comfyui-to-python-extension
Route ComfyUI Save As Script and workflow export tasks into the CLI and Web UI sub-skills.
Skill by VectorSpaceLab
Chalk Labs
Need help deploying comfyui-to-python-extension?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/vectorspacelab-comfyui-to-python-extension
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/comfyui-to-python-extension
What's inside
- Skill name
comfyui-to-python-extension- Description
- Route ComfyUI Save As Script and workflow export tasks into the CLI and Web UI sub-skills.
- License
- MIT
- Metadata
- disco-role: operating
- Instructions
- 50 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (16)
- SKILL.md
- api-reference.md · references/
- configuration.md · references/
- install-and-setup.md · references/
- repo-provenance.md · references/
- repo-routing-metadata.json · references/
- troubleshooting.md · references/
- SKILL.md · sub-skills/cli-export/
- cli-reference.md · sub-skills/cli-export/references/
- generated-script-runtime.md · sub-skills/cli-export/references/
- troubleshooting.md · sub-skills/cli-export/references/
- export_smoke.py · sub-skills/cli-export/scripts/
- SKILL.md · sub-skills/web-ui-extension/
- install-and-discovery.md · sub-skills/web-ui-extension/references/
- troubleshooting.md · sub-skills/web-ui-extension/references/
- check_discovery.py · sub-skills/web-ui-extension/scripts/
SKILL.md (first lines)
# ComfyUI-to-Python Extension Use this router for the repository that turns ComfyUI node graphs into runnable Python and adds the in-UI **Save As Script** extension command. ## Start here - Read [`references/install-and-setup.md`](references/install-and-setup.md) when the user asks how to install, expose, or run the extension. - Read [`references/api-reference.md`](references/api-reference.md) when you need exact public class, function, or module names. - Read [`references/configuration.md`](references/configuration.md) when the question is about `COMFYUI_PATH`, default filenames, queue size, or generated-script runtime switches. - Read [`references/troubleshooting.md`](references/troubleshooting.md) for shared failure modes before you route into a sub-skill. - Read [`references/repo-provenance.md`](references/repo-provenance.md) if you need to check freshness or source state. - Read [`references/repo-routing-metadata.json`](references/repo-routing-metadata.json) if you need the router placement metadata for import. ## Route to `cli-export` Go to [`sub-skills/cli-export/SKILL.md`](sub-skills/cli-export/SKILL.md) when the task is about any of these: - converting `workflow_api.json` or another API-format workflow into Python - running `python -m comfyui_to_python` or the legacy `comfyui_to_python.py` wrapper - choosing `--input_file`, `--output_file`, or `--queue_size` - understanding the generated script layout, bootstrap, cleanup, or seed handling - running exported Python with ComfyUI, `torch`, or model files - debugging `COMFYUI_PATH`, `No module named 'torch'`, custom-node import, or generated-script runtime failures - smoke-testing export behavior with a tiny workflow ## Route to `web-ui-extension` Go to [`sub-skills/web-ui-extension/SKILL.md`](sub-skills/web-ui-extension/SKILL.md) when the task is about any of these: - installing the repo as a ComfyUI custom node - making **File -> Save As Script** appear in the ComfyUI UI - understanding `__init__.py`, the `/saveasscript` route, or the frontend menu command - using `extra_model_paths.yaml`, symlinks, or `ComfyUI/custom_nodes` discovery - diagnosing why the extension does not show up after restart - the browser-side download flow and the default `workflow_api.py` filename ## Shared facts - The project targets Python 3.12+. - `black` is required by the exporter path. - `COMFYUI_PATH` is the primary runtime locator when ComfyUI is not already discoverable from the current working directory. - Generated scripts still need a real ComfyUI runtime, not just this repository checkout. ## Working rules - Keep generated guidance self-contained. Use the bundled references and scripts under this skill tree instead of pointing back to the source checkout. - Prefer the narrowest sub-skill that matches the request. - If the user mixes UI installation and CLI export concerns, answer from the more specific route first and cross-reference the other route only when needed.
