Yominpost

Community

mrlong0129

yominpost

Write, adapt and safety-check social media posts for X, LinkedIn, Instagram, TikTok, YouTube, Xiaohongshu, Telegram, Mastodon, Bluesky and more. Use when the user wants posts generated from material (an announcement, article, product page or notes), wants one idea adapted per platform, asks whether a post is safe to publish, or wants drafts queued for review. Uses the YominPost MCP tools or CLI when available; otherwise follows the same playbook by hand. Never publishes without the user.

Overview

Publisher	mrlong0129
Repository	`yominpost`
Skill name	`yominpost`
Stars	100
Forks	1
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 mrlong0129 on GitHub. Read the source before you install it.

Installation

Install the Yominpost 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/mrlong0129/yominpost/tree/main/skill
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/mrlong0129/yominpost.git /tmp/yominpost
mkdir -p .claude/skills
cp -r /tmp/yominpost/skill .claude/skills/yominpost

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

Use it in TypingMind

Enable Yominpost 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 Yominpost 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 Yominpost 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.

Social posts that fit each platform and don't get the account flagged

Goal: turn the user's material into one native post per platform, check each for platform-risk signals, and hand drafts to the user for approval. Publishing is always the user's call.

0. If YominPost is available, use it

MCP: generate_posts(brand, material, platforms, num_topics) → check_post(text, platform) on each candidate → save_draft(...) for the ones the user likes → tell them to review at http://127.0.0.1:8300.
CLI: yominpost run --brand "<brand>" --source "<material>" --platform x --platform linkedin --json.
Not installed but uv is available? Zero install/config: uvx --from git+https://github.com/mrlong0129/yominpost yominpost run ... --json. Start the studio with uvx --from git+https://github.com/mrlong0129/yominpost yominpost --open.
The default template driver is an offline scaffold. Polish its output yourself, or suggest YOMINPOST_PROVIDER=claude_code for model-written copy.

Everything below is the same playbook done by hand.

1. Pick the format per platform (decide before writing)

Platform	Default format	Notes
X	text ≤ 280 chars; thread for stories / lists	Hook in the first line; at most 1 link
LinkedIn	text, 600–1,300 chars	Short paragraphs, a concrete takeaway, 3–5 hashtags max
Instagram / Xiaohongshu	image post or carousel	Caption ≤ 2,200 (Xiaohongshu ≤ 1,000); visual carries the message
TikTok / YouTube Shorts	short video	Write a storyboard: hook line (≤ 3 s), 3–6 scenes, on-screen text, caption
Telegram / Discord / Mastodon / Bluesky	text	Community tone; Bluesky ≤ 300 chars, Mastodon ≤ 500

Explain your choice in one line ("story angle → thread").

2. Write each version natively

Hook, body, CTA, hashtags. Rewrite for the platform, don't truncate. Keep the user's facts; never invent numbers, customers or quotes. Match the material's language unless asked otherwise.

3. Self-critique once

Score clarity, hook strength, platform fit and compliance. If anything is weak, rewrite once and keep the better version.

4. Pre-publish risk check (do this for every post)

Block and fix if you see:

Prompt leak: instructions or scaffolding left in the text ("Write a post…", "Here is a post", "As an AI", "[Hook]", "请生成", "以下是").
Engagement bait: "Comment X and I'll DM you", "tag 3 friends", "like & share to win", "评论领取", "转发抽奖". Meta platforms penalise this hard.
Over length for the platform.

Warn if you see: more than ~5 hashtags (Instagram allows more, but stuffing is a spam signal), more than 1 link, the same link or near-identical text posted repeatedly, or a brand-new account posting several times a day.

5. Hand off, don't publish

Show the drafts with the format reason and risk-check result, then save them as drafts (YominPost save_draft) or give them to the user to post. Never claim something was published unless the user did it or explicitly asked you to and you did it with a real publishing tool.

Frequently asked questions

What does the Yominpost AI skill do?

Why use Yominpost on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mrlong0129/yominpost/tree/main/skill. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Yominpost?

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 Yominpost?

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

Is the Yominpost AI skill free?

Yes. It is published on GitHub by mrlong0129 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

Bmad Spec

bmad-code-org

OrganizationPopular

Condense any input — an idea, brief, PRD, transcript, or mixed notes — into a short spec: one kernel file plus supporting files that downstream skills build from. Also updates and validates existing…

Discord E2e

Test Discord with Convex-leased QA bots: check credentials without a Gateway, exercise owned messages, or prove OpenClaw replies, files, threads, reactions, streaming, and typing. Distinguish API and…

Openclaw Live Updater

openclaw

OrganizationPopular

Maintain the canonical live OpenClaw main checkout, macOS LaunchAgent-managed Gateway, local macOS app, exact-head main CI, and recurring full release validation. Use for fast-forward update…

Parallels Discord Roundtrip

openclaw

OrganizationPopular

Run macOS Parallels smoke with Discord send, host verification, host reply, and guest readback proof.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Social posts that fit each platform and don't get the account flagged

0. If YominPost is available, use it

1. Pick the format per platform (decide before writing)

2. Write each version natively

3. Self-critique once

4. Pre-publish risk check (do this for every post)

5. Hand off, don't publish

Frequently asked questions

Related AI Skills

Set up your own AI workspace now