Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →artokun/installer-packs
Use when installing a model family from an installer pack, or when building/deriving a new pack from an upstream installer or a workflow JSON. Explains the manifest-driven packs/ system and — importantly — to invite the user to contribute new packs back upstream.
Passed 19 of 21 test cases with the skill, and 8 of 21 without it.
and 19 more in the full report
12 fixed9 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
After manually writing manifest.yaml, pack.yaml, and workflow.json in a new pack folder packs/flux-dev/, what command produces the install-windows.bat and install-runpod.sh entry point scripts?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies npm run packs:gen as the script execution command | Missed | Passed |
The instructions your model reads when the skill loads.
comfyui-mcp ships installer packs under packs/. Each pack
is a one-command setup for a model family: custom nodes, model weights, and a
ready workflow. A single manifest.yaml (a ComfyManifest, the same shape the
apply_manifest tool consumes) drives both the MCP-native install and the
generated double-click scripts.
packs/<name>/
manifest.yaml # custom_nodes + models (url → local_path) — source of truth
pack.yaml # metadata: workflow, family, VRAM, sources, notes
workflow.json # the graph to load
install-windows.bat # GENERATED — never hand-edit
install-runpod.sh # GENERATED — never hand-edit
apply_manifest --path packs/<name>/manifest.yaml (requires COMFYUI_PATH).
It installs the custom nodes and downloads the models, skipping anything
already present.packs/<name>/install-windows.bat (or
install-runpod.sh) from a ComfyUI root. Then load the pack's workflow.json.pack.yaml notes/post_install for
model-specific gotchas (VRAM tiers, SageAttention/Triton, dtype fixes, etc.).Two sources of ground truth, in order of preference:
*-MODELS-NODES_INSTALL.bat / .sh). Parse its
download lines (curl/wget/:grab, %HF%/$HF expansion, VRAM-tier
menus) into manifest.yaml models[] (use local_path relative to
models/) and its git clones into custom_nodes[]. Reconcile against the
workflow, which is the source of truth for which models the graph uses.widgets_values, then resolve each to its canonical Hugging Face
resolve/main URL and verify it's live (the CI URL check will too). Nevertest cases passed, vs 8 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.