AI Engineering

Use when building retrieval-augmented generation. Covers chunking, embedding and hybrid search, reranking, grounding and citation, and diagnosing whether a bad answer is a retrieval failure or a generation failure.

Implements a Visionary/Integrator workflow between Fable and Codex to start projects, refactor code, validate plans, and delegate builds.

A guide for creating skills that trigger reliably and change an AI agent's behavior. Use when writing or debugging a skill, focusing on scoping, description writing, and progressive disclosure.

Provides guidance for creating reusable slash commands for AI agents, covering argument handling, workflow composition, and distinguishing commands from skills.

Use when an LLM must return machine-readable data. It covers schema design, native structured-output modes, validation and repair, and extraction from messy input.

Design and dispatch subagents for context isolation, parallel work, or verification. Use when delegating tasks to a separate agent with its own context is more efficient than processing in the main context.

Performs deep, source-validated literature reviews on agricultural questions using a 12-subagent AI system with rigorous source screening and academic integrity checks.

Conducts comprehensive literature and evidence synthesis for agricultural science, acting as a senior agricultural scientist. Use for in-depth research, literature reviews, evidence briefs, or systematic reviews.

Multi-reviewer peer-review system for agricultural manuscripts. Simulates an editorial panel of domain reviewers and a formatting check against the target journal.

Multi-subagent manuscript system for food and nutrition science covering literature review, data analysis, statistics, figure building, drafting, and journal formatting.

Orchestrates the complete food & nutrition research-to-publication pipeline, routing tasks to specialist AI skills with quality checks. Use when you need to manage a paper from research through submission and revision.

Foreman interviews the user, forces scope and design decisions, then writes one build brief for a coding agent to implement and verify. Use it before any web build or redesign, including portfolios, landing pages, docