the whole folder, loaded on every use

files

instructions only

copies elsewhere

how many repositories repackaged it

983

stars on the repo

on the repository, not the skill itself

Install

one command, takes just this skill from the repository

npx skills add https://github.com/pytorch/kineto --skill kineto-release

What it tells the agent to use

found in the instruction text

Bash runs shell commands — read the instruction before connecting

The instruction itself

3 sections, as written by the author

Update Kineto Submodule

Update the third_party/kineto submodule in a local PyTorch repo to point to a

commit from this Kineto repo.

If a commit hash is provided via $ARGUMENTS, use that as the target hash.

Otherwise, use the tip of main from this repo.

Prerequisites

Before starting, you need the path to the local PyTorch repo. If you do not

already know it from prior conversation context, ask the user:

> "What is the path to your local PyTorch repo?"

The PyTorch repo is required — do not proceed without it. Store the path as

$PYTORCH for the steps below.

Steps

(PyTorch) Get the current submodule hash:

   cd $PYTORCH && git submodule status third_party/kineto | awk '{print $1}' | sed 's/^[-+]//'

(Kineto) Get the target hash. If $ARGUMENTS is provided, use it. Otherwise, get

the tip of main from this repo:

   git log -1 --format='%H' main

Do NOT fetch or pull from remote -- you do not have permissions. The repo is

already up to date.

(PyTorch) Create a branch named release_YYYY_MM_DD_<short_new_hash> (using today's

date and the short target commit hash) and switch to it.

(Kineto) List included commits between old and new hash:

   git log --format='- %s %h' <old_hash>..<new_hash> | sed 's/(#/(pytorch\/kineto#/g'

(PyTorch) Update the submodule to the new hash. The submodule's local

object store likely won't have the target commit, so fetch from the local

Kineto repo first:

   cd $PYTORCH/third_party/kineto && git fetch <path_to_kineto_repo> main && git checkout <new_hash>

(PyTorch) Commit with a message in this format:

   Update third_party/kineto submodule to <short_new_hash>

   Includes the following commits:

   - <message1> <hash1>
   - <message2> <hash2>
   - ...

If the current hash already matches the target, inform the user that kineto is

already up to date and stop.

Other skills for the same job

different authors, same section of the catalogue

Skill Creator

by anthropics

vendor ×10

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Access NCBI GEO for gene expression/genomics data. Search/download microarray and RNA-seq datasets (GSE, GSM, GPL), retrieve SOFT/Matrix files, for transcriptomics and expression analysis.

12k tokens

Pymc Bayesian Modeling

by christophacham

×4

Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.

Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems.

Statistical modeling toolkit. OLS, GLM, logistic, ARIMA, time series, hypothesis tests, diagnostics, AIC/BIC, for rigorous statistical inference and econometric analysis.

Fine-tune models on Azure AI Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file upload, calibrate grader, deploy fine-tuned model, evaluate fine-tuned model. DO NOT USE FOR: general model deployment without fine-tuning (use deploy-model), agent creation (use agents), prompt optimization without training (use prompt-optimizer).

Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.

Work with Data Commons, a platform providing programmatic access to public statistical data from global sources. Use this skill when working with demographic data, economic indicators, health statistics, environmental data, or any public datasets available through Data Commons. Applicable for querying population statistics, GDP figures, unemployment rates, disease prevalence, geographic entity resolution, and exploring relationships between statistical entities.

9k tokens

How to use it

Copy the folder

Take pytorch/kineto-release from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.