# AI use cases for Yominpost (mrlong0129/yominpost) Repo: [mrlong0129/yominpost](https://github.com/mrlong0129/yominpost) | Use cases: 4 | Page: https://dedupedai.com/use-cases/mrlong0129-yominpost/ YominPost is a self-hosted AI social media studio that turns one piece of material into platform-native posts, checks them for platform risk, and schedules or publishes them through OAuth connectors. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Turn one idea into posts for several platforms from the terminal: https://dedupedai.com/use-cases/mrlong0129-yominpost/one-idea-to-posts-from-terminal/ - Let a coding agent draft and risk-check posts through MCP: https://dedupedai.com/use-cases/mrlong0129-yominpost/agent-drafts-and-checks-posts-via-mcp/ - Screen existing drafts for account-risk signals before posting: https://dedupedai.com/use-cases/mrlong0129-yominpost/pre-publish-risk-check-on-existing-drafts/ - Schedule and publish approved posts to your own social accounts: https://dedupedai.com/use-cases/mrlong0129-yominpost/self-hosted-studio-publishes-approved-posts/ ## How to turn one idea into posts for several platforms from the terminal with Yominpost Repo: [mrlong0129/yominpost](https://github.com/mrlong0129/yominpost) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README One source text becomes a draft for each chosen platform in a single command. **Who it is for:** A creator or developer with a long-form idea who needs versions for X, LinkedIn and TikTok today and has a terminal open. **The problem:** Rewriting the same idea for each platform by hand takes time, and each platform wants a different format. **The outcome:** Platform-specific drafts for each selected channel, with a format chosen per platform, ready for review in the studio. ### Steps 1. Install uv with `curl -LsSf https://astral.sh/uv/install.sh | sh` if you do not have it. 2. Run `uvx --from git+https://github.com/mrlong0129/yominpost yominpost run --brand "Acme" --source "Acme turns one long-form idea into ten platform-native posts." --platform x --platform linkedin --platform tiktok --topics 3`. (inferred, check the README) 3. Replace the Acme brand and source text with your own material and keep the platform flags you need. 4. Start the web studio with `uvx --from git+https://github.com/mrlong0129/yominpost yominpost --open` to review the drafts on the canvas. 5. Edit or refine each draft in the studio before scheduling or publishing it. ### Prompt to paste into your agent ```text Use the yominpost repo at git+https://github.com/mrlong0129/yominpost to run the yominpost run command with for platforms x, linkedin and tiktok. Expected output: one draft per platform with a chosen format. Verify that each draft is platform-specific and that no post was published. ``` ### Caveat The default template driver is an offline scaffold, so drafts are a starting point until you switch to claude_code, codex or anthropic. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/mrlong0129-yominpost/one-idea-to-posts-from-terminal/ ## How to let a coding agent draft and risk-check posts through MCP with Yominpost Repo: [mrlong0129/yominpost](https://github.com/mrlong0129/yominpost) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README Claude Code or Cursor generates and checks posts, then saves drafts for a human to approve. **Who it is for:** A developer who already works in Claude Code or Cursor and wants the agent to write social copy for a launch without leaving the editor. **The problem:** Writing and checking launch posts is a separate chore from coding, and agents have no safe way to hand off drafts. **The outcome:** Drafts saved in the YominPost studio, each with a risk check result, waiting for a human to press Publish. ### Steps 1. Register the MCP server in Claude Code with `claude mcp add yominpost -- uvx --from git+https://github.com/mrlong0129/yominpost yominpost-mcp`. 2. For Cursor, add the Yominpost entry to ~/.cursor/mcp.json or .cursor/mcp.json as shown in the README. 3. Install the agent skill by copying skill/SKILL.md into ~/.claude/skills/yominpost/ so the agent knows the workflow. (inferred, check the README) 4. Ask the agent to call generate_posts for your material, then check_post on each draft. 