DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to read long Pi answers faster with the ELI5 tab with Speak Like You Eat

Get a short ELI5 rewrite under any finished Pi answer and switch tabs to compare.

Who it is forA Pi user who gets long, dense answers and needs the conclusion and next steps quickly.

The problemLong assistant answers bury the conclusion, the actions, and the open decisions under detail.

The outcomeA plain-language ELI5 card sits below the unchanged original, starting with the conclusion and what you need to do.

What you need first

  • Pi (current release) or Oh My Pi (OMP) installed
  • A model available and authenticated in the host so SLYE can call it
  • A terminal to run the install command
  • Node 24+ only if you plan to develop or test the repo itself

Steps

  1. Run pi install npm:speak-like-you-eat to make SLYE available to all projects, or pi install -l npm:speak-like-you-eat for the current project only.
  2. Wait until Pi finishes an answer, then run /slye.
  3. Read the ELI5 tab, which is active by default on the new card.
  4. Press ctrl+\ in any mode, or click a tab in fullscreen mode, to switch to the Light tab.

Prompt for your agent

Using the SLYE repo (wtfzambo/speak-like-you-eat), install the package in Pi and run /slye on the latest completed assistant response in <target project>. Expected output: an ELI5 card under the original answer that starts with the conclusion. Verify that the original response text is unchanged.

Caveat. On Pi each rewrite makes two provider requests in parallel, so it costs about twice as much as one version.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for wtfzambo/speak-like-you-eat and "Read long Pi answers faster with the ELI5 tab"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer