comfyui-agent-skill-mie
Agent skill for running registered ComfyUI workflows through a stable CLI, and for importing a user's own ComfyUI workflow into their private registry after review. Supports image, video, music, and speech generation, plus text-driven matting, face/expression transfer, and voice cloning, on a local or trusted self-hosted ComfyUI server (default http://127.0.0.1:8188). Can check server health, preflight workflow dependencies, and save the server URL. Runs only registered workflows and reviewed private-registry imports; does not execute arbitrary unreviewed workflow JSON.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Badge for your README
Markdown
[](/listings/miemieeeee--comfyui-agent-skill)HTML
<a href="/listings/miemieeeee--comfyui-agent-skill"><img src="/api/listings/miemieeeee--comfyui-agent-skill/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
Install (Recommended: pipx)
pipx install comfyui-agent-skill-mie comfyui-agent-skill-mie check comfyui-agent-skill-mie generate -p "a cute cat sitting on a windowsill at golden hour" comfyui-skill check comfyui-skill generate -p "a cute cat sitting on a windowsill at golden hour"
Alternative: uv tool install
uv tool install comfyui-agent-skill-mie comfyui-agent-skill-mie check comfyui-agent-skill-mie generate -p "a cute cat sitting on a windowsill at golden hour" comfyui-skill check comfyui-skill generate -p "a cute cat sitting on a windowsill at golden hour"
Source mode (for development / maintainers)
uv sync uv run --no-sync python -m comfyui check uv run --no-sync python -m comfyui generate -p "a cute cat sitting on a windowsill at golden hour"
Optional short command (after `uv sync` installs the project):
uv run --no-sync comfyui-skill check uv run --no-sync comfyui-skill generate -p "a cute cat sitting on a windowsill at golden hour"
From a local wheel (for testing before PyPI publish):
pipx install dist/comfyui_agent_skill_mie-*.whl
Or install from GitHub:
pipx install "git+https://github.com/MieMieeeee/comfyui-agent-skill.git"
In tool-install mode, workflows/references are read from the installed package, while writable data goes to a per-user directory:
- Windows: `%APPDATA%\\comfyui-skill` - macOS: `~/Library/Application Support/comfyui-skill` - Linux: `$XDG_DATA_HOME/comfyui-skill` or `~/.local/share/comfyui-skill`
Short alias also available: `comfyui-skill`
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
SKILL.md · Manifest · 299 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- ---
- name: comfyui-agent-skill-mie
- description: >
- Agent skill for running registered ComfyUI workflows through a stable CLI,
- and for importing a user's own ComfyUI workflow into their private registry
- after review. Supports image, video, music, and speech generation, plus
- text-driven matting, face/expression transfer, and voice cloning, on a local
- or trusted self-hosted ComfyUI server (default http://127.0.0.1:8188). Can
- check server health, preflight workflow dependencies, and save the server
- URL. Runs only registered workflows and reviewed private-registry imports;
- does not execute arbitrary unreviewed workflow JSON.
- ---
- # comfyui-agent-skill-mie
- ## Purpose
- Run registered ComfyUI workflows through a stable Agent-facing CLI, with prompt enhancement, fail-fast errors, and structured JSON results.
- Use this skill when the user asks to:
- - Generate an image from text.
- - Generate a new image inspired by a reference image.
- - Edit an input image while preserving some structure or subject details.
- - Generate text-to-video or image-to-video MP4 output.
- - Generate music / instrumental / song-style MP3 output.
- - Synthesize spoken voice audio with Qwen3-TTS.
- - Cut out or mask an object in a picture by describing it in words.
- - Transfer a face, expression, or pose from a driving video onto a reference face photo.
- - Clone a specific voice from a reference audio sample and speak new text in that voice.
- - Check whether a ComfyUI server is available.
- - Import a workflow the user already validated in ComfyUI into their private registry, and activate it only after the generated config is reviewed.
- - Preflight a registered workflow's nodes and models before a long run.
