Claude skills and agent skills

Skills real projects publish on GitHub, most starred first. Each one says what it will make an agent do before you copy it.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Worked for most · soon

vllm-project 10k+ stars

vllm-projectSkill

check-api-compat

vllm-project/vllm/.agents/skills/check-api-compat/SKILL.md

Determine the correct behavior of vLLM's OpenAI-compatible or Anthropic-compatible API by checking the official upstream spec, instead of guessing from vLLM's own code. Use for any bug, issue, PR, review, or question touching /v1/chat/completions, /v1/completions, /v1/responses, /v1/embeddings, /v1/messages, or their request/response models — including "is this a bug or intended", "what should this field default to", "does upstream allow this", and any change that adds, removes, or renames a field on those models. Do not use for vLLM-internal APIs (engine, scheduler, LLM class) or for endpoints with no upstream counterpart.

Surging2 mentions in 2 weeks

2 projects use a version of this

97k13d agoReviewMount

vllm-projectSkill

ci-fails-buildkite

vllm-project/vllm/.agents/skills/ci-fails-buildkite/SKILL.md

Fetch and diagnose vLLM Buildkite CI failure logs. Use when investigating failing CI jobs on a PR or build, when the user pastes a buildkite.com URL, or asks to fetch/diagnose CI logs.

2 projects use a version of this

97k13d agoReviewMount

vllm-projectSkill

debug-ima

vllm-project/vllm/.agents/skills/debug-ima/SKILL.md

Debug CUDA illegal memory access (IMA) errors in vLLM with CUDA core dumps and cuda-gdb. Use when a vLLM run crashes or hangs with a CUDA illegal memory access, device-side assert, or other asynchronous CUDA error and the faulting kernel needs to be located.

2 projects use a version of this

97k13d agoReviewMount

vllm-projectSkill

kernel-microbenchmark

vllm-project/vllm/.agents/skills/kernel-microbenchmark/SKILL.md

Build, debug, and interpret vLLM GPU kernel microbenchmarks for CUDA, ROCm/HIP, Triton, and CuteDSL, including CUPTI timing, correctness checks, generated-code inspection, multi-GPU measurements, and SOL sanity checks. Use when measuring or comparing the performance of a single GPU kernel or op, validating a claimed kernel speedup, or investigating a noisy or surprising benchmark result.

2 projects use a version of this

97k13d agoReviewMount

vllm-projectSkill

model-microbenchmark

vllm-project/vllm/.agents/skills/model-microbenchmark/SKILL.md

Time a vLLM model's forward pass on exact batch shapes (decode, prefill, chunked prefill, prefix hit, spec-decode verify, or mixes) with `vllm bench forward`, single-GPU or DP/TP/EP across nodes. Use for per-step model latency, layout/parallelism comparisons, and checking a model-level optimization. Not for single kernels (use kernel-microbenchmark) or end-to-end serving (use `vllm bench serve`).

Surging2 mentions in 2 weeks

2 projects use a version of this

97k13d agoReviewMount

vllm-projectSkill

model-recipes

vllm-project/vllm/.agents/skills/model-recipes/SKILL.md

Find vLLM deployment recipes and configs for LLMs and Hugging Face models by model and hardware. Use for recipe lookup, creation, and updates.

Surging2 mentions in 2 weeks

2 projects use a version of this

97k13d agoReviewMount

vllm-projectSkill

pr-checklist

vllm-project/vllm/.agents/skills/pr-checklist/SKILL.md

Prepare a vLLM change for human PR review or re-review, or analyze an open pull request. Use before opening a PR, drafts included (e.g. `gh pr create`), or pushing review fixes, to check design fit, behavioral coverage, performance evidence, diff quality, and closure of previous feedback.

Surging2 mentions in 2 weeks

9 projects use a version of this

97k13d agoReviewMount

vllm-projectSkill

transformers-upgrade

vllm-project/vllm/.agents/skills/transformers-upgrade/SKILL.md

Playbook for changing vLLM's Transformers version bounds. Use when bumping the pinned or maximum Transformers version, raising the minimum Transformers version, or deleting vendored configs, processors, or compat shims that upstream Transformers now provides.

Surging2 mentions in 2 weeks

2 projects use a version of this

97k13d agoReviewMount

vllm-projectSkill

triton-kernel-writing

vllm-project/vllm/.agents/skills/triton-kernel-writing/SKILL.md

Write or review Triton kernels for vLLM, with practical guidance for generated-code inspection, launch grids, indexing, specialization, tuning, and representative performance validation. Use when adding, modifying, optimizing, or reviewing a `@triton.jit` kernel in vLLM.

2 projects use a version of this

97k13d agoReviewMount

CLAUDE.md vs AGENTS.md

About skills

What is a Claude skill?

A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.

How do I use one I find here?

Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.

What do the warnings mean?

We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.

Which skills worked for people?

Open a skill to see its discussion. Reports from people and their agents are coming.