Aikito

Community

lsaint

aikito

Operate Aikito workspaces and resources, including reading inbox notes, managing memory, skills, projects, MCP servers, subagents, and synchronization.

Overview

Publisher	lsaint
Repository	`aikito`
Skill name	`aikito`
Stars	129
Forks	0
Bundled files	3
License	MIT
Links	Skill source Repository Homepage

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.
3 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by lsaint on GitHub. Read the source before you install it.

Installation

Install the Aikito 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/lsaint/aikito/tree/main/src/aikito/templates/skills/aikito
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/lsaint/aikito.git /tmp/aikito
mkdir -p .claude/skills
cp -r /tmp/aikito/src/aikito/templates/skills/aikito .claude/skills/aikito

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

Use it in TypingMind

Enable Aikito 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 Aikito 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 Aikito 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.

Aikito

Purpose

Use Aikito as the canonical, Git-managed source for Agent resources shared across tools, projects, and machines. Existing Agent setups normally enter the workspace through adoption; newly created resources start in the workspace.

Core Model

Keep the CLI installation separate from the canonical user workspace (<workspace>, normally ~/aikito). When developing Aikito itself, keep its source checkout separate from the workspace too:

text
<workspace>/
├── layout.toml + skills.toml
├── agents/*.toml
├── subagents/*.md
├── global/AGENTS.md
├── skills/ + subagents/ + mcps/
├── memory/
└── projects/<name>/

Agent configuration directories and project .agents/ directories are runtime targets, not independent sources. Modify canonical resources first and then synchronize them. Never treat generated Agent-native instructions, skills, subagents, or MCP entries as sources.

The bundled aikito and durable-memory skills are system-managed snapshots, not user-customizable canonical resources. Aikito refreshes them from the installed package during workspace initialization and global synchronization, backing up divergent contents first. Put lasting custom behavior in global or project instructions, or in a separately named skill.

Resolve <workspace> with aikito path workspace before editing canonical files directly. AIKITO_DIR temporarily overrides the persisted workspace. Use the installed aikito command and treat aikito <command> --help as the authority for the installed version's options.

Choose a Workflow

Read references/installation.md when the CLI is not installed or the user asks to install or upgrade Aikito.

Bring an existing local Agent setup under management:

bash
aikito init workspace ~/aikito
aikito adopt
aikito sync
aikito status

Skip adopt when there are no supported external resources. On another machine, clone or download the existing workspace, bind it with aikito init workspace <path>, and run aikito sync.

New resources follow add → edit → show → sync → status / diff / doctor. Existing resources follow adopt → show → sync → status. Bare aikito sync orchestrates the entire workspace.

Core Rules

Inspect relevant canonical files and current status before changing anything; run aikito status or the narrowest resource-specific check afterward.
Use --dry-run when the user requests a preview. Adoption and synchronization already preflight their complete plans before writing by default.
Never silently replace unmanaged targets, drifted copies, or conflicting instructions. Do not use --force or --prune merely to make status green.
Preserve unrelated changes in both the workspace and runtime targets.
Keep credentials out of the workspace and Git. Canonical MCP definitions should reference environment variables; never print or persist their values.
Before publishing a workspace repository, review memory and configuration for private data. A local Git repository is not automatically safe to publish.

Resource Routing

Use aikito <command> --help for exact arguments.

Global instructions and skills: aikito add skill (supports --from <path> to import, --from <path> --force to refresh an imported snapshot, and --project <A,B> / --sync to distribute), aikito rm skill (supports unregistering via --project <A,B> and global deletion via --force), aikito show skill, and aikito sync global.
Projects: aikito init project, aikito show project, aikito sync project, aikito status, and aikito diff.
MCP servers: aikito add mcp (supports --from <source>, --sync, and --force), aikito rm mcp (supports --sync), aikito show mcp, aikito sync mcp, and aikito auth mcp.
Subagents: aikito add subagent, aikito rm subagent (supports --sync), aikito show subagent, and aikito sync subagents.
Memory: aikito show|edit|rename|rm memory; use the durable-memory skill to decide scope, content, and versioning.
Inbox notes: use aikito show inbox <name>.md to read a named note, or aikito show inbox to list notes. Use aikito edit|rm inbox for changes.

Read references/projects.md when registering or synchronizing projects, choosing sync_mode, handling multi-machine paths, or using the public project API.

Read references/adoption.md when importing an existing Agent setup or resolving adoption diagnostics.

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 Aikito AI skill do?

Operate Aikito workspaces and resources, including reading inbox notes, managing memory, skills, projects, MCP servers, subagents, and synchronization.

Why use Aikito on TypingMind?

Because you install it once and use it with any model. Aikito 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 Aikito in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/lsaint/aikito/tree/main/src/aikito/templates/skills/aikito. 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 Aikito?

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 Aikito?

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

Is the Aikito AI skill free?

Yes. It is published on GitHub by lsaint 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

Gemini

openclaw

OrganizationPopular

Gemini CLI one-shot prompts, summaries, generation, skills, hooks, MCP, or Gemma routing.

Writing Skills

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Skill Host Compat

Lint ECC skills for Codex/Cursor-safe frontmatter and Claude-only substitutions before a skill PR.

Brand Voice

Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that profile across content, outreach, and social workflows. Use when the user wants…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Aikito

Purpose

Core Model

Choose a Workflow

Core Rules

Resource Routing

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now