- - Save a persistent ComfyUI server URL when the user asks.
- Do not use this skill when the user only wants prompt writing, brainstorming, or discussion without actual generation.
- A ComfyUI server being unavailable is not a reason to skip this skill. Return `SERVER_UNAVAILABLE`, ask whether ComfyUI is running on the local machine or on another machine, and point the user at `check` (single health check) and `doctor` (server health plus per-workflow preflight) to diagnose it.
- ## Hard Rules
- - Source mode: run CLI commands from the skill root (the directory containing `SKILL.md` and `scripts/`).
- - Tool-install mode: `comfyui-agent-skill-mie` / `comfyui-skill` can be run from any directory.
- - Source mode: use `uv run --no-sync python -m comfyui` (or `uv run --no-sync comfyui-skill`) for runtime calls.
- - Tool-install mode: use `comfyui-skill` (or `comfyui-agent-skill-mie`) directly; do not wrap with `uv run`.
- - Use registered workflows only. Do not run arbitrary unreviewed ComfyUI workflow JSON.
- - If server health fails, stop generation and return/handle `SERVER_UNAVAILABLE`; do not search disk for ComfyUI installs or guess ports.
- - Do not create or edit `config.local.json` unless the user explicitly wants a persistent server URL. For one-off runs, use `--server` or `COMFYUI_URL`.
- - For `reference_to_image`, inspect the reference image with Agent vision and create a prompt. Do not upload that reference image to ComfyUI.
- - Upload local media with the role's flag from the quick command table. `--image` is the image role. `liveportrait` also needs `--video`. `qwen3_tts_clone` needs `-p`, `--text-input "ref_text=..."`, and `--audio`. Do not choose those flags from the capability name.
- - Pass `--width`/`--height` only when the workflow config maps both dimensions and does not use `size_strategy: "workflow_managed"`; always pass both together. Otherwise the CLI returns `INVALID_PARAM` on both the sync and `--submit` paths instead of ignoring them.
- - Analyzer-generated workflow configs require human review before activation.
- ## Workflow Selection Policy
- - Built-in defaults are fallback choices, not hard requirements.
- - If another registered workflow is a stronger semantic match for the request, prefer the stronger match.
- - Use workflow capability metadata and workflow selection guidance to choose among registered workflows.
- - Any automatic workflow selection in the CLI is only a low-risk fallback when no explicit workflow has been chosen.
- - If multiple workflows appear suitable and the user’s preference is ambiguous, ask a brief clarifying question.
- ## User-Added Workflows
- - Users may add custom workflows that were first validated in ComfyUI, then imported into the skill as reviewed registered capabilities.
- - Do not execute arbitrary raw workflow JSON directly.
- - Import the workflow, generate/review the config template, and activate it only after a reviewed `workflow.config.json` exists.
- - User-added workflows must be stored in the per-user workflow registry so skill upgrades do not overwrite them.
- - Once activated, user-added workflows may be selected like other registered workflows when they are a stronger semantic match and required inputs are available.
- - `import-workflow` only accepts **API format** (ComfyUI's *Save (API)* button, requires *Settings → Enable Dev mode options*). A plain *Save* product (UI/Save format, `{nodes, links}`) is refused with `WORKFLOW_NOT_API_FORMAT`. To convert existing UI/Save workflows in place, run `convert-ui` (needs a running ComfyUI + Playwright).
- ## Setup
- Recommended install (tool-install mode):
- ```bash
- pipx install comfyui-agent-skill-mie
- ```
- - Install package: `comfyui-agent-skill-mie`
- - Main command: `comfyui-agent-skill-mie`
- - Short alias: `comfyui-skill`
- Prerequisites:
- - ComfyUI server with `GET /system_stats` available.
- - Python 3.10+.
- - Source mode only: `uv`.
- - Required ComfyUI models/custom nodes for the selected workflow.
- Networking note:
- - Default local examples use `http://127.0.0.1:8188` for same-environment setups.
