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.
Surging4 mentions in 2 weeks
2 projects use a version of this
97k11d agoReviewMountCreate a free account to mount
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
97k11d agoReviewMountCreate a free account to mount
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
97k11d agoReviewMountCreate a free account to mount
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
97k11d agoReviewMountCreate a free account to mount
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`).
Surging4 mentions in 2 weeks
2 projects use a version of this
97k11d agoReviewMountCreate a free account to mount
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.
Surging4 mentions in 2 weeks
9 projects use a version of this
97k11d agoReviewMountCreate a free account to mount
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.
Surging4 mentions in 2 weeks
2 projects use a version of this
97k11d agoReviewMountCreate a free account to mount
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
97k11d agoReviewMountCreate a free account to mount
Develop stylized 3D narrative shorts through story, character and environment references, timed shot tables, storyboards, generation, and assembly. Use for coherent animated storytelling or its planning stages, not isolated image edits or photorealistic live action.
7.6k52d agoReviewMountCreate a free account to mount
Plan, prompt, or produce brand, product, website, app, and service promotional shorts using traceable assets, accurate claims, timed beats, and clear calls to action. Use for launch and campaign videos, not invented product evidence or long narrative films.
7.6k52d agoReviewMountCreate a free account to mount
Design or generate a two-player co-op game menu and opening animation from player names, title, style, and optional identity references. Use for character-led game intros, not playable game implementation or complex multi-page interfaces.
7.6k52d agoReviewMountCreate a free account to mount
Write MiniMax H3 video generation prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA. Use when rewriting multimodal requests into H3 prompt structures, composing integrated_multimodal_description, overall_soundscape, and non_diegetic_music, aligning keyframes, or defining reference labels for images, videos, and audio.
7.6k52d agoReviewMountCreate a free account to mount
Write or generate a continuous live-action scene with a rough luminous hand-drawn entity that contacts real objects, morphs, and escapes a slightly delayed handheld camera. Use for gentle surreal mixed-media shorts, not flat-vector-only animation or horror clips.
7.6k52d agoReviewMountCreate a free account to mount
Plan, prompt, or produce minimalist product advertising shorts from product images, preserving variants, material, color, concise typography, and rhythmic camera motion. Use for product launches and ecommerce films, not presenter-led ads or complex UI demonstrations.
7.6k52d agoReviewMountCreate a free account to mount
Plan, write, audit, or produce music videos with coordinated music, imagery, camera motion, optional performance, and lyric typography. Use for beat-aware MVs and instrumental visual narratives, not ordinary subtitle cleanup or unrelated video edits.
7.6k52d agoReviewMountCreate a free account to mount
Translate narration, ideas, or knowledge points into editorial halftone paper-collage metaphors, still prompts, storyboards, or stop-motion clips. Use for photographic cutout collage and tactile assembly, distinct from paper-puppet dioramas or generic cartoons.
7.6k52d agoReviewMountCreate a free account to mount
Turn knowledge topics into layered papercraft stop-motion explainers, including visual metaphors, miniature sets, prompts, storyboards, motion and sound plans, or rendered video. Use for tactile paper dioramas and mechanisms, not ordinary vector cartoons or photographic collage.
7.6k52d agoReviewMountCreate a free account to mount
Add a new diffusion model (text-to-image, text-to-video, image-to-video, text-to-audio, image editing) to vLLM-Omni, including native non-Diffusers ports, reference-parity validation, Cache-DiT, offload, and parallelism support (TP, SP/USP, CFG-Parallel, HSDP). Use when integrating or reviewing a new diffusion model, porting a Diffusers pipeline or custom model repository, creating a DiT adapter, reusing shared examples, or qualifying multi-GPU and memory optimizations.
7.6k52d agoReviewMountCreate a free account to mount
Integrate a new multi-stage autoregressive omni model (thinker/talker/code2wav style, multimodal input with text and speech output) into vLLM-Omni, from the Hugging Face reference through stage separation, pipeline and deploy config, stage input processors, async_chunk streaming, parity validation, tests, and recipe. Use when adding a model like Qwen3-Omni, Qwen2.5-Omni, or MiniCPM-o, splitting an omni checkpoint into stages, writing `pipeline.py` or `stage_input_processors/` hooks, wiring `_OMNI_MODELS` / `OMNI_PIPELINES`, or debugging parity of a newly integrated omni model. Not for diffusion models (`add-diffusion-model`) or TTS-only models (`add-tts-model`).
7.6k52d agoReviewMountCreate a free account to mount
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.
vllm-projectSkill