KS
Killer-Skills

md-style-preserving-edit — how to use md-style-preserving-edit how to use md-style-preserving-edit, md-style-preserving-edit alternative, md-style-preserving-edit setup guide, what is md-style-preserving-edit, md-style-preserving-edit vs markdown editors, md-style-preserving-edit install, markdown editing tools, ai agent skills for developers, non-destructive markdown editing

v1.0.0
GitHub

About this Skill

Perfect for Content Creation Agents needing to edit Markdown documents while preserving their style and structure. md-style-preserving-edit is a skill that enables non-destructive editing of Markdown documents, preserving heading hierarchy and terminology while inserting new sections.

Features

Scans Markdown files for heading hierarchy and numbering conventions
Preserves terminology and labels, including window names and variables
Performs non-destructive editing, keeping existing text intact
Inserts new sections where appropriate, maintaining document structure
Supports editing of .md files, ensuring consistency in Markdown formatting

# Core Topics

Rukkha1024 Rukkha1024
[0]
[0]
Updated: 3/6/2026

Quality Score

Top 5%
20
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add Rukkha1024/replace_V3D/md-style-preserving-edit

Agent Capability Analysis

The md-style-preserving-edit MCP Server by Rukkha1024 is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for how to use md-style-preserving-edit, md-style-preserving-edit alternative, md-style-preserving-edit setup guide.

Ideal Agent Persona

Perfect for Content Creation Agents needing to edit Markdown documents while preserving their style and structure.

Core Value

Empowers agents to seamlessly integrate new content into existing Markdown files, adhering to the document's heading hierarchy, terminology, and labeling conventions, using non-destructive editing to keep existing text intact.

Capabilities Granted for md-style-preserving-edit MCP Server

Automating updates to technical documentation
Generating new sections for Markdown-based blogs
Preserving formatting while inserting new content into knowledge base articles

! Prerequisites & Limits

  • Requires read access to the target .md file
  • Limited to editing Markdown files (.md)
  • Default behavior is non-destructive, which may not be suitable for all use cases
Project
SKILL.md
2.5 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

Md Style Preserving Edit

Overview

Edit existing Markdown documents by adding content in a way that matches the document's current writing style and structure. Default behavior is non-destructive: keep existing text intact and only insert new sections where appropriate.

Workflow

1) Scan Style And Structure (Read-Only)

Before editing, scan the target .md file for:

  • Heading hierarchy: #, ##, ### usage and numbering conventions.
  • Terminology and labels: window names, variable names, abbreviations, domain terms.
  • Table style: column order, alignment, numeric formatting (M±SD, decimals), separators.
  • Citation/link style: wiki links [[...]], [@paper], plain text references.
  • Tone: bullet-heavy vs narrative, Korean vs English mix, sentence endings.

Produce a short "style contract" (internal checklist) and follow it for all inserted text.

2) Decide Edit Mode (Default: Insert)

Pick one of the following, in this priority order:

  • Insert (default): add a new section into an existing location (recommended for analysis updates).
  • Append: add a new section at the end (recommended when the document has stable ordering).
  • Replace/Rewrite: only if the user explicitly says to rewrite, reorganize, or replace existing text.

If the user did not explicitly request rewrite, do not overwrite the whole file even if automation would be easier.

3) Choose Insertion Location (Style-Compatible)

Preferred insertion rules:

  • Insert near the most relevant existing section (e.g., under # 3. results if adding new results).
  • Do not renumber existing headings unless requested.
  • Avoid changing the document's outline unless necessary.

If a safe insertion point cannot be determined, ask the user where to add the new content.

4) Write New Content To Match Existing Style

Rules:

  • Use the same language mix (Korean/English), punctuation, and bullet style found nearby.
  • Match numeric formatting already used in the file (decimals, units, M±SD, p-value format).
  • If adding tables, keep column order and headers consistent with neighboring tables.
  • Reuse existing labels (e.g., 분석구간, 요약, 해석상 주의사항) instead of inventing new ones.

5) Prevent Accidental Duplication (When Automating Inserts)

When inserts are produced by scripts, add a small marker line to the inserted block, e.g.:

  • <!-- AUTO_APPEND: <id> -->

Then:

  • If the marker already exists, skip inserting again.
  • Do not delete or replace existing content unless explicitly requested.

Related Skills

Looking for an alternative to md-style-preserving-edit or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication