Skip to content
SkillModel-led205 tokens in use

Sepia Review

A fixed entry to the Sepia writing skill that runs only the review operation, reporting AI tells with quoted evidence and leaving your text unchanged.

3,912 stars on the repository MIT LicenseNanako0129/sepia · skills/sepia-review
npx skills add Nanako0129/sepia -g
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Sepia Review costs

19tokens idle
205tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Fair
  • Frontmatter15/15
  • Structure0/25
  • Examples0/15
  • Output5/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity88
  • Maintenance100
  • Community52
  • Maturity16
  • Momentum40

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.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers