How do I install the Markdown Pipeline skill?

Run npx skillmds@latest add bh611627/markdown-pipeline in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Markdown Pipeline skill do?

Markdown and MDX pipelines with remark rehype - security performance and GFM parity It is listed under DevOps & Infra on SkillMD.

Is Markdown Pipeline safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Markdown Pipeline?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Markdown Pipeline free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Markdown Pipeline?

bh611627 (@bh611627) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Markdown Pipeline by bh611627 — Agent Skill

Name: Markdown Pipeline
Author: bh611627

File contents

Instructions

When to Use

Use for MDX/Markdown sanitize + GFM pipelines.
Prefer content-creator for social copy, not MDX plumbing.
Prefer skillcodex-browser-ui for the doc browser shell.

Design a markdown/MDX rendering pipeline for docs or blogs in Next.js.

User-generated content: sanitize HTML; forbid raw dangerouslySetInnerHTML without allowlist.
GFM: tables, task lists, strikethrough via remark-gfm.
Syntax highlight: server vs client component for Shiki or prism - pick based on bundle budget.
Links: rel on external; heading slug plugin alignment with TOC.
Images: next/image in MDX wrapper components with dimensions.

Outcomes

Plugin list + security policy paragraph + component map.

Output Rules

No unbounded HTML pass-through in examples.

Scope and boundaries

In scope: rendering stack, sanitization, MDX component whitelist.
Out of scope: full CMS selection, search indexing backend.

Safety

Read-only; highlight XSS risks if user content is involved.

Troubleshooting

Hydration on code blocks: split highlighter to client leaf or use static HTML at build time.
MDX eval: never suggest eval or arbitrary component mapping from URL params.

Related skills

content-creator - copy before pipeline
skillcodex-browser-ui - doc browser rendering
secure-dependencies - sanitizer library risk

GitHub: https://github.com/bh611627/skillcodex/tree/main/skills/markdown-pipeline/SKILL.md
npm: https://www.npmjs.com/package/@skillcodex/skills

Frequently asked questions