Find agent skills by outcome

Generate a LinkedIn post about {{topic}} as a real-world engineering lesson.

Structure:

Generate a LinkedIn post describing a real-world performance or design improvement.

Structure:

Generate a LinkedIn post that explains {{topic}} as a layered or stacked mental model.

Structure:

Generate a LinkedIn post that breaks down {{topic}} from a practitioner's perspective.

Structure:

Generate a LinkedIn post about {{topic}} focused on automation and operational reliability.

Structure:

Generate a LinkedIn post comparing data or AI architectures from a real-world engineering perspective.

Structure:

Stage 6: Supplemental

> Prompts: **Author Bio** | **Colophon / Technical Notes** | **Acknowledgements** | **Back Cover Blurb** | **Metadata Block**

Stage 5: Illustration

> Prompts: **Visual Brief** (figure and diagram specification) | **COMAC-Visual** (visual accessibility check) | **Caption Generator**

Stage 4: Review

> Prompts: **AASS** (Quality Scoring) | **DARE** (Targeted Dimension Review) | **IRIN** (Integrated Review Inline) | Reader Simulation panels

Stage 3: Refinement

> Prompts: **COREF** (Consistency Reference Check) | **STRAL** (Style Alignment) | **COMAC** (Comprehension and Accessibility Check) | **CAM** (Chapter Arc Map)

Stage 2: Writing

> Prompts: **CHDD** (Chapter Detail Definition) | **CHFO** (Chapter From Outline) | **SUBREF** (Subject Reference Generator)

Stage 1: Concept Development

> Prompts: **STRUO** (Concept Development) | **ANALY** (Domain Analysis) | **COMPR** (Concept Stress-Test)

prompts/ — Static Prompt Library

Six-stage prompt library for the Static Prompt Bootstrap (Phase 0) — generating book chapters without a world model infrastructure, using a chatbot and copy-paste.

Task Prompts (Portable)

Input:

System Prompt (Portable)

You are the UAE Radio Content Agent.

Output Templates and Multi-Format Rules

The study notes must render correctly in three contexts: Markdown viewers, PDF conversion, and plain text reading. Follow these rules to ensure compatibility.

Curriculum Coverage Search Strategy

This file defines how to find and evaluate standard curriculum coverage for **any academic subject**. It replaces hardcoded topic lists — which only covered 8 CS/engineering subjects — with a live search approach that works for any course a student might take.

Phase 2: Cross-Lecture Deep Synthesis

Build a **deep conceptual structure** of the entire course by connecting knowledge across all lectures/sections. This is NOT a simple merge — it requires applying world knowledge, revealing relationships the slides only imply, and identifying what the course doesn't teach.

Phase 4: Structured Deep Study Notes

Produce the **final, comprehensive study notes** integrating all prior phases into a single authoritative document. This is the deliverable the student will actually use.

phase-intake — Phase 0: Intake Workflow

Run all steps below before starting any phase. **Keep this fast** — intake should take one exchange, not five.

Phase 1: Backbone Extraction

Extract every concept, definition, formula, algorithm, code snippet, and diagram from the course PDFs, **strictly aligned to page numbers**. Zero information loss is the target.

Phase 3: External Knowledge Expansion

Expand the knowledge base **beyond the course boundary** with precisely sourced external knowledge. The result should make the student's understanding deeper and broader than the course alone provides.

pdf-export — PDF Conversion Configuration

**Load this file only when the user has requested PDF output** (confirmed in Phase 0 or explicitly during Phase 4). For Markdown-only output, format rules in `rules/templates.md` are sufficient.

changelog — Version History

- **Exam Ready output package** — Quick Reference Sheet + Exam Q&A Appendix