- - If the agent runs inside WSL/container/sandbox while ComfyUI runs on the host OS, `127.0.0.1` may refer to the runtime itself. Try `--server http://localhost:8188` or the host machine IP (and optionally persist it via `save-server`).
- Initial setup from the skill root:
- ```bash
- uv sync
- uv run --no-sync python -m comfyui --help
- ```
- Tool-install mode:
- ```bash
- comfyui-agent-skill-mie --help
- comfyui-agent-skill-mie check
- comfyui-skill --help
- comfyui-skill check
- ```
- ## Quick Workflow Choice
- Minimal decision tree:
- - User gives text only → start from general T2I (`z_image_turbo` fallback), but prefer a stronger registered match when workflow guidance indicates one (e.g. posters / anime / artistic styles).
- - Poster / text-in-image requests → prefer `qwen_image_2512_4step`
- - Anime / manga / illustration style → prefer `anima_turbo`
- - Artistic / painterly realism / concept art / product → prefer `krea2_turbo`
- - User gives a reference image and wants a new similar image → vision → `reference_to_image` prompt → run `z_image_turbo`
- - User gives an input image and wants edits → `generate --workflow klein_edit --image input_image=... -p "..."`
- - User wants to mask / cut out an object by describing it → `sam3_mat_image`
- - User wants face/expression transfer (face photo + driving video) → `liveportrait`
- - User wants TTS / voice audio → `generate --workflow qwen3_tts --speech-text "..." --instruct "..."`
- - User wants to clone a specific voice from a sample → `qwen3_tts_clone`
- - User wants video → `ltx_23_t2v_distill` (text→video) or `ltx_23_i2v_distilled` (image→video)
- | User intent | Workflow / mode | Required command shape |
- |-------------|-----------------|------------------------|
- | Text to image (general fallback) | `z_image_turbo` | `generate -p "prompt"` |
- | Poster / embedded text (preferred) | `qwen_image_2512_4step` | `generate --workflow qwen_image_2512_4step -p "prompt"` |
- | Anime / manga / illustration | `anima_turbo` | `generate --workflow anima_turbo -p "prompt"` |
- | Artistic / painterly realism / concept art / product | `krea2_turbo` | `generate --workflow krea2_turbo -p "prompt"` |
- | Similar image from reference | Agent vision + T2I | Read reference image, create English prompt, then T2I |
- | Edit image | `klein_edit` | `generate --workflow klein_edit --image input_image=photo.png -p "edit prompt"` |
- | Mask / cut out an object (text-driven) | `sam3_mat_image` | `generate --workflow sam3_mat_image --image photo.png -p "the cat"` |
- | Face/expression transfer (photo + video) | `liveportrait` | `generate --workflow liveportrait --image face.png --video drive.mp4` |
- | Text to video | `ltx_23_t2v_distill` | `generate --workflow ltx_23_t2v_distill -p "shot prompt"` |
- | Image to video | `ltx_23_i2v_distilled` | `generate --workflow ltx_23_i2v_distilled --image input_image=photo.png -p "motion prompt"` |
- | Text to music | `ace_step_15_music` | `generate --workflow ace_step_15_music -p "music tags"` |
- | Text to speech | `qwen3_tts` | `generate --workflow qwen3_tts --speech-text "..." --instruct "..."` |
- | Voice cloning (from a sample) | `qwen3_tts_clone` | `generate --workflow qwen3_tts_clone -p "new text" --text-input "ref_text=..." --audio sample.mp3` |
- For workflow-specific size rules, capability boundaries, and examples, read [references/workflows.md](references/workflows.md).
- ## Core Commands
- Environment doctor (check server + preflight registered workflows):
- Tool-install mode:
- ```bash
- comfyui-skill doctor
- ```
- Source mode:
- ```bash
- uv run --no-sync python -m comfyui doctor
- ```
- If it exits with code 0, the environment is ready for all checked workflows. Exit code 1 means missing nodes/models or server is unreachable (see JSON payload).
