ai-dynamoOfficial·8 Agent Skills Included

aiperf

Benchmark LLM inference servers and automate release engineering workflows

Measures LLM inference server performance with detailed latency, throughput, and token metrics via CLI and live dashboards. Automates release chores like cherry-picking commits, bumping versions, and creating Linear issues without manual git work. Reviews branches and PRs for code quality and agent-readability, then drafts inline GitHub review comments. Migrates plain Markdown docs folders into fully branded Fern documentation sites.

631|166

↗

npx skills add ai-dynamo/aiperf --all -g -y

Available:

Gives the AI agent the project's coding standards, build and test commands, and step-by-step rules for adding services, plugins, messages, and CLI flags when working in this repository.

All Skills in This Repository (8)

Pure Emerald Level Indicators

📦 In Repo

ai-dynamo

docs-to-fern

Migrates a Markdown docs/ folder into a Fern documentation site with scaffolding, navigation, and NVIDIA SPDX frontmatter.

linear-issue

Create Linear issues with Todo status assigned to the current user.

aiperf-code-review

Compare current branch to origin/main and document code-quality gaps with runtime evidence.

aiperf-llm-ergonomics-review

Audit AIPerf code for ergonomics issues across seven quality axes.

cherry-pick

Cherry-pick commits from main into release branches using temporary git worktrees.

aiperf-kube-sweep

Runs parameter sweeps and Bayesian search benchmarks on Kubernetes via AIPerfSweep CRs.

aiperf-kube-setup

Installs and configures the aiperf-operator Helm chart on multi-node Kubernetes clusters.

aiperf-kube-triage

Diagnose stuck, failing, or erroring AIPerf benchmark jobs on Kubernetes from CR status, pod state, and logs.

Official

Advanced

Frequently Asked Questions

FAQPage Schema

How to install AIPerf?▼

Run `npx skills add ai-dynamo/aiperf --all -g -y` in your terminal to install all skills in this suite globally.

What does AIPerf do?▼

AIPerf benchmarks generative AI inference servers, reporting metrics like time to first token, latency percentiles, and throughput through a CLI, live dashboard, and exportable reports.

How to cherry-pick a commit to a release branch with AI?▼

The cherry-pick skill fetches the commit, creates a temporary worktree, applies it to your chosen release branch, and opens a labeled PR automatically.

Can AI review my AIPerf pull request?▼

Yes. The code review skill validates findings against the real code, reproduces issues with the CLI, and drafts inline GitHub PR comments for your approval before posting.

Do these skills work with Claude Code and Cursor?▼

Yes. All skills follow the standard SKILL.md format and run in Claude Code, Cursor, Codex, and other compatible AI coding agents.