Claude skills and agent skills

vllm-projectSkill

add-recipe

vllm-project/vllm-omni/.claude/skills/add-recipe/SKILL.md

Add or update an in-repository vLLM-Omni model recipe with verified task, input, output, hardware, command, feature, and validation contracts. Use when creating files under recipes/, restructuring a recipe after review, documenting a newly supported model, or synchronizing recipe claims with support tables and shared feature guides.

vllm-projectSkill

add-tts-model

vllm-project/vllm-omni/.claude/skills/add-tts-model/SKILL.md

Integrate a new text-to-speech model into vLLM-Omni from HuggingFace reference implementation through production-ready serving with streaming and CUDA graph acceleration. Use when adding a new TTS model, wiring stage separation for speech synthesis, enabling online voice generation serving, debugging TTS integration behavior, or building audio output pipelines.

vllm-projectSkill

diffusion-accuracy-test

vllm-project/vllm-omni/.claude/skills/diffusion-accuracy-test/SKILL.md

Add or extend numerical accuracy tests and Buildkite CI coverage for existing vLLM-Omni diffusion image and video models, using aligned reference outputs and scoped tolerances. Use for native/reference parity or accuracy checks for acceleration features; generation smoke tests and performance benchmarking are separate workflows.

vllm-projectSkill

diffusion-perf-opt

vllm-project/vllm-omni/.claude/skills/diffusion-perf-opt/SKILL.md

Diagnose and optimize vLLM Omni diffusion workloads, especially Wan/Qwen/Flux-style image and video generation. Use when Codex is asked to analyze profiling traces, choose parallel strategies, inspect torch profiler trace.json or trace.json.gz timelines, estimate optimization ROI, investigate GPU idle/free bubbles, compare USP/CFG/HSDP/VAE parallelism, or design operator/host/quantization optimizations for vLLM Omni.

vllm-projectSkill

diffusion-perf-test

vllm-project/vllm-omni/.claude/skills/diffusion-perf-test/SKILL.md

Add or extend nightly/weekly performance-benchmark CI coverage for an existing vLLM-Omni diffusion image or video model, using the unified run_benchmark.py config schema, Buildkite Perf steps, and retained result artifacts. Use when adding performance watch cases and their CI wiring; numerical accuracy testing is diffusion-accuracy-test and optimization diagnosis is diffusion-perf-opt.

vllm-projectSkill

dit-npu-fusion-analysis

vllm-project/vllm-omni/.claude/skills/dit-npu-fusion-analysis/SKILL.md

Route Ascend NPU diffusion model and operator optimization to MindIE-SD skills. Use for NPU DiT fusion, profiling, kernel/pattern work and related parallelism, VAE or host bottlenecks. Supply Omni context and load the applicable external skill. CUDA/ROCm tuning, pure AR optimization and runner-version upgrades use their own workflows.

vllm-projectSkill

find-simplifications

vllm-project/vllm-omni/.claude/skills/find-simplifications/SKILL.md

Find evidence-backed simplification candidates in vLLM-Omni and, when requested, turn them into focused proposals or code changes. Use for audits of dead, duplicated, speculative, over-generalized, unnecessarily defensive, or hand-rolled code. Use review-pr for ordinary correctness review and diffusion-perf-opt for performance-first optimization.

vllm-projectSkill

omni-perf-opt

vllm-project/vllm-omni/.claude/skills/omni-perf-opt/SKILL.md

Diagnose and optimize serving performance of multi-stage autoregressive omni models in vLLM-Omni (Qwen3-Omni, Qwen2.5-Omni, MiniCPM-o, and similar thinker/talker/code2wav pipelines). Use when asked to lower TTFT or first-audio latency (AUDIO_TTFP), keep AUDIO_RTF below 1 under load, raise throughput or concurrency, fit stages on fewer GPUs, fix choppy streaming audio, attribute latency to a stage or connector, tune deploy YAML performance knobs (batching, CUDA graphs, async_chunk codec chunking, MRv2, replicas), or plan and validate omni performance PRs. Diffusion workloads use `diffusion-perf-opt`.

vllm-projectSkill

precheck-pr

vllm-project/vllm-omni/.claude/skills/precheck-pr/SKILL.md

Self-check your branch before creating a PR — catch dead code, prevent new model-specific Python examples, verify accuracy/perf claims, validate PR title format, and confirm merge readiness. Use before implementing a contribution and when the user says "precheck", "self review", "pre-submit check", or "check my PR before I open it." Never posts to GitHub.

vllm-projectSkill

production-add-diffusion-model

vllm-project/vllm-omni/.claude/skills/production-add-diffusion-model/SKILL.md

Productionize a vLLM-Omni diffusion model after its Day-0 vertical slice works. Use when work requires official API parity and input limits, feature-combination evidence, online FP8, distributed layerwise offload, per-request Cache-DiT, CUDA/ROCm/NPU/XPU recipes, faster or sparse attention, fused operators, USP or disaggregation analysis, continuous batching and abort handling, long-running RPS stability, or accuracy/performance/reliability CI. For initial architecture porting, registry wiring, and basic weight loading, use add-diffusion-model first.

