Skills for Real Engineers. Straight from my .agents directory.
39 skills
comfyui-launch-flags
Agent skill from
Pick the right ComfyUI startup flags for VRAM, attention, caching, and speed. The full decision matrix for OOM (--novram / --cache-none / --disable-smart-memory), shared-VRAM creep on Windows (--reserve-vram N), model-switching with big text encoders (--cache-none), high-VRAM throughput (--gpu-only / --highvram), and attention-backend selection (--use-sage-attention for speed, --use-pytorch-cross-attention as the highest-quality / Z-Image-safe fallback). Also the acceleration-stack + Blackwell/RTX 5000 (sm_120) notes. Use when a graph OOMs (especially long video like LTX 2 / WAN), when the GPU spills into shared VRAM and slows to a crawl, when switching between models eats all RAM, when Z-Image produces black/garbled output under Sage, or when deciding which attention backend to launch with. Flag names verified against upstream comfy/cli_args.py; see Sources.
How to install comfyui-launch-flags
install comfyui-launch-flags
# install the comfyui-mcp pack with the skills CLI
npx skills add artokun/comfyui-mcp# or add only this skill to Claude Code: copy the folder
plugin/skills/comfyui-launch-flags/
# into
~/.claude/skills/comfyui-launch-flags/ (all projects)
.claude/skills/comfyui-launch-flags/ (one project)
1# ComfyUI launch/performance flags23## Overview45CLI flags passed to `main.py` control ComfyUI's runtime behavior6(e.g. `python main.py --reserve-vram 2 --use-sage-attention`). The three that7matter most for making a graph *run* rather than OOM or crawl are the8VRAM strategy, the attention backend, and the cache mode. This skill9is the decision matrix for choosing them.1011> ⚠️ **Verification note (August 2026).** Every flag below was checked against12> upstream [`comfy/cli_args.py`](https://github.com/comfyanonymous/ComfyUI/blob/master/comfy/cli_args.py)13> on current master. ComfyUI adds/renames flags often — when in doubt run14> `python main.py --help` in the target install and prefer that over this list.15> **`--enable-triton-backend` / `--disable-triton-backend` ARE ComfyUI `main.py`16> flags on master** (they used to be documented as SwarmUI-only; that is stale).17> `--use-ck-attention` is kitchen INT8 attention — no `sageattention` wheel.18> A June ComfyUI checkout still pins comfy-kitchen 0.2.10 and lacks19> `--use-ck-attention`; `kitchen` action:"status" reports ComfyUI-side flag20> support, not only the kitchen version. Use `kitchen` / `panel_kitchen` to see21> what this GPU can actually run.2223> How to apply today. The MCP's `restart_comfyui` (with `action: "start"`)24> currently *replays the exact argv of the previous run*. It does not compose25> fresh flags. So set these when you launch ComfyUI yourself (the26…
Excerpt shown under the repository's MIT license.
More skills in comfyui-mcp
Keep exploring
Similar skill repositories
An agentic skills framework & software development methodology that works.
15 skills
Public repository for Agent Skills
20 skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
CCCU6 skills
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
CCCXCUGH6 skills
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
CCCXGHGM+135 skills