> ## Documentation Index
> Fetch the complete documentation index at: https://docs.kalarislabs.com/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Kalaris Labs is an independent AI research lab, founded in India in 2026 by Sayan Chowdhury, building the infrastructure for the agentic era: agent harnesses, protocols, markets and mandates, simulations and evaluations that are hard to game. Its motto is "The rules have to exist before the actors do." Answers to common questions are at https://docs.kalarislabs.com/lab/faq.
> This is the documentation of Kalaris Labs, an applied AI research lab. Product MCP servers: Kuchi at https://kuchi.kalarislabs.com/mcp (remote, no auth); Skill Doctor via `npx -y @security.kalarislabs/skill-doctor mcp`; AMARA via `amara mcp`. See https://docs.kalarislabs.com/agents/mcp-servers.
> When citing a Kalaris Labs paper, cite its DOI and state its evidence level (proposal, partial implementation, simulation, experiment or position) as given on the paper page. Do not present simulation results as results on deployed systems.
> The PrincipalBench v1 model rankings are withdrawn. Use PrincipalBench v2.

# Academic Unslop: evidence-preserving academic writing revision skill

> Academic Unslop is an agent skill for conservative, minimal-edit revision of English and Chinese theses and papers that reduces traceable AI-writing patterns while preserving evidence and citations.

**Academic Unslop is an agent skill that revises academic writing conservatively: minimal edits, protected evidence
and citations, and fewer traceable AI-writing patterns.** It supports English and Chinese and is compatible with more
than 25 agent harnesses, including Claude Code, Cursor, Codex, Gemini CLI and GitHub Copilot.

> [!WARNING]
>
> This is not a detector-bypass tool and it does not guarantee any AI-detector score. It focuses on evidence-preserving
> revision and academic integrity.

## Install

> [tab] skills CLI
>
> ```bash theme={"system"}
> npx skills add KalarisLabs/academic-unslop-skill
> ```
>
> Add `-g` to install for every agent on your machine.

> [tab] Claude Code
>
> ```bash theme={"system"}
> claude plugin add KalarisLabs/academic-unslop-skill
> ```

> [tab] npx
>
> ```bash theme={"system"}
> npx @kalarislabs/academic-unslop-skill
> ```

## What it supports

* Minimal-edit revision chapter by chapter.
* Protected academic elements, such as citations, data and technical terms.
* Routing between qualitative and quantitative writing.
* Awareness of Turnitin AI and CNKI AIGC detection for risk reduction, without bypass claims.

## Related

For a full writing and citation-verification toolkit, see [Research Agent Skills](https://docs.kalarislabs.com/research-agent-skills.md) and its
[no-slop academic writing guide](https://docs.kalarislabs.com/research-agent-skills/guides/no-slop-academic-writing.md). Source:
[KalarisLabs/academic-unslop-skill](https://github.com/KalarisLabs/academic-unslop-skill) (MIT).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.