- Health check:
- ```bash
- uv run --no-sync python -m comfyui check
- ```
- Tool-install mode:
- ```bash
- comfyui-skill check
- ```
- Generate an image:
- ```bash
- uv run --no-sync python -m comfyui generate -p "a cute cat sitting on a windowsill at golden hour"
- ```
- Tool-install mode:
- ```bash
- comfyui-skill generate -p "a cute cat sitting on a windowsill at golden hour"
- ```
- Generate with a specific workflow and server:
- ```bash
- uv run --no-sync python -m comfyui generate --workflow z_image_turbo --server http://192.168.1.100:8188 -p "a landscape"
- ```
- Save a persistent server URL only when the user asks for it:
- ```bash
- uv run --no-sync python -m comfyui save-server http://192.168.1.100:8188
- ```
- Preflight a workflow before a long run:
- ```bash
- uv run --no-sync python -m comfyui generate --workflow qwen_image_2512_4step --preflight
- ```
- Show progress for long jobs:
- ```bash
- uv run --no-sync python -m comfyui generate --workflow ltx_23_t2v_distill -p "cinematic waves at sunset, slow pan" --progress
- ```
- Convert UI/Save workflows to API format (opt-in; needs a running ComfyUI + Playwright, does not run inference):
- ```bash
- uv run --no-sync python -m comfyui convert-ui path/to/ui_workflow.json --server http://127.0.0.1:8188
- uv run --no-sync python -m comfyui convert-ui path/to/workflows_dir -o api_workflows/
- ```
- Full CLI options, output path behavior, async submit/poll, and error code details are in [references/cli.md](references/cli.md).
- ## Prompt Enhancement
- Before generation, convert the user's intent into the right workflow inputs.
- | Type | Read this file | Use when |
- |------|----------------|----------|
- | `character` | [references/prompt_enhancement/character.md](references/prompt_enhancement/character.md) | Portrait, person, character, figure photo |
- | `reference_to_image` | [references/prompt_enhancement/reference_to_image.md](references/prompt_enhancement/reference_to_image.md) | User provides a reference image and wants a new similar image |
- | `image_to_image` | [references/prompt_enhancement/image_to_image.md](references/prompt_enhancement/image_to_image.md) | User provides an input image and wants to edit it |
- | `text_to_speech` | [references/prompt_enhancement/text_to_speech.md](references/prompt_enhancement/text_to_speech.md) | User gives a short voice description and needs full Qwen3-TTS instruction |
- Reference-to-image flow:
- 1. Ensure a usable reference image exists; otherwise return Agent error `NO_REFERENCE_IMAGE`.
- 2. Ensure this runtime can inspect images; otherwise return Agent error `VISION_UNAVAILABLE`.
- 3. Read the reference prompt enhancement file and create one English prompt.
- 4. Call T2I generation with that prompt. Do not pass the reference image to ComfyUI.
- Image-to-image flow:
- 1. Ensure a local image path is available.
- 2. Read the image edit prompt enhancement file.
- 3. Call `klein_edit` with `--image input_image=path`.
- Text-to-speech flow:
- 1. Split user intent into spoken content and voice/style instruction.
- 2. Read the TTS prompt enhancement file.
- 3. Call `qwen3_tts` with `--speech-text` and `--instruct`; do not use positional prompt.
- ## Fail-Fast and Recovery
- CLI failures are structured JSON on stdout. Agent-only pre-check failures for reference images should also be JSON.
- Agent-only error shape:
- ```json
- {
- "source": "agent",
- "success": false,
- "error": {"code": "VISION_UNAVAILABLE", "message": "Cannot read reference image in this runtime."}
- }
- ```
- Required fail-fast behavior:
- - Missing prompt: return/handle `EMPTY_PROMPT`.
- - Unregistered workflow: return/handle `WORKFLOW_NOT_REGISTERED`.
- - Server unavailable: return/handle `SERVER_UNAVAILABLE` and ask whether ComfyUI is running locally or on another machine.
