📊

DevOpsPython

Graphsignal Profiler

Graphsignal Profiler is a DevOps skill for Claude Code, published by graphsignal in graphsignal-profiler.

241 stars12 forkson graphsignal/graphsignal-profilerAdded 2026/07/16Repository updated 2026/06/26

View source on GitHub Download repo ZIP

ai-agentsartificial-intelligencedebuggingdeep-learninghuggingfaceinferencelangchainlangchain-pythonmachine-learningmonitoringobservabilityopenai-apipythonpytorchtracer

Install in seconds

Install Graphsignal Profiler

Copy Graphsignal Profiler into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/graphsignal/graphsignal-profiler ~/.claude/skills/graphsignal-profiler

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/graphsignal/graphsignal-profiler.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: SKILL.md in graphsignal/graphsignal-profiler
Installs to: ~/.claude/skills/graphsignal-profiler
Collection: The only skill cataloged from this repository
Category: DevOps — 1075 skills

What Graphsignal Profiler does

Monitor and profile GPU inference workloads with Graphsignal. Set up profiling for vLLM, SGLang, PyTorch, and dstack services to optimize performance and trace errors.

Graphsignal Profiler is cataloged under DevOps on DirSkills. Graphsignal Profiler comes from a repository tagged ai-agents, artificial-intelligence, debugging, deep-learning and huggingface.

Documentation

README

Excerpt

Graphsignal Profiler

Graphsignal observes inference workloads from a sidecar process — the profiler. It never shares a process with CUDA: the profiler watches the workload externally via CUPTI, OTLP/gRPC, Prometheus scraping, and NVML. Auto-instrumentation covers vLLM, SGLang, and PyTorch out of the box.

Install

Two install patterns depending on how you'll launch the profiler.

For graphsignal-run (CLI, recommended): install as a uv tool, isolated from your workload env.

UV_TOOL_BIN_DIR=/usr/local/bin uv tool install 'graphsignal[cu12]'   # CUDA 12.x
# or
UV_TOOL_BIN_DIR=/usr/local/bin uv tool install 'graphsignal[cu13]'   # CUDA 13.x

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Graphsignal Profiler

How does Graphsignal Profiler compare to other DevOps skills?
Graphsignal Profiler ranks #764 by stars among the 1075 DevOps skills in this catalog. The most-starred ones next to it are Backend Patterns, API Connector Builder and Migration. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Graphsignal Profiler against them. Open each page to compare what they document and how they install.

More DevOps skills

Graphsignal Profiler is one of 1075 DevOps skills cataloged on DirSkills, ranked #764 by stars among them.

Browse all DevOps skills →

Backend Patterns

Backend Patterns covers backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes. Use when building or reviewing Node.js, Express, or Next.js API routes and their data access.

API Connector Builder

API Connector Builder builds a new API connector or provider by matching an existing integration pattern in the codebase exactly. Use it when adding a new integration to a project without introducing a second architecture.

Migration

Migration implements reversible compatibility-safe transitions for schema, data, API, protocol, configuration, or dependency changes. Use it when rollback and preservation proof are required.