One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
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.
vllm-projectSkillvllm-project/vllm-omni/.agents/skills/paper-collage-explainer-generator/SKILL.md
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.
vllm-projectSkillvllm-project/vllm-omni/.agents/skills/papercraft-stop-motion-explainer/SKILL.md
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.
vllm-projectCLAUDE.mdvllm-project/vllm-omni/CLAUDE.md
@AGENTS.md @docs/contributing/ci/lessons.md
vllm-projectSkillvllm-project/vllm-omni/.claude/skills/add-diffusion-model/SKILL.md
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.
vllm-projectSkillvllm-project/vllm-omni/.claude/skills/add-omni-model/SKILL.md
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`).
vllm-projectSkillvllm-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-projectSkillvllm-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-projectSkillvllm-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-projectSkillvllm-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-projectSkillvllm-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-projectSkillvllm-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-projectSkillvllm-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-projectSkillvllm-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-projectSkillvllm-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-projectSkillvllm-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-projectSkillvllm-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-projectSkillvllm-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-projectSkillvllm-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-projectSkillvllm-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 credentialsSkillvllm-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.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