- - Missing reference image before `reference_to_image`: return Agent error `NO_REFERENCE_IMAGE`; do not call CLI.
- - No vision for `reference_to_image`: return Agent error `VISION_UNAVAILABLE`; do not call CLI.
- - Missing required input media: return/handle `NO_INPUT_IMAGE` when an image role is absent and `NO_INPUT_MEDIA` when a video or audio role is absent. If the local path does not exist, handle `INPUT_IMAGE_NOT_FOUND` or `INPUT_MEDIA_NOT_FOUND` respectively. Do not report a missing video or audio input as `NO_INPUT_IMAGE`.
- - A required mapped role that is present but empty: return/handle `MISSING_INPUT`.
- - Missing custom nodes/models during preflight: return/handle `PREFLIGHT_MISSING_NODES` or `PREFLIGHT_MISSING_MODELS`.
- When the user provides a remote ComfyUI address, save it only if they want persistence:
- ```bash
- uv run --no-sync python -m comfyui save-server http://<address>:<port>
- ```
- Otherwise retry the original command with `--server http://<address>:<port>`.
- ## Output Handling
- After successful generation, present the result to the user. Do not silently parse JSON and stop.
- - For images, display the file when the runtime supports local image display; otherwise provide the absolute/local path from `outputs[].path`.
- - For MP3/MP4, provide the path or use the runtime's media display/playback capability when available.
- - Prefer omitting `--output`; the CLI writes to a per-job directory under `results/` inside the per-user data root and returns exact paths in JSON. The per-user data root is `%APPDATA%\comfyui-skill` on Windows, `~/Library/Application Support/comfyui-skill` on macOS, and `$XDG_DATA_HOME/comfyui-skill` (or `~/.local/share/comfyui-skill`) on Linux. `save-server` writes `config.local.json` under that same root. Always use the returned `outputs[].path`.
- - For `--count > 1`, parse the wrapper object and present each result.
- See [references/cli.md](references/cli.md) for JSON schemas and output directory rules.
- ## References
- - [references/workflows.md](references/workflows.md) — workflow selection, capabilities, size rules, examples.
- - [references/cli.md](references/cli.md) — CLI contract, async jobs, output paths, JSON schemas, error codes.
- - `references/prompt_enhancement/` — prompt enhancement instructions.
README.md · README · 239 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- # ComfyUI Agent Skill
- This repository is an Agent Skill folder (Claude Code / Claude.ai / Agent Skills). The only required file is [SKILL.md](SKILL.md).
- - 中文文档: [README.zh-CN.md](README.zh-CN.md)
- ## Status
- - Requires a local or trusted self-hosted ComfyUI server (this repo is not a hosted service).
- - Not a hosted generation service; this package does not provide a ComfyUI backend.
- - This package does not install ComfyUI itself.
- - Stable interface: registered workflows only + CLI with structured JSON output.
- - Recommended trust model: do not point this at an untrusted public ComfyUI endpoint.
- - PyPI package: `comfyui-agent-skill-mie` (includes `comfyui-skill` alias).
- ## Registered Workflows
- Stable (reviewed configs in `assets/workflows/*.config.json`):
- - `z_image_turbo` (text-to-image)
- - `klein_edit` (image edit)
- - `qwen3_tts` (text-to-speech)
- - `ltx_23_t2v_distill` (text-to-video)
- - `ltx_23_i2v_distilled` (image-to-video)
- - `ace_step_15_music` (music/audio)
- - `qwen_image_2512_4step` (text-to-image)
- - `anima_turbo` (anime/illustration text-to-image)
- - `krea2_turbo` (artistic/painterly realism, concept art, product visualization)
- - `sam3_mat_image` (text-driven matting)
- - `liveportrait` (face/expression transfer)
- - `qwen3_tts_clone` (voice cloning)
- Source of truth: the runtime registry is derived from `assets/workflows/*.config.json` (and the corresponding `assets/workflows/*.json` workflow files). If this list drifts, trust the configs and `python -m comfyui generate --help` output.
