comfyui-research
Research latest ComfyUI models, techniques, and community discoveries. Monitors YouTube channels, GitHub repos, and HuggingFace. Updates reference files with timestamped findings and flags stale information. Invoke with /research comfyui or automatically at session start for staleness checks.
- Installs
- 409
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/mckruz/comfyui-expert --skill comfyui-research- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads comfyui-research automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
ComfyUI Research Skill
Keeps the VideoAgent knowledge base current by monitoring sources, extracting knowledge, and flagging stale information.
Triggers
- On demand: User invokes
/research comfyuior asks to check for updates - Session start: Quick staleness check (read
references/staleness-report.md) - Before workflow generation: Targeted check if the specific model/technique is >2 months old
Research Pipeline
1. Discovery
Search for new developments across three source types:
YouTube Channels (technique extraction):
| Channel | Focus | URL |
|---|---|---|
| Pixaroma | ComfyUI tutorials, GGUF, beginner-friendly | youtube.com/@pixaroma |
| Kijai | Advanced nodes, model implementations | youtube.com/@Kijai |
| Sebastian Kamph | ComfyUI workflows, automation | youtube.com/@sebastiankamph |
| Olivio Sarikas | AI art techniques, ComfyUI | youtube.com/@OlivioSarikas |
| Matt Wolfe | AI tool roundups | youtube.com/@maboroshi |
| Nerdy Rodent | Stable Diffusion deep dives | youtube.com/@NerdyRodent |
GitHub Repositories (node/model updates):
| Repository | What to Check |
|---|---|
| comfyanonymous/ComfyUI | Releases, breaking changes |
| Kosinkadink/ComfyUI-AnimateDiff-Evolved | New motion modules |
| cubiq/ComfyUI_IPAdapter_plus | Maintenance status, forks |
| ltdrdata/ComfyUI-Impact-Pack | FaceDetailer updates |
| Wan-AI/Wan2.1-Preview | New model versions |
| hzwer/Practical-RIFE | Interpolation updates |
| resemble-ai/chatterbox | Voice model updates |
| SWivid/F5-TTS | TTS updates |
HuggingFace (model releases):
- Trending models:
huggingface.co/models?sort=trending - Filter: diffusers, video, audio, text-to-image
- Watch for: New FLUX variants, Wan updates, identity models, voice models
2. Extraction
For each discovery, extract structured knowledge:
From YouTube videos:
Use youtube-video-analyst or youtube-chapter-clipper skills to:
- Get transcript
- Identify new models mentioned (name, source, requirements)
- Identify new techniques (workflow changes, parameter discoveries)
- Identify new nodes (package name, what it does)
- Note any benchmark results or comparisons
From GitHub releases:
- Check release notes for breaking changes
- Identify new features or supported models
- Note version requirements
- Check if deprecated features affect our workflows
From HuggingFace:
- Model card: architecture, training data, requirements
- VRAM requirements and quantization options
- ComfyUI compatibility (is there a node?)
- Quality comparison vs current recommendations
3. Integration
Update reference files with timestamped entries:
<!-- Updated: 2026-02-06 | Source: Pixaroma Ep 45 -->
### New Model: XYZ
- Download: {url}
- VRAM: {requirement}
- Notes: {key findings}
Which file to update:
| Finding Type | Update File |
|---|---|
| New model | references/models.md |
| New workflow technique | references/workflows.md |
| LoRA training discovery | references/lora-training.md |
| Voice tool update | references/voice-synthesis.md |
| New prompt technique | references/prompt-templates.md |
| Bug workaround | references/troubleshooting.md |
| Model landscape shift | foundation/model-landscape.md |
4. Staleness Audit
Scan all reference files for <!-- Updated: --> timestamps:
Thresholds:
| Category | Max Age | Action |
|---|---|---|
| Models | 3 months | Flag: "Model recommendations may be outdated" |
| Nodes | 2 months | Flag: "Custom node versions may have updates" |
| Techniques | 6 months | Flag: "Techniques may have been superseded" |
| Voice tools | 3 months | Flag: "Voice synthesis landscape may have changed" |
Generate report: Update references/staleness-report.md with current status.
Research State
Maintained in skills/comfyui-research/state/:
state/
last-research-run.json # When, what was checked, what was found
watch-list.yaml # Sources to monitor (see references/)
last-research-run.json
{
"last_run": "2026-02-06T12:00:00Z",
"sources_checked": 15,
"findings": 3,
"updates_made": [
{"file": "models.md", "entry": "Added ModelX", "source": "HuggingFace"},
{"file": "workflows.md", "entry": "Updated Wan settings", "source": "Pixaroma Ep 50"}
],
"stale_entries": 0
}
Quick Staleness Check (Session Start)
Fast check without full research:
- Read
references/staleness-report.md - If
last_runis >2 weeks ago:- Notify: "Research data is {N} days old. Run
/research comfyuifor updates."
- Notify: "Research data is {N} days old. Run
- If any entries are beyond their threshold:
- Notify: "Stale items found: {list}. These may have newer alternatives."
