# Nanako0129/sepia

> An Agent Skill for de-AI-ing writing: it repairs narrative architecture in fiction and applies venue-matched rules to professional prose (release notes, PR replies, postmortems, tickets, articles). Based on the StoryScope study.

- Magnitude: 1.4 out of 10 — Steady
- Stars: 3,542 total · +5 stars measured 2026-10-29, 00:09–07:13 UTC, ≈ 14 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · License: MIT · Created: 2026-08-28 · Last push: 2026-10-15
- GitHub: https://github.com/Nanako0129/sepia · Page: https://gitnova.dev/en/r/Nanako0129/sepia

## Useful for

- Run a short-story draft through review to surface architectural AI tells without edits
- Draft release notes or a postmortem using the venue-matched rule file
- Refactor a text with minimal in-place edits instead of a full rewrite

## Why it’s here

- Star-counter measurements on 2026-10-29 (UTC), 00:09–07:13: 3537 → 3542 stars (+5). This is the change over that interval.
- Estimated end-of-day forecast: about +14 stars, using observed gains and the previous day.
- Interest is fading: the two-day pace is 45% of the previous week and a half.

## Star trust

Star growth looks organic.
- Hardly anyone watches for updates: 5 watchers for 3,542 stars.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 218
- Issues and pull requests: 108
- Watchers: 5
- Average over the last week: 18 per day
- Usual pace: 31 per day
- Stars in the last hour (measured): 1
- Latest release: v0.12.4 (2026-10-15)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-30 … 2026-10-29: 3, 14, 5, 11, 9, 38, 14, 22, 23, 22, 13, 15, 52, 15, 16, 15, 14, 16, 17, 27, 23, 124, 29, 13, 18, 19, 23, 26, 12, 5

## Magnitude by day, last 14 days

09-26 1.3, 09-27 1.7, 09-28 1.7, 09-29 1.2, 09-30 1.2, 10-01 1.1, 10-02 1.2, 10-03 1.0, 10-04 1.2, 10-05 1.9, 10-06 2.1, 10-27 1.6, 10-28 1.9, 10-29 1.4

## Similar by description

1. **KKKKhazix/human-writing** — 1.7 · Steady · AI agents · Python · +7 stars measured 2026-10-29, 00:09–07:12 UTC, ≈ 19 by evening
   A Skill (rules plus scripts) for agents that makes AI write Chinese like a real person: grounded facts, forward-moving prose, and no clichés like "not A but B". Suited to articles, posts, blogs, scripts and fiction.
   Full card: https://gitnova.dev/en/r/KKKKhazix/human-writing.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-29 07:17 UTC, updated every 30 minutes.