- ## For Skill Users (Generate / Edit / Video / Audio)
- Use this when you want to run registered ComfyUI workflows via the CLI in this repo.
- - Primary entry: [SKILL.md](SKILL.md)
- - Workflow selection and sizing: [references/workflows.md](references/workflows.md)
- - Full CLI contract (output paths, async submit/poll, JSON schemas, error codes): [references/cli.md](references/cli.md)
- - Prompt enhancement playbooks: [references/prompt_enhancement/](references/prompt_enhancement/)
- ## Quick Start
- ### Install (Recommended: pipx)
- ```bash
- pipx install comfyui-agent-skill-mie
- comfyui-agent-skill-mie check
- comfyui-agent-skill-mie generate -p "a cute cat sitting on a windowsill at golden hour"
- comfyui-skill check
- comfyui-skill generate -p "a cute cat sitting on a windowsill at golden hour"
- ```
- ### Alternative: uv tool install
- ```bash
- uv tool install comfyui-agent-skill-mie
- comfyui-agent-skill-mie check
- comfyui-agent-skill-mie generate -p "a cute cat sitting on a windowsill at golden hour"
- comfyui-skill check
- comfyui-skill generate -p "a cute cat sitting on a windowsill at golden hour"
- ```
- ### Source mode (for development / maintainers)
- ```bash
- uv sync
- uv run --no-sync python -m comfyui check
- uv run --no-sync python -m comfyui generate -p "a cute cat sitting on a windowsill at golden hour"
- ```
- Optional short command (after `uv sync` installs the project):
- ```bash
- uv run --no-sync comfyui-skill check
- uv run --no-sync comfyui-skill generate -p "a cute cat sitting on a windowsill at golden hour"
- ```
- From a local wheel (for testing before PyPI publish):
- ```bash
- pipx install dist/comfyui_agent_skill_mie-*.whl
- ```
- Or install from GitHub:
- ```bash
- pipx install "git+https://github.com/MieMieeeee/comfyui-agent-skill.git"
- ```
- In tool-install mode, workflows/references are read from the installed package, while writable data goes to a per-user directory:
- - Windows: `%APPDATA%\\comfyui-skill`
- - macOS: `~/Library/Application Support/comfyui-skill`
- - Linux: `$XDG_DATA_HOME/comfyui-skill` or `~/.local/share/comfyui-skill`
- Short alias also available: `comfyui-skill`
- ## End-to-End Example (User input → decision → workflow → result)
- This project is designed for agent-first workflow selection:
- - The Agent makes the primary workflow decision using [SKILL.md](SKILL.md), workflow capability metadata, and [references/workflows.md](references/workflows.md).
- - The CLI only provides a low-risk fallback when no explicit `--workflow` is chosen.
- ### 1) User input (natural language)
- > "帮我做一张海报,标题写「夏日促销」,风格现代简洁,主色调蓝白。"
- ### 2) Decision (what gets chosen and why)
- - Task type: text-to-image
- - Strong cue: poster / embedded text requirement ("海报", "标题写…")
- - Prefer a stronger match over the general fallback T2I workflow
- - Selected workflow: `qwen_image_2512_4step`
- - Size choice: `704x1280` (HD portrait preset for posters)
- ### 3) CLI command (agent explicitly chooses the workflow)
- In this example, the agent explicitly chooses `qwen_image_2512_4step`; the CLI fallback selector is only a convenience when no explicit workflow is passed.
