Tinder Play

Organization

pockebot

tinder-play

Automate Tinder conversations and swiping. Use when the user asks to use Tinder, reply to matches, swipe, or manage their dating app interactions on phone.

Overview

Publisher	pockebot
Repository	`openpocket`
Skill name	`tinder-play`
Stars	848
Forks	6
Bundled files	Instructions only
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.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by pockebot on GitHub. Read the source before you install it.

Installation

Install the Tinder Play 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/pockebot/openpocket/tree/main/skills/tinder-play
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/pockebot/openpocket.git /tmp/openpocket
mkdir -p .claude/skills
cp -r /tmp/openpocket/skills/tinder-play .claude/skills/tinder-play

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

Use it in TypingMind

Enable Tinder Play 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 Tinder Play 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 Tinder Play 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.

Tinder Play

Use this skill to automate Tinder interactions — swiping, messaging, and replying to matches — without asking the user for permission at each step. The goal is full automation.

Core Principle

Act autonomously. Do not ask the user what to say or whether to swipe. Make decisions yourself — you are the autopilot. The user will intervene only if they want to override.

Swiping

To see detailed user info (bio, interests, basics), tap the up arrow button on the profile card or swipe up.
Swipe right (like) on profiles that look genuine and have bios.
Swipe left (pass) on empty profiles, obvious spam, or profiles with no photos.
If a Super Like prompt or boost popup appears, dismiss it unless the user previously asked to use them.
Do not spend time analyzing profiles deeply — keep a steady pace.

Conversations

What "Help Me Chat" Means

When the user asks to "help chat on Tinder" or similar, handle both:

Your turns: conversations where the other person sent the last message — reply to these.
Never-replied matches: new matches where no one has messaged yet — send an opener to these.

Work through both categories before finishing.

Finding Your Turn

Open the matches/messages tab.
Identify conversations where the other person sent the last message — these are your turns to reply.
Also identify matches with no messages at all — these need an opening message.
Prioritize recent messages (within the last few hours) over older ones.
Skip conversations where you (the user) already sent the last message — no double-texting.

Composing Replies

Read the conversation history on screen to understand context and tone.
Reply in the same language the conversation is in. If the other person writes in Spanish, reply in Spanish. Match their language.
Reply with natural, friendly, and engaging messages. Keep it light and conversational.
Match the energy of the other person — if they're playful, be playful; if they're direct, be direct.
Ask follow-up questions to keep the conversation going.
Keep messages short — 1–3 sentences max. No essays.
Avoid generic openers like "Hey" or "What's up" when replying mid-conversation.
Do not use pickup lines or anything cringe. Be genuine.
Reference something specific from their message or profile when possible.

Opening New Matches

For new matches with no messages yet, open with something specific to their profile (bio, photos, interests).
If the profile has nothing to work with, a simple friendly opener is fine.

Navigation

Swipe screen: main screen — swipe right to like, left to pass.
Matches tab: tap the chat bubble icon at the bottom to see matches and messages.
Conversation view: tap a match to open the chat. Message input is at the bottom.
Back: use the back arrow or Android back to return to the matches list.
Profile view: tap the profile photo in a conversation to see their full profile for context.

Batch Workflow

When the user says "handle my Tinder" or similar:

Open the messages tab.
Scan for conversations where it's your turn to reply.
Reply to each one — read context, compose, type, send.
After replying to all pending conversations, switch to the swipe screen.
Swipe through a batch of profiles (10–20).
Return to messages to check for any new replies that came in.
Call finish with a summary: number of replies sent, number of swipes, any new matches.

Sending a Message

Tap the text input field at the bottom of the conversation.
Type the message using type_text.
Tap the send button (arrow icon) to send.
Use batch action for the tap-input → type → send flow.

Common Pitfalls

Do not double-text. If the user's message is the last one, move on.
Do not ask the user what to say. Compose and send autonomously.
Popups and promotions: Tinder frequently shows upgrade prompts, boost offers, and super-like nudges. Dismiss all of these by tapping X or "No thanks".
Match animations: when a new match appears, dismiss the celebration screen to continue.
GIF/emoji keyboards: if the keyboard switches to GIF or emoji mode, tap the text/ABC key to switch back before typing.
Read the room: if someone seems uninterested or gives one-word replies, don't force the conversation. Move on.

Failure Handling

If a message fails to send, retry once. If it fails again, skip and move to the next conversation.
If Tinder asks to verify or shows a captcha, call request_human_auth with capability=oauth.
If the app crashes or freezes, relaunch it and continue from the messages tab.

Frequently asked questions

What does the Tinder Play AI skill do?

Automate Tinder conversations and swiping. Use when the user asks to use Tinder, reply to matches, swipe, or manage their dating app interactions on phone.

Why use Tinder Play on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/pockebot/openpocket/tree/main/skills/tinder-play. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Tinder Play?

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 Tinder Play?

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

Is the Tinder Play AI skill free?

Yes. It is published on GitHub by pockebot 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

Skill Host Compat

affaan-m

CommunityPopular

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…

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…

Content Engine

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…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Tinder Play

Core Principle

Swiping

Conversations

What "Help Me Chat" Means

Finding Your Turn

Composing Replies

Opening New Matches

Navigation

Batch Workflow

Sending a Message

Common Pitfalls

Failure Handling

Frequently asked questions

Related AI Skills

Set up your own AI workspace now