agenty

Plugin agenty from marketplace agentY in szprivate/agentY-mcp. Commands read from the repo's manifest — today.

Skills (30)

• annotation

  Handles user-provided annotated images. When the user submits a drawing or mark-up on top of an image alongside a message, this skill wires the last generated output as the primary edit target and the annotation as the second (control/reference) input, then selects an appropriate image-editing templ

• assemble-from-template

  Assembles a workflow on the basis of a brainbriefing JSON and a pre-selected template.

• assemble-new-workflow

  Build a ComfyUI workflow from scratch when no template matches (template.name == "build_new"). Builds to the standard in the recipe database (task -> model -> node clusters), starting from a recipe member template.

• assemble-workflow-learnings

  Consult long-term memory before assembling or patching a ComfyUI workflow, and especially before retrying a failing pattern (repeated tool calls to fix the same assembly sub-problem, or the same validation error recurring). Every prior session's problem→solution lessons live in long-term memory (loc

• camera-move-control

  Make a new shot with a chosen camera move from ONE picture - picture to 3D scene, animate a camera through it in the ComfyUI Image Viewer, render the move, and use the render as the control video of a video model (Wan Fun Control, LTX IC-LoRA). Use for "fly the camera through this", "a low drone pas

• character-animation

  Rig and animate a character in the ComfyUI Image Viewer's 3D space - controls on a skinned model, auto-rig a model with no skeleton (UniRig), AI motion from a text prompt and AI in-betweens between keyed poses (NVIDIA Kimodo), feet pinned to the floor, motion restyled ("make the walk sneaky"), motio

• custom-node-from-github

  Turn a model's GitHub repository (already cloned locally) into a self-contained, importable ComfyUI custom-node pack — __init__.py, nodes.py, requirements.txt, README.md, pyproject.toml. Use when handed a repo_dir to read and an empty pack_dir to fill.

• dashscope-generate

  Generate an image or video with an Alibaba DashScope (Model Studio) model - Wan, HappyHorse, Qwen-Image - billed to the user's own DashScope key instead of ComfyUI partner credits. Activate when the user names a DashScope / Alibaba / Wan / HappyHorse / Qwen-Image model, or when a partner node fails

• dcc-destruction-houdini

  Destroy a 3D model in Houdini with a rigid-body (RBD) simulation — a building, a set or an object collapsing, breaking apart, being knocked over — plus dust and simple cloth, rendered as an OpenGL flipbook (or Karma for a single frame). Use for "make the house collapse", "destroy this in Houdini", "

• deadline-farm

  Render a ComfyUI workflow on the studio's Deadline render farm instead of the local ComfyUI. Use for "render this on the farm", "send it to Deadline", "run 20 variations on the farm", "is the farm free", "what happened to my farm job", "get the farm results".

• execution-modes

  Where the open-weight models of a run execute - this machine's GPU or Comfy Cloud. Use for "run this in the cloud", "use Comfy Cloud", "keep it local", "run it on my GPU", "why did that run in the cloud", "what did that cost", "it says a model is missing / does not fit", or any run that came back wi

• flux-sampling

  ModelSamplingFlux node patch requirements. Activate in Brain step 2 (Patch and validate) whenever the workflow contains a ModelSamplingFlux node.

• image-downsize

  Resize images to a specific resolution OR downsize to fit Claude API upload limits (max 1568px long edge, max 5MB). Use the exact-resize mode when the user requests a specific width/height; use downsize mode before sending images to Claude for analysis.

• kling-multishot

  Kling 3.0 multi-shot storyboard (template Kling3_multiShot). Activate in the Query Templates when the selected template is Kling3_multiShot — overrides the standard prompting step. Activate in the Assemble Workflow during assembly of the Kling3_multiShot template to patch storyboard nodes correctly.

• lora-training

  Train a LoRA for an image or video model - a person, pet, product, style or motion - with the agent doing every preparation step and the USER approving the dataset before anything trains. Use for "train a LoRA of my dog", "make a style LoRA from these pictures", "teach Wan this motion", "fine-tune Z

• model-from-reference

  Model a building, object or set in a 3D app (Blender, Maya or Houdini) so that it matches a reference photo — the way a 3D artist does it - measure the photo, match the camera, block out grey shapes until the silhouette and proportions match, THEN details, THEN materials and light. Use for "model th

• motion-graphics-scene

  Make EDITABLE motion graphics - titles, lower thirds, logo reveals, animated text / shapes / pictures - by writing a scene file (*.mgscene.json, data, not React), checking it, looking at stills, rendering it to video, and opening it in the viewer's Motion panel so the user can change layers and keyf

• output-paths

  Media-kind output_path mapping for brainbriefing output_nodes. Activate during step 6 (Identify output nodes) to set the correct output_path for each output node.

