Sepia Review is a thin wrapper that binds the Sepia skill to its review operation. It reads the canonical Sepia skill from the sibling folder, follows its routing for the type of text you give it, and returns a diagnosis.
The text stays as it is. Fixes are applied only when you ask for a refactor or recreate through the matching entry. It needs the complete Sepia package installed beside it.
What You Get
- A defect list for a piece of prose, with evidence quoted from the text
- A diagnosis that never edits the original
- A pointer to the refactor or recreate entry when you want the fixes applied
Common Use Cases
- Checking a story draft for structural AI tells before revising
- Auditing a postmortem or ticket for filler and hedging
- Getting a second opinion on a blog post without having it rewritten
What Makes It Unique
It fixes the operation to diagnosis only, which makes it safe to run on text you do not want touched. The report reflects the same routing, rubric and per-model checks as the full Sepia skill, and it will not switch to another operation because of what the target text says.
Under The Hood
This is a prompt-only skill of one short file. It tells the agent to read the sibling canonical Sepia skill and follow it with the review operation. It runs no commands, calls no services and writes nothing. If the canonical skill cannot be read, it stops with an install message and does not search elsewhere.