5. Ask the agent to call save_draft, then open the studio with `uvx --from git+https://github.com/mrlong0129/yominpost yominpost --open` to review and publish. ### Prompt to paste into your agent ```text Using the yominpost MCP server from github.com/mrlong0129/yominpost, call generate_posts for , run check_post on each draft, and save the passing drafts with save_draft. Expected output: saved drafts with risk check results. Verify that no publish action was taken, since the MCP server has no publish tool. ``` ### Caveat The MCP server deliberately has no publish tool, so every draft still needs a person to approve it in the UI. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/mrlong0129-yominpost/agent-drafts-and-checks-posts-via-mcp/ ## How to screen existing drafts for account-risk signals before posting with Yominpost Repo: [mrlong0129/yominpost](https://github.com/mrlong0129/yominpost) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README Run the pre-publish risk gate on drafts you already wrote to catch leaks, bait and duplicates. **Who it is for:** A social media manager with drafts written elsewhere who wants to avoid signals that get AI-assisted accounts restricted. **The problem:** Drafts can contain leaked prompt text, engagement bait, hashtag stuffing or duplicates that put the account at risk. **The outcome:** A list of risk findings per draft, so you can fix or drop risky posts before they are scheduled. ### Steps 1. Install and start the studio with `uvx --from git+https://github.com/mrlong0129/yominpost yominpost --open`. 2. Paste or save each existing draft into the studio so it appears in the post list. 3. Run the risk gate on each draft; it checks prompt-leak and engagement-bait lint, hashtag and link limits, duplicates and cadence caps. 4. Edit or delete any draft flagged by the gate. 5. Schedule only the drafts that pass. ### Prompt to paste into your agent ```text Using the yominpost repo at github.com/mrlong0129/yominpost, run check_post on each draft in and report the findings. Expected output: one risk result per draft. Verify that the findings name the rule that fired, such as hashtag limits or duplicate detection. ``` ### Caveat The gate is a set of rules that reduce risk and cannot guarantee that a platform will not restrict an account. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/mrlong0129-yominpost/pre-publish-risk-check-on-existing-drafts/ ## How to schedule and publish approved posts to your own social accounts with Yominpost Repo: [mrlong0129/yominpost](https://github.com/mrlong0129/yominpost) | Difficulty: Advanced | Time: 60 minutes | Basis: From the README Connect your accounts, approve drafts in the studio, and let the scheduler publish them on time. **Who it is for:** A small team or solo operator who wants a self-hosted alternative to hosted schedulers and keeps tokens on their own machine. **The problem:** Hosted schedulers hold your tokens and drafts in their cloud, and most AI writers stop at a caption. **The outcome:** Approved posts go out on schedule to connected platforms, with encrypted tokens stored locally. ### Steps 1. Start the studio with `uvx --from git+https://github.com/mrlong0129/yominpost yominpost --open` on your own machine. 2. Add your OAuth client IDs as environment variables such as X_CLIENT_ID or LINKEDIN_CLIENT_ID, or paste them on the Settings page. 3. Connect each platform with one-click Connect and confirm its health status. 4. Approve each draft in the calendar and place it in the scheduled queue. 5. Back up data/.secret.key together with the SQLite database in ~/.yominpost/ so stored tokens stay readable. ### Prompt to paste into your agent ```text Using the yominpost repo at github.com/mrlong0129/yominpost, start the studio, connect with its OAuth client, and schedule the approved draft for a time you set. Expected output: the post in the scheduled queue with a status. Verify that a person approved the post in the UI before it was published. ``` ### Caveat TikTok, Xiaohongshu, Threads and Pinterest use simulated connectors, so only the listed real platforms publish. Risk, credentials: OAuth tokens for your real accounts are stored in ~/.yominpost/ and must be backed up together with data/.secret.key, so keep that folder private. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/mrlong0129-yominpost/self-hosted-studio-publishes-approved-posts/