proomt

Search

Search posts, papers, and topics

All posts

Daniel Doubrovkine (dB.)2 min readintermediate

Serving Markdown for AI Agents, Now as a Jekyll Plugin

Summary

The author turned a one‑off script that rendered each Jekyll page to Markdown and added a `<link rel="alternate" type="text/markdown">` tag into a reusable Jekyll plugin (jekyll‑md). The gem hooks into the build, extracts the main content (defaulting to `<main>` or `[role="main"]`), converts it to Markdown, injects the discovery link, and requires no per‑page front‑matter. Configuration is option…

  • Package site‑wide Markdown rendering as a Jekyll plugin to avoid per‑page boilerplate.
  • Leverage Jekyll generators and hooks to run after HTML rendering, keeping the workflow in the static‑site build.
  • Default content extraction from `<main>` or `[role="main"]` works for most themes; a custom selector can be supplied.
  • Avoid generating a monolithic llms.txt; instead curate a small file manually to stay within LLM context limits.

Providing clean Markdown lets LLM‑based agents consume content without HTML parsing, improving reliability and enabling downstream use‑cases (e.g., the author’s $360 referral conversion). Packaging the logic as a plugin simplifies maintenance, reduces duplication, and makes the technique reusable f…

6/10

Related reading

  1. Markdown in /src

    The essay argues that Markdown should be treated as source code and checked into a /src/md directory alongside the implementation it describes. Keeping intent in diffable, reviewable Markdown lets teams generate code and tests from it while preserving locality for both humans and AI agents.

    Lobstershtmx.org6 minlobste.rs10
  2. Rails Hyperdrive: supercharged agentic development for Rails

    Rails Hyperdrive is a development‑only Rails engine that mounts a Model Context Protocol (MCP) server and lets any gem ship agent knowledge (skills, agents, commands, guidelines) as markdown files. The engine adds no knowledge itself; companion gems provide the context‑aware artifacts that agents can query at runtime, avoiding token‑heavy guessing and stale schema reads. Installation is a single…

    Evil Martiansevilmartians.com22 min
  3. Grounded Skill Synthesis from Code at Scale for Agentic Intelligence

    Code2Skill is an automated pipeline that mines popular GitHub repositories to extract verifiable, implementation‑anchored procedural “skills”. It builds a bank of ~1 M skill records (atomic ops, workflows, patterns) with provenance metadata, verifies each via blind reconstruction, and shows that augmenting LLM‑based agents with these skills yields an average 11.7% performance lift across 72 proto…

    Hugging Face Daily Papersarxiv.org1 minpaper