Full Research Run
When user triggers /research comfyui:
- Check all YouTube channels for recent uploads (last 30 days)
- Check all GitHub repos for new releases
- Check HuggingFace trending for relevant models
- Extract findings using youtube-video-analyst
- Update reference files with timestamped entries
- Run staleness audit on all references
- Update staleness report
- Summarize findings for user
Targeted Research
When asked about a specific topic:
- Search YouTube for recent videos on the topic
- Search HuggingFace for related models
- Check GitHub for related node packages
- Synthesize findings
- Update relevant reference files if significant discoveries
Integration with Other Skills
| Skill | How Research Helps |
|---|---|
comfyui-workflow-builder | Ensures recommended models/nodes are current |
comfyui-character-gen | Updates identity method recommendations |
comfyui-video-pipeline | Flags new video models (Wan updates, new engines) |
comfyui-voice-pipeline | Tracks voice synthesis tool releases |
comfyui-troubleshooter | Adds community-discovered workarounds |
Reference
references/staleness-report.md- Current freshness statusreferences/evolution.md- Update protocol and changelogskills/comfyui-research/references/watch-list.yaml- Monitored sources
FAQ
What does the comfyui-research skill do?
Research latest ComfyUI models, techniques, and community discoveries. Monitors YouTube channels, GitHub repos, and HuggingFace. Updates reference files with timestamped findings and flags stale information. Invoke with /research comfyui or automatically at session start for staleness checks.
How do I install comfyui-research?
Run npx skills add https://github.com/mckruz/comfyui-expert --skill comfyui-research in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/comfyui-research/ (personal) or .claude/skills/comfyui-research/ (project).
Which AI agents can use comfyui-research?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is comfyui-research safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains comfyui-research?
It is published by mckruz in mckruz/comfyui-expert. It has 409 recorded installs.
More from mckruz/comfyui-expert
comfyui-workflow-builder
mckruz/comfyui-expert
Generate, build, create, or design ComfyUI workflow JSON from natural language descriptions. Produces valid node graphs with correct classtypes, connections, output indices, and model-appropriate settings. Handles txt2img, img2img, inpainting, ControlNet, LoRA stacking, upscaling, and face detailing pipelines. Does NOT cover ComfyUI installation, custom node development, Python scripting, model training, hardware advice, or architectural explanations.
comfyui-api
mckruz/comfyui-expert
Connect to a running ComfyUI instance, queue workflows, monitor execution, and retrieve results. Supports both online (REST API) and offline (JSON export) modes. Use when executing ComfyUI workflows or checking server status.
comfyui-prompt-engineer
mckruz/comfyui-expert
Craft model-specific prompts optimized for the target checkpoint and identity method. Handles FLUX, SDXL, SD1.5, and Wan video models with proper syntax, quality tags, and negative prompts. Use when generating or refining prompts for ComfyUI workflows.
comfyui-video-pipeline
mckruz/comfyui-expert
Generate videos using ComfyUI with Wan 2.2, FramePack, or AnimateDiff. Handles image-to-video, text-to-video, talking heads, and motion-controlled animation. Use when creating any video content from character images or text descriptions.
comfyui-troubleshooter
mckruz/comfyui-expert
Diagnose ComfyUI errors, workflow failures, and quality issues. Suggests fixes based on error patterns, missing dependencies, and community-known workarounds. Use when ComfyUI workflows fail or produce unexpected results.
comfyui-character-gen
mckruz/comfyui-expert
Build identity-preserving character generation workflows and pipelines in ComfyUI. Selects the optimal identity method (InfiniteYou, FLUX Kontext, PuLID, InstantID, IP-Adapter) based on use case requirements. Handles face preservation, likeness transfer, cross-domain conversion (3D to photo), multi-reference consistency, iterative character editing, and character variation generation. Triggers on requests to generate consistent characters, preserve identity across images, create face-swapping workflows, or convert 3D renders to photorealistic portraits. Does NOT cover general image generation without identity preservation, model training/LoRA fine-tuning, animation, technical explanations, or workflow debugging.
Popular productivity & automation skills
agent-browser
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
lark-doc
open.feishu.cn
飞书云文档（Docx / Wiki）内容操作：读取、创建、编辑文档，插入或下载图片附件，以及操作思维笔记。用户提供文档 URL/token（包括 doubao.com 的 /docx/、/wiki/）时使用；按 URL 路径/token 而非域名路由；/page/ 是妙搭应用，非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive；随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。
lark-base
open.feishu.cn
飞书多维表格（Base）操作：建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式（BaseApp/AppMode 页面与组件）、Workspace 目录、workflow、角色权限、模板中心（多维表格模板分类/列表/搜索）；遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps；文件导入/导出转 lark-drive，认证/授权转 lark-shared。
lark-drive
open.feishu.cn
飞书云空间（云盘/云存储）：管理 Drive 文件和文件夹，包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签（secure labels）和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题，或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用；doubao.com 云空间 URL/token 也按资源路径和 token 路由，不回退 WebFetch。不负责：文档内容编辑（走 lark-doc）、表格/Base 表内数据操作（走 lark-sheets/lark-base）、知识空间节点/成员管理（走 lark-wiki）、原生 Markdown 文件读写/patch/diff（走 lark-markdown）。
lark-shared
open.feishu.cn
Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.
lark-im
open.feishu.cn
飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。