- ```bash
- comfyui-skill generate \
- --workflow qwen_image_2512_4step \
- --width 704 --height 1280 \
- -p "Modern minimalist marketing poster, blue and white palette, bold Chinese title text '夏日促销', clean layout, high contrast, product-focused composition"
- ```
- ### 4) Example JSON result (stdout)
- ```json
- {
- "success": true,
- "workflow_id": "qwen_image_2512_4step",
- "status": "completed",
- "outputs": [
- {
- "path": "C:\\\\Users\\\\<you>\\\\AppData\\\\Roaming\\\\comfyui-skill\\\\results\\\\20260504\\\\120301_<job_id>\\\\output.png",
- "filename": "output.png",
- "size_bytes": 1234567
- }
- ],
- "error": null,
- "job_id": "<prompt_id>",
- "metadata": {
- "seed": 123456789,
- "prompt_id": "<prompt_id>",
- "prompt": "Modern minimalist marketing poster ...",
- "width": 704,
- "height": 1280
- }
- }
- ```
- ## Adding Your Own Workflow (User Extension Example)
- If you want to add your own ComfyUI workflow and make it available to the skill, treat it as “connecting a proven ComfyUI graph as a reviewed capability”.
- ### 1) Export a working workflow from ComfyUI
- First make sure the workflow runs inside ComfyUI, then export it as API-format JSON.
- ### 2) Import into your per-user workflow registry
- Run:
- ```powershell
- python -m comfyui import-workflow .\my_workflow.json --id my_custom_workflow
- ```
- This writes files under your per-user skill data directory (not the packaged built-in workflow registry), for example:
- ```text
- <user_data_root>/custom_workflows/my_custom_workflow/
- workflow.json
- workflow.source.json
- workflow.config.template.json
- ```
- ### 3) Review and activate the config
- - Open `workflow.config.template.json`
- - Confirm the minimal required fields:
- - `description`, `capability`, `output_kind`, and the exposed inputs in `node_mapping`
- - Optional: improve agent choice by adding selection metadata:
- - `intent_categories`, `input_modes`, `priority`, `keywords_any`, `selection_guidance`
- - Rename the reviewed file to:
- ```text
- workflow.config.json
- ```
- Only `workflow.config.json` is treated as an activated registered workflow. The template is not loaded.
- User-added workflows are stored in the per-user skill data directory, not in the packaged built-in workflow registry, so upgrading the skill will not overwrite them.
- ### 4) Run using your custom workflow
- ```powershell
- comfyui-skill generate --workflow my_custom_workflow -p "test prompt"
- ```
- If you omit `--workflow`, the CLI may apply low-risk fallback selection (for example, poster-like keywords) but it will not attempt to fully “understand” arbitrary user workflows. Agent-first selection remains the intended model.
- ## Upgrade
- If you installed via pipx:
- ```bash
- pipx upgrade comfyui-agent-skill-mie
- ```
- If you installed via uv tool:
- ```bash
- uv tool upgrade comfyui-agent-skill-mie
- ```
- ## Troubleshooting
- - Run an environment doctor check (server + workflow preflight):
- - `comfyui-skill doctor` (recommended)
- - `comfyui-agent-skill-mie doctor`
- - `uv run --no-sync python -m comfyui doctor` (source mode)
- - If the agent/skill runs inside WSL/container/sandbox while ComfyUI runs on the host OS, `127.0.0.1` may point to the runtime itself instead of the host. Try `--server http://localhost:8188` or the host machine IP (and optionally persist it via `save-server`).
- - `SERVER_UNAVAILABLE`: ComfyUI is not reachable at the target URL. Start ComfyUI or re-run with `--server http://<ip>:8188`.
- - `PREFLIGHT_MISSING_NODES`: install/enable required custom nodes on the ComfyUI server.
- - `PREFLIGHT_MISSING_MODELS`: download required model files on the ComfyUI server.
- - `NO_OUTPUT`: workflow ran but no media could be retrieved; check the workflow output node and server logs/UI.
- - For `PREFLIGHT_MISSING_NODES`, `PREFLIGHT_MISSING_MODELS`, or `NO_OUTPUT`, consult the dependency reference: [references/workflow_nodes.md](references/workflow_nodes.md).
- ## For Maintainers (Add / Review Workflows)
- Maintenance docs are intentionally kept out of `SKILL.md` to keep the skill instructions user-focused.
- - Maintainer entry: [MAINTAINER.md](MAINTAINER.md)
- - Detailed workflow registration guide: [references/extension.md](references/extension.md)
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.