X Content Workflow

Checked post/thread and optional generated image with alt text

v0.2.0

View example draft · How to use

Example output

Keep the source beside the claim

An original English research-workflow post with a SandBase-generated illustration.

Three blue and coral paper cards connected to notes on an open notebook.

Post

Keep the source beside the claim. Save the link, capture time and exact passage before turning AI research into a post. If a number loses its definition or date on the way to the draft, pause and restore that context.

Actual generated image and a draft checked for weighted X length. The illustration represents a workflow; it is not evidence of a real event.

What you get

  • Checked post/thread and optional generated image with alt text

Good fit

  • Product updates grounded in confirmed facts
  • Reference-account research followed by usable copy

Not for

  • Automatic publishing, account management or guaranteed audience outcomes.

How to use

Supplied material works without API calls. Live data uses your SandBase connection and current API pricing; eligible calls share the daily free quota. Image generation is optional and billed separately after model inspection. Weighted-length checks need Node.js 20+ and the bundled npm dependencies (npm ci).

Download and unpack the complete Skill folder, keep its references, and use it with a local Agent that supports Skills.

Download Skill v0.2.0

Ask your Agent

Use x-content-workflow. Start from the account, link, topic or material I provide, and use SandBase where needed to complete the requested task. Deliver: Checked post/thread and optional generated image with alt text

  1. Research comparable posts through SandBase

  2. Apply the task rules to observed evidence

  3. Check and deliver the native result with limits

FAQ

How do I use this Skill?

Download and unpack the whole Skill folder, including references, into your Agent’s supported Skill directory. You can also ask the Agent to read its SKILL.md and follow the instructions. Run it locally with your own material.

Does a strong reference post predict my results?

No. Comparisons describe the retrieved sample. They do not establish causation or predict engagement for a new post.