Ruflo

Community

makabakaxy

ruflo

Manage multi-agent swarms, memory, tasks, hooks, workflows, and browser automation via CLI. Use when spawning agents, storing/searching memory, orchestrating workflows, coordinating hive-minds, or automating browser interactions.

Overview

Publisher	makabakaxy
Repository	`mcp2cli`
Skill name	`ruflo`
Stars	66
Forks	5
Bundled files	10
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
10 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by makabakaxy on GitHub. Read the source before you install it.

Installation

Install the Ruflo AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/makabakaxy/mcp2cli/tree/main/presets/ruflo/3.0.0/skills
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/makabakaxy/mcp2cli.git /tmp/mcp2cli
mkdir -p .claude/skills
cp -r /tmp/mcp2cli/presets/ruflo/3.0.0/skills .claude/skills/ruflo

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ruflo in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ruflo on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ruflo is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

ruflo (via mcp2cli)

Multi-agent orchestration, vector memory, task management, and browser automation.

Shortcuts

No shortcuts configured. Use full form: mcp2cli ruflo <group> <cmd>

Commands

Agent

Command	Description	Example	Ref
`mcp2cli ruflo agent spawn`	Spawn a new agent	`mcp2cli ruflo agent spawn --agent-type worker --model sonnet`	ref
`mcp2cli ruflo agent list`	List all agents	`mcp2cli ruflo agent list`	ref
`mcp2cli ruflo agent status`	Get agent status	`mcp2cli ruflo agent status --agent-id agent-1`	ref
`mcp2cli ruflo agent update`	Update agent config		ref
`mcp2cli ruflo agent terminate`	Terminate an agent	`mcp2cli ruflo agent terminate --agent-id agent-1`	ref
`mcp2cli ruflo agent health`	Check agent health		ref

Memory

Command	Description	Example	Ref
`mcp2cli ruflo memory store`	Store value with vector embedding	`mcp2cli ruflo memory store --key mykey --value "data"`	ref
`mcp2cli ruflo memory get`	Retrieve value by key	`mcp2cli ruflo memory get --key mykey`	ref
`mcp2cli ruflo memory search`	Semantic vector search	`mcp2cli ruflo memory search --query "auth patterns"`	ref
`mcp2cli ruflo memory list`	List memory entries		ref
`mcp2cli ruflo memory delete`	Delete memory entry	`mcp2cli ruflo memory delete --key mykey`	ref
`mcp2cli ruflo memory stats`	Get memory statistics		ref

Task

Command	Description	Example	Ref
`mcp2cli ruflo task create`	Create a new task	`mcp2cli ruflo task create --type feature --description "Add login"`	ref
`mcp2cli ruflo task list`	List all tasks	`mcp2cli ruflo task list --status pending`	ref
`mcp2cli ruflo task status`	Get task status	`mcp2cli ruflo task status --task-id t1`	ref
`mcp2cli ruflo task update`	Update task progress		ref
`mcp2cli ruflo task complete`	Mark task complete	`mcp2cli ruflo task complete --task-id t1`	ref
`mcp2cli ruflo task assign`	Assign task to agents		ref
`mcp2cli ruflo task cancel`	Cancel a task		ref

Hooks

Command	Description	Example	Ref
`mcp2cli ruflo hooks pre-task`	Record task start, get agent suggestions	`mcp2cli ruflo hooks pre-task --task-id t1 --description "Fix bug"`	ref
`mcp2cli ruflo hooks post-task`	Record task completion	`mcp2cli ruflo hooks post-task --task-id t1 --success true`	ref
`mcp2cli ruflo hooks route`	Route task to optimal agent	`mcp2cli ruflo hooks route --task "implement OAuth"`	ref
`mcp2cli ruflo hooks pre-edit`	Get context before editing file	`mcp2cli ruflo hooks pre-edit --file-path src/auth.ts`	ref
`mcp2cli ruflo hooks init`	Initialize hooks in project	`mcp2cli ruflo hooks init --template standard`	ref
`mcp2cli ruflo hooks metrics`	View learning metrics		ref

