20 Magpie Kernel Evaluator alternatives
Magpie Kernel Evaluator: AMD's official skill for benchmarking vLLM/SGLang inference and driving GPU kernel optimization with Magpie and TraceLens trace analysis. 20 agent skills do similar work, most sharing Evaluation, Official and GPU, ranked by how much they have in common with Magpie Kernel Evaluator.
Back to Magpie Kernel Evaluator
-
by AMD
AMD's official skill for standing up a vLLM endpoint on Instinct MI300X/MI325X/MI350X/MI355X GPUs — detection, recipe lookup, launch and health check in one flow.
-
by AMD
AMD's official meta-skill: permanently reroutes an agent's image generation, text-to-speech and speech-to-text to a local Lemonade Server instead of a paid cloud API.
-
by AMD
AMD's official skill for CPU inference: brings up a single vLLM + zentorch endpoint on an EPYC server, sized to the socket it runs on.
-
by NVIDIA
Diagnoses wrong gradients in differentiable NVIDIA Warp programs by measuring first — comparing autodiff against finite differences on a shrunk reproduction before proposing any fix.
Also: Evaluation, GPU
-
by Anthropic
Anthropic's official skill that appends 2-3 targeted follow-up questions to a substantive answer, prompting the reader to check facts, probe assumptions and spot missing context.
Also: Evaluation, Official
-
by AWS Labs
Read-only diagnostics for cluster-wide SageMaker HyperPod failures on EKS or Slurm — CloudFormation errors, EFA health checks, lifecycle scripts, capacity, dangling nodes and autoscaler conflicts.
-
by Callstack
Callstack's official React Native performance skill: a priority-ordered framework for FPS, time-to-interactive, bundle size, memory leaks and re-render problems.
Also: Official, Performance
-
by MongoDB
MongoDB's official skill for connection pools and timeouts — it refuses to hand you numbers until it knows your deployment, workload and concurrency.
Also: Official, Performance
-
by Inngest
Seven ways to throttle agent and background workloads — concurrency keys, throttling, rate limiting, debounce, singleton, priority and batching — with a decision guide that picks the right one.
Also: Official, Performance
-
by .NET Team at Microsoft
Make slow Entity Framework Core queries fast — read the generated SQL first, fix N+1s, cartesian Include explosions and non-sargable predicates, then re-measure one change at a time.
Also: Official, Performance
-
by Tencent
Tencent's skill-evolution harness: it rewrites a whole skill folder — SKILL.md, scripts and references together — and lands every decision as a real Git issue, PR and wiki entry you can review.
Also: Evaluation
-
by Agnost AI
Walks a coding agent through wiring Agnost AI conversation analytics into a Python or TypeScript app — inspecting existing OpenTelemetry first and only adding an SDK when the traces are not usable.
Also: Evaluation
-
by Addy Osmani
Sends every non-trivial decision to a fresh-context adversarial reviewer before it stands — for production, security-sensitive or irreversible work.
Also: Evaluation
-
by Anthropic
Anthropic's guide for building high-quality MCP servers end to end — research, tool design, implementation in TypeScript or Python, testing, and a 10-question evaluation suite.
Also: Evaluation
-
by Anthropic
Create, edit, and optimize Agent Skills — scaffold new skills, refine existing ones, run evals, and tune descriptions for reliable triggering.
Also: Evaluation
-
by SerpApi
A protocol for measuring whether agents can discover and use your tool without being told about it — WITH/WITHOUT trials, binary scoring, and lift as the only metric. The subject under test is your docs, not the model.
Also: Evaluation
-
by NVIDIA
NVIDIA's official skill for building synthetic datasets with NeMo Data Designer — describe the data you want and the agent writes a declarative generation pipeline, column by column.
Also: Evaluation
-
by Hugging Face
Fine-tune object detection, image classification and SAM/SAM2 segmentation models on Hugging Face Jobs cloud GPUs, with dataset validation before you spend GPU minutes.
Also: GPU
-
by NVIDIA
Trains, distils, quantises, evaluates, exports and runs inference for RT-DETR real-time object detection in NVIDIA TAO, routing training through AutoML hyperparameter search by default.
Also: GPU
-
by NVIDIA
Inspects the host's hardware, OS, CUDA driver and existing tooling, recommends one Holoscan SDK install method with a reason, then hands off to the matching install skill.
Also: GPU
