…y dependency

Complete rewrite of the ComfyUI skill to use:
- comfy-cli (official, Comfy-Org/comfy-cli) for lifecycle management:
  install, launch, stop, node management, model downloads
- Direct REST API + helper scripts for workflow execution:
  parameter injection, submission, monitoring, output download
- No dependency on comfyui-skill-cli or any unofficial tool

New files:
- SKILL.md: full rewrite with two-layer architecture, decision tree, pitfalls
- references/official-cli.md: complete comfy-cli command reference
- references/rest-api.md: all REST endpoints (local + cloud)
- references/workflow-format.md: API format spec, common nodes, param mapping
- scripts/extract_schema.py: analyze workflow → extract controllable params
- scripts/run_workflow.py: inject args, submit, poll, download outputs
- scripts/check_deps.py: check missing nodes/models against running server
- scripts/comfyui_setup.sh: full setup automation with official CLI

Removed:
- references/cli-reference.md (was for unofficial comfyui-skill-cli)
- references/api-notes.md (replaced by rest-api.md)

Addresses feedback from PR #17316 comment:
- Correct author attribution
- Remove references to unofficial OpenClaw project
- License field reflects hermes-agent repo (MIT)

…links, cloud setup

Adds structured onboarding flow to SKILL.md:
- Decision table: which install path for which situation
- Path A: Comfy Cloud (zero setup, API key, pricing)
- Path B: Desktop app (Windows/macOS, one-click)
- Path C: Portable build (Windows, extract-and-run)
- Path D: comfy-cli (recommended for agents, all platforms)
- Path E: Manual install (advanced, all hardware types)
- Post-install: model downloads, custom nodes, verification

All paths link to official docs:
- https://docs.comfy.org/installation
- https://docs.comfy.org/comfy-cli/getting-started
- https://docs.comfy.org/get_started/cloud
- https://docs.comfy.org/installation/desktop
- https://docs.comfy.org/installation/comfyui_portable_windows
- https://docs.comfy.org/installation/manual_install

…to onboarding

Instead of asking the user what they have, the agent now:
1. Runs system detection commands (OS, GPU, VRAM, RAM, disk, Python)
2. Checks if ComfyUI is already installed/running
3. Recommends the best path based on findings

Adds:
- Step 1: detection script block (nvidia-smi, system_profiler, etc.)
- Step 2: decision table mapping detected system → recommended path
- Hardware requirements table (VRAM tiers, RAM, disk)
- Specific recommendations per platform:
  macOS → Desktop app, Linux+NVIDIA → comfy-cli, no GPU → Cloud, etc.