From VectorSpaceLab/AREX-Skill, MIT.
More from VectorSpaceLab/AREX-Skill
- 0.563score
data-designer-repo-skill
VectorSpaceLab
Use when you need to design DataDesigner configs, run preview/create/validate workflows, inspect the CLI or agent context, work with plugins or MCP tools, or…
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
everos
VectorSpaceLab
Use this skill for EverOS local-first Markdown memory service setup, HTTP memory and knowledge APIs, cascade/OME operations, and observability integration.
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
bentoml
VectorSpaceLab
Use BentoML to author model-serving Services, build and containerize Bentos, run HTTP/gRPC servers and clients, manage models, operate the CLI and BentoCloud…
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
dash
VectorSpaceLab
Use when building, debugging, testing, or maintaining Plotly Dash applications, callbacks, server backends, component packages, renderer internals, and Dash…
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
diffusers
VectorSpaceLab
Use this skill for Hugging Face Diffusers tasks: pipeline inference, schedulers, adapters/loaders, training recipes, modular pipelines, conversion helpers…
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
espnet
VectorSpaceLab
Use when working with ESPnet speech AI toolkit: installation, ESPnet2 recipes and training, pretrained inference/model zoo, ESPnet3 stage workflows, and…
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
alphafold3
VectorSpaceLab
Use this skill for AlphaFold 3 input preparation, prediction command planning, output interpretation, and Python API inspection.
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
autogen
VectorSpaceLab
Use this skill for maintaining, migrating, debugging, and safely operating Microsoft AutoGen Python 0.7.x applications, including AgentChat, Core runtimes…
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
browser-use
VectorSpaceLab
Use this self-contained Browser Use repo skill for Python agents that automate websites, browser sessions, custom tools, LLM/provider setup, persistent CLI…
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
dagster
VectorSpaceLab
Use when working with Dagster OSS: assets, jobs, Definitions, config/resources, schedules/sensors, automation, CLI/local development, deployment operations…
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
datasets
VectorSpaceLab
Use this skill when working with Hugging Face Datasets: loading local or Hub datasets, defining Features schemas, processing/streaming datasets, converting…
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
geopandas
VectorSpaceLab
Use when working with GeoPandas GeoDataFrame and GeoSeries workflows, vector geospatial I/O, CRS-aware spatial operations, mapping, geocoding, and…
SkillBFreshness: B★ 341Claude Code +9
Signals
- Stars
- 341
- Forks
- 26
- Open issues
- 0
- Last commit (this folder)
- Aug 26, 2026 (2 months ago)
- Last release
- Sep 2, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/VectorSpaceLab/AREX-Skill
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from VectorSpaceLab
- 0.563score
bentoml
VectorSpaceLab
Use BentoML to author model-serving Services, build and containerize Bentos, run HTTP/gRPC servers and clients, manage models, operate the CLI and BentoCloud…
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
dagster
VectorSpaceLab
Use when working with Dagster OSS: assets, jobs, Definitions, config/resources, schedules/sensors, automation, CLI/local development, deployment operations…
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
alphafold3
VectorSpaceLab
Use this skill for AlphaFold 3 input preparation, prediction command planning, output interpretation, and Python API inspection.
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
autogen
VectorSpaceLab
Use this skill for maintaining, migrating, debugging, and safely operating Microsoft AutoGen Python 0.7.x applications, including AgentChat, Core runtimes…
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
browser-use
VectorSpaceLab
Use this self-contained Browser Use repo skill for Python agents that automate websites, browser sessions, custom tools, LLM/provider setup, persistent CLI…
SkillBFreshness: B★ 341Claude Code +9 - 0.563score
dash
VectorSpaceLab
Use when building, debugging, testing, or maintaining Plotly Dash applications, callbacks, server backends, component packages, renderer internals, and Dash…
SkillBFreshness: B★ 341Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get comfyui-to-python-extension running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
comfyui-to-python-extension skill. Agent Mart. https://agentmart.dev/skills/vectorspacelab-comfyui-to-python-extension (last updated 2026-10-24)