No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by Nanako0129 · Claude Skill · ★ 2.7k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is sepia safe to install? View the security audit →
sepia English | 繁體中文 De-AI writing at the layer that actually gives AI away. Fiction gets its narrative architecture repaired before anyone touches word choice; professional documents (release notes, PR replies, postmortems, tickets, technical articles) each get rules matched to their venue. A portable Agent Skill for Claude Code, Codex, Grok Build, and Antigravity. One canonical , no per-platform forks. Four operations: write, review (diagnose only), refactor (minimal edits), recreate (full rewrite). Why another humanizer Every popular humanizer edits word choice and syntax. StoryScope (Russell et al., 2026: 61,608 stories, human + 5 frontier LLMs) showed that a classifier using narrative-structure features alone detects AI fiction at 93.2% macro-F1, and that editing the surface style away barely moves it (95.5% → 93.9%). The tells that survive are architectural: themes explained by the narrator, single-track causally-tidy plots, emotions rendered only as bodily sensation, no real-world references, no reader, linear time, endings resolved by protagonist growth and acceptance.
| Stars | 2,703 |
| Forks | 180 |
| Language | Python |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 67.470381975794/100 |
| Open Issues | 7 |
| Last Updated | 2026-09-20 |
| Created | 2026-08-28 |
| Platforms | claude-code, cli, codex, python |
| Est. Tokens | ~15k |
These tools work well together with sepia for enhanced workflows:
Looking for a sepia alternative? If you're comparing sepia with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
说人话｜中文优先的去 AI 味改写 skill：保事实、分场景、改完可直接发。Chinese-first rewrite skill for Codex / Claude Code / Cursor / ChatGPT
去 AI 味：去除简体中文 AI 写作痕迹 / Chinese humanizer skill
The most comprehensive Claude Code guide: agentic workflows, hooks, skills, MCP servers, quizzes, and producti
Skill that audits and rewrites content to remove AI writing patterns. Use it with your favorite agents includi
Templates and workflow for generating PRDs, Tech Designs, and MVP and more using LLMs for AI IDEs
🎭 AI 写小说：从零生成 10-50 章完整中文小说，三层问答 · 创作记忆 · 悬念钩子 · 自动校验，长篇网文连载皆宜｜开源免费，适配主流 coding agent｜AI novel writing skill
Explore other popular claude skill tools:
sepia is De-AI writing skill for any Agent Skills-compatible agent (77+ via the Skills CLI), with native plugins for Claude Code, Codex, Grok Build, and Antigravity. Narrative-architecture repair for fiction, . It is categorized as a Claude Skill with 2.7k GitHub stars.
sepia is primarily written in Python. It covers topics such as agent-skills, ai-writing, antigravity.
You can find installation instructions and usage details in the sepia GitHub repository at github.com/Nanako0129/sepia. The project has 2.7k stars and 180 forks, indicating an active community.
sepia is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to sepia on Agent Skills Hub include shuorenhua, qu-ai-wei, claude-code-ultimate-guide. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: