Learning & Documentation Agent Skills for Claude Code

Parse Fluent `/results/*.md` session files to extract error patterns, strengths, accuracy trends, and focus areas for the next session.

Markdoc is a powerful Markdown-based authoring framework created by Stripe to power their public documentation.

Audit and fix markdown for accessibility.

Comprehensive markdown and Mermaid diagram writing skill.

Internal helper agent. Invoked by orchestrator agents via Task tool. Internal helper for applying accessibility fixes to markdown files…

Build a library of metacognitive prompts targeting planning, monitoring, or evaluation for a specific task.

Create comprehensive HTML architecture diagrams showing data flows, business objectives, features, technical architecture, and deployment.

MultiGlossar configuration and exclusion rules - glossar_starttag/glossar_endtag scope selection, glossar_ignoretags with tag/class locks…

Analyze content sequences within a section and provide neutral descriptions for AEM Edge Delivery Services.

Extract TikZ diagrams from Beamer `.tex` source, compile each to a standalone PDF, and convert to SVG with 0-based indexing.

Convert HTML and Markdown content into Portable Text blocks for Sanity.

Generates professional, high-quality slide decks with structured storytelling, data visualizations, and speaker notes.

Agent role definitions for generating PPTX slides.

Adversarial reading methodology for narrative fiction — find what doesn't work, not confirm what does.

Publish Markdown articles to Substack as drafts.

Render academic Markdown documents (English or Korean) to publication-quality PDF via pandoc + xelatex.

Research Elixir/Phoenix/Ecto topics or evaluate Hex libraries (--library).

AUTO-INVOKE when user mentions research, paper, citation, GRADE, corpus, provenance, literature review, induct paper, induct media…

Look up current research information using Perplexity's Sonar Pro Search or Sonar Reasoning Pro models through OpenRouter.

PDF manipulation toolkit. Extract text/tables, create PDFs, merge/split, fill forms, for programmatic document processing and analysis.

Navigates and extracts hierarchical information from academic papers, ranging from metadata to full-text markdown content.