Hive-Mind

Command	Description	Example	Ref
`mcp2cli ruflo hive-mind spawn`	Spawn workers and join hive	`mcp2cli ruflo hive-mind spawn --count 3 --role worker`	ref
`mcp2cli ruflo hive-mind init`	Initialize hive-mind collective	`mcp2cli ruflo hive-mind init --topology mesh`	ref
`mcp2cli ruflo hive-mind status`	Get hive-mind status		ref
`mcp2cli ruflo hive-mind consensus`	Propose or vote on consensus	`mcp2cli ruflo hive-mind consensus --action propose --type config`	ref
`mcp2cli ruflo hive-mind broadcast`	Broadcast to all workers	`mcp2cli ruflo hive-mind broadcast --message "Start phase 2"`	ref

Workflow

Command	Description	Example	Ref
`mcp2cli ruflo workflow run`	Run workflow from template	`mcp2cli ruflo workflow run --template ci-pipeline`	ref
`mcp2cli ruflo workflow create`	Create a new workflow	`mcp2cli ruflo workflow create --name my-flow`	ref
`mcp2cli ruflo workflow list`	List all workflows		ref
`mcp2cli ruflo workflow status`	Get workflow status	`mcp2cli ruflo workflow status --workflow-id wf1`	ref
`mcp2cli ruflo workflow execute`	Execute a workflow	`mcp2cli ruflo workflow execute --workflow-id wf1`	ref

Claims

Command	Description	Example	Ref
`mcp2cli ruflo claims claim`	Claim an issue for work	`mcp2cli ruflo claims claim --issue-id 123 --claimant "agent:coder-1:coder"`	ref
`mcp2cli ruflo claims list`	List all claims		ref
`mcp2cli ruflo claims release`	Release a claim	`mcp2cli ruflo claims release --issue-id 123 --claimant "agent:coder-1:coder"`	ref
`mcp2cli ruflo claims handoff`	Handoff issue to another agent		ref
`mcp2cli ruflo claims load`	Get agent load info		ref

Browser

Command	Description	Example	Ref
`mcp2cli ruflo browser open`	Navigate to URL	`mcp2cli ruflo browser open --url https://example.com`	ref
`mcp2cli ruflo browser snapshot`	Get accessibility tree		ref
`mcp2cli ruflo browser screenshot`	Capture screenshot		ref
`mcp2cli ruflo browser click`	Click an element	`mcp2cli ruflo browser click --ref elem-1`	ref
`mcp2cli ruflo browser fill`	Fill an input field	`mcp2cli ruflo browser fill --ref input-1 --value "text"`	ref

Swarm

Command	Description	Example	Ref
`mcp2cli ruflo swarm init`	Initialize a swarm	`mcp2cli ruflo swarm init --topology hierarchical`	ref
`mcp2cli ruflo swarm status`	Get swarm status		ref
`mcp2cli ruflo swarm health`	Check swarm health		ref
`mcp2cli ruflo swarm shutdown`	Shutdown a swarm		ref

Discover Parameters

Append --help to any command for full parameter list:


mcp2cli ruflo agent spawn --help

Note: Use Ref links above to view detailed parameter reference and more examples.

User Notes

MUST READ users/skill.md for custom workflows and tips. Config: MCP server settings live in ~/.agents/mcp2cli/servers.yaml - edit there to take effect.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Ruflo AI skill do?

Why use Ruflo on TypingMind?

Because you install it once and use it with any model. Ruflo is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ruflo in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/makabakaxy/mcp2cli/tree/main/presets/ruflo/3.0.0/skills. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Ruflo?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ruflo?

As many as you like. As long as a model supports skills, you can use Ruflo with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ruflo AI skill free?

Yes. It is published on GitHub by makabakaxy under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Notcrawl

openclaw

OrganizationPopular

Notion archive: search, sync freshness, pages/databases, Markdown exports, SQL counts, and Notcrawl repo work.

Openclaw Test Heap Leaks

openclaw

OrganizationPopular

Investigate OpenClaw pnpm test memory growth, Vitest OOMs, RSS spikes, and heap snapshot deltas.

Prototype Openclaw Tui

openclaw

OrganizationPopular

Build throwaway, fixture-driven OpenClaw Clack or Pi TUI prototypes and compare multiple interactive variants side by side in tmux without running the full application or touching live state.

Slacrawl

Slack archive: search, sync freshness, threads/DMs, SQL counts, and Slacrawl repo work.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

ruflo (via mcp2cli)

Shortcuts

Commands

Agent

Memory

Task

Hooks

Hive-Mind

Workflow

Claims

Browser

Swarm

Discover Parameters

User Notes

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now