TypingMindTypingMindThe best frontend for AI
Skill Flow logo

Skill Flow

Community
VintLin
skill-flow

Use when the user asks Codex to inspect, import, enable, disable, deploy, update, repair, migrate, or uninstall Skill Flow skill groups through the skill-flow CLI or bridge protocol.

Overview

PublisherVintLin
Repositoryskill-flow
Skill nameskill-flow
Stars
264
Forks
16
Bundled files
2
LicenseApache-2.0
Links
Skill sourceRepository
  • 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.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by VintLin on GitHub. Read the source before you install it.

Installation

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

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/VintLin/skill-flow/tree/main/skills/skill-flow
  4. 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.
2

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/VintLin/skill-flow.git /tmp/skill-flow
mkdir -p .claude/skills
cp -r /tmp/skill-flow/skills/skill-flow .claude/skills/skill-flow
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Skill Flow 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 Skill Flow 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 Skill Flow 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.

Skill Flow

Overview

Operate Skill Flow through its CLI without editing state files directly. Prefer the machine-readable bridge protocol for agent work; use the human CLI only for simple commands that already emit usable output.

Core Rules

  • Use skill-flow bridge --json for structured operations and parse the JSON response.
  • Never edit ~/.skillflow, target skill directories, manifests, locks, or source checkouts directly.
  • Inspect before mutating: run list, inspect, doctor, or preview-import-source first.
  • Default imports to OFF by using enabledTargets: [] unless the user explicitly asks to deploy immediately.
  • Treat skill enablement and deployment as draft state: use apply, not direct filesystem edits.
  • Explain impact before state-changing operations; require explicit confirmation for destructive operations.

Command Entry

Use installed CLI:

bash
skill-flow bridge --json --request '{"protocolVersion":"1.0","command":"list"}'

Inside this repository, use the workspace CLI:

bash
npm run -w skill-flow dev -- bridge --json --request '{"protocolVersion":"1.0","command":"list"}'

For payload details, read references/bridge-commands.md before crafting a bridge request.

Workflow

  1. Classify the task as read-only, normal mutation, or destructive.
  2. Read current state with list or a narrower inspect command.
  3. For imports, run preview or prepare first; build draft from returned skill selectors.
  4. For enable/disable/deploy, call apply with full selectedLeafIds and enabledTargets.
  5. For updates or repairs, run doctor before and after.
  6. Report ok, warnings, errors, changed source ids, and any blocked actions.

Safety Levels

LevelOperationsRule
Read-onlylist, doctor, inspect, inspect-enrichment, search-import-groups, scan-local-import-groups, preview-import-source, inspect-state-migrationExecute directly when useful.
Normal mutationbootstrap, commit-import-source, import-source, apply, update, toggle-pin, rename-source, collections, save-settingsSummarize impact; proceed if the user requested that exact change.
Destructive/high-riskuninstall, non-dry-run migrate-state, broad repairs such as repair-state --allRequire explicit confirmation after identifying exact ids and scope.

Common Tasks

User asksDo
"What groups do I have?"Bridge list.
"Search for a skill"Human CLI skill-flow find <query> --json, or bridge import search for remote groups.
"Import this repo, keep skills off"preview-import-source, then import-source or prepare-import-source + commit-import-source with enabledTargets: [].
"Turn these skills on for Codex"inspect, map names to leaf ids, then apply with enabledTargets: ["codex"].
"Disable a skill"inspect, remove its leaf id from selectedLeafIds, then apply with remaining ids.
"Why did deployment fail?"doctor, then inspect for the affected source.
"Remove this group"list/inspect, ask for confirmation, then uninstall.

Common Mistakes

  • Using interactive config or add when bridge JSON can do the same job.
  • Omitting protocolVersion: "1.0" from bridge requests.
  • Passing skill names to apply; it requires leaf ids such as source-id:skills/review.
  • Importing with non-empty enabledTargets when the user did not request deployment.
  • Running uninstall or migration based on display names instead of exact source ids.

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 Skill Flow AI skill do?

Use when the user asks Codex to inspect, import, enable, disable, deploy, update, repair, migrate, or uninstall Skill Flow skill groups through the skill-flow CLI or bridge protocol.

Why use Skill Flow on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/VintLin/skill-flow/tree/main/skills/skill-flow. 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 Skill Flow?

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 Skill Flow?

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

Is the Skill Flow AI skill free?

Yes. It is published on GitHub by VintLin under the Apache-2.0 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.

Related AI Skills

View all
affaan-m logo

Competitive Platform Analysis

affaan-m
CommunityPopular

Use when scoping a competitive landscape — identifying, categorising, and score-filtering a competitor set before any benchmarking begins. Decides who counts as a competitor, which tier they belong…

40.4K
270.2K
1 files
View
affaan-m logo

Content Engine

affaan-m
CommunityPopular

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content…

40.4K
270.2K
1 files
View
mattpocock logo

Domain Modeling

mattpocock
CommunityPopular

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.

22.3K
264.4K
3 files
View
mattpocock logo

Writing Fragments

mattpocock
CommunityPopular

Writing, explore: mine raw fragments, no structure yet.

22.3K
264.4K
1 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