• partner-run

  Run ONE partner (API) node directly - Seedance, Kling, GPT Image, Nano Banana / Gemini image, Ideogram, Meshy, Veo, Runway, Hailuo ... - with partner_run, no template search. Activate when the request names a partner model or node and the job is that node alone (text/image/first-frame/reference to i

• prompting

  ComfyUI prompt engineering — universal CLIP/weight syntax plus per-model prompt rules loaded on demand from references/. Activate whenever composing a generation or edit prompt.

• recipe

  Recipe-based ComfyUI workflow building — the (task -> model -> node clusters) knowledge base. Front door for building a workflow from a recipe; the full build procedure lives in the assemble-new-workflow skill.

• seedance-reference

  Seedance 2.0/2.5 node wiring (ByteDance2ReferenceNode, ByteDance2TextToVideoNode, ByteDance2FirstLastFrameNode). Activate in the Query Templates when a Seedance template is selected, and in the Assemble Workflow when patching one — it carries the model-version choice, the reference-slot binding orde

• show-in-viewer

  Load files into the ComfyUI Image Viewer when the user asks to see them there, and read what it shows (frame, range, marks) - "show me clip 3 in the viewer", "open these frames side by side", "open the edit", "put the two renders side by side". Also opens an edit's cut in the viewer's Edit panel, an

• story-scene

  Expand a synopsis into a sequence of consistent, visual scene descriptions that serve as the starting point for start-frame image and video generation. Activate when the user provides (or you just produced) a synopsis and wants it turned into scenes.

• story-storyboard

  Turn a whole storyline into a production blueprint for a short film: a story bible plus the entire story split into Kling multi-shot SEQUENCES of <=10s each, ending with a single machine-readable JSON spec. Activate when the user asks for a short-film / storyboard breakdown to be rendered as video s

• story-synopsis

  Write a very short synopsis (a logline of a few words up to ~2 short sentences) capturing a storyline's premise. Activate whenever the user wants a new story idea, logline, premise, or storyline seed.

• upscale-ultimatesd

  Ultimate SD upscaler on Flux1-dev fp8 (template upscale_ultimateSD). Activate in the Query Templates when the selected template is upscale_ultimateSD. Activate in the Assemble Workflow during assembly of the upscale_ultimateSD template to patch the UltimateSDUpscale node, ensure the Flux1-dev fp8 ch

• video-gemini-motionpromptgeneration

  Analyse video input using Gemini, create motion prompts. Activate when brainbriefing template name contains 'video_gemini_motionPromptGeneration'. Patchable: Input video, Output; Locked: Structural nodes, Sampler recipe, and Resolution-driven logic.

• workflow-templates

  Select ComfyUI workflow templates based on user requests. Retrieves metadata about the workflow, such as used models and input / output nodes, to assist with workflow assembly.

• worldlabs-atlas

  Make a 3D scene from a picture or a text prompt with World Labs Atlas (a depth mesh in the picture's camera), grow it with new views, use it as the set for render_camera_move, and render single new views of it from any camera (consistent backgrounds). Use for "turn this image into a 3D world with At

Slash commands (5)

• /agenty:agenty-atlas

  Turn a picture or a prompt into a 3D scene with World Labs Atlas, then fly a camera through it or render new views.

• /agenty:agenty-cost

  Price a workflow in credits before running it, and compare cheaper settings.

• /agenty:agenty-destroy

  Destroy a 3D model in Houdini (collapse, break, knock over) with a rigid-body sim, dust and a flipbook or Karma render.

• /agenty:agenty-generate

  Generate or edit an image or video with agentY (template or partner model), price-checked, validated and looked at.

• /agenty:agenty-model-from-photo

  Model a building, object or room in Blender, Maya or Houdini so it matches a reference photo.

Subagents (2)

• agenty-scout

  Cheap, read-only look-ups about the system: which templates, models, nodes or skills exist, what a workflow does, which model suits a task, what a node's inputs are, or facts and reference images from the web. Never builds or runs anything. Use before deciding, or for a question that only needs an a

• agenty

  Drive ComfyUI, partner (API) models, 3D apps (Blender, Maya, Houdini), World Labs Atlas and the Deadline farm with agentY's tools. Use for any image, video or 3D job that needs more than one or two tool calls, so the long tool traffic stays out of the main conversation; hand it the request and every

MCP servers (1)

• agentY

  runs: uv run --no-project --with-requirements ${CLAUDE_PLUGIN_ROOT}/requirements-plugin.txt python -m src

Similar plugins