vllm-projectSkill

quantization

vllm-project/vllm-omni/.claude/skills/quantization/SKILL.md

Work on vLLM-Omni quantization for diffusion, autoregressive, omni, or multi-stage models. Use when choosing or adding methods such as fp8, int8, gguf, mxfp8, mxfp4, mxfp4_dualscale, ModelOpt, AutoRound, INC, msModelSlim, awq, or gptq; debugging quantized loading; or validating memory, speed, and output quality.

vllm-projectSkill

review-pr

vllm-project/vllm-omni/.claude/skills/review-pr/SKILL.md

Review pull requests and local branches for vllm-project/vllm-omni with a frozen snapshot, module-design ownership, feature-design overlays, targeted validation, and concise evidence-backed findings. Use for default, detailed, or repeat maintainer reviews; checking correctness, compatibility, tests, benchmarks, model additions, distributed changes, or breaking behavior; and identifying or explicitly requesting the most relevant code-owner reviewers. Use precheck-pr instead for an author's pre-submit self-check.

vllm-projectSkill

vllm-omni-npu-model-runner-upgrade

vllm-project/vllm-omni/.claude/skills/vllm-omni-npu-upgrade/SKILL.md

Upgrade vllm-omni NPU model runners (OmniNPUModelRunner, NPUARModelRunner, NPUGenerationModelRunner) to align with the latest vllm-ascend NPUModelRunner while preserving omni-specific logic.

vllm-projectSkill

vllm-omni

vllm-project/vllm-omni/.claude/skills/vllm-omni/SKILL.md

Deploy, serve, debug, benchmark, and extend multi-stage omni models in vLLM-Omni (Qwen3-Omni, Qwen2.5-Omni, MiniCPM-o, and similar thinker/talker/code2wav pipelines). Use when writing or tuning deploy YAML under vllm_omni/deploy, launching `vllm serve --omni`, diagnosing stage startup hangs, OOM, connector stalls, or broken streaming audio, measuring TTFT/AUDIO_TTFP/AUDIO_RTF with `vllm bench serve --omni`, or navigating the orchestrator and stage runtime code. Routes new omni model integration to `add-omni-model`, omni performance optimization to `omni-perf-opt`, and diffusion, TTS-only, quantization, testing, recipe, and PR tasks to their dedicated skills.

vllm-projectReads credentialsSkill

vllm-omni-test

vllm-project/vllm-omni/.claude/skills/vllm-omni-test/SKILL.md

Generate and run tests for vllm-project/vllm-omni with CI-aligned levels and markers; wire new tests into Buildkite (test-ready.yml for L1/L2, test-merge.yml for L3, test-nightly.yml for L4). On completion, always provide copy-paste local and CI-like pytest commands plus prerequisites. Use when creating regression tests, adding L1-L4 coverage, selecting pytest markers, or validating fixes from issues/PRs.

vllm-projectSkill

contribute-research

vllm-project/llm-compressor/.agents/skills/contribute-research/SKILL.md

Create, update, or review LLM Compressor Open Research Hub entries in docs/research from experiment results, logs, or issue discussions.

No other project uses it yet

vllm-projectSkill

create-tiny-model

vllm-project/llm-compressor/.agents/skills/create-tiny-model/SKILL.md

Create and manage tiny models for testing and development. Includes utilities for saving tiny models, inspecting tensors, and finetuning workflows.

No other project uses it yet

vllm-projectSkill

vllm-ascend-model-adapter

vllm-project/vllm-ascend/.agents/skills/vllm-ascend-model-adapter/SKILL.md

Adapt and debug existing or new models for vLLM on Ascend NPU. Implement in /vllm-workspace/vllm and /vllm-workspace/vllm-ascend, validate via direct vllm serve from /workspace, and deliver one signed commit in the current repo.

No other project uses it yet

vllm-projectReads credentialsSkill

vllm-ascend-release

vllm-project/vllm-ascend/.agents/skills/vllm-ascend-release/SKILL.md

End-to-end release management skill for vLLM Ascend. Creates release checklist issues, triages critical bugs, audits test coverage, aggregates release note fragments, and guides through the complete release process.

No other project uses it yet

vllm-projectSkill

guidellm-review-translation

vllm-project/guidellm/.agents/skills/guidellm-review-translation/SKILL.md

Review a GuideLLM translation pull request by number, detect its target languages, and compare translated documentation in any language with the English source. Produce an English report for English-speaking reviewers, noting minor differences but recommending edits only for major errors or project Code of Conduct violations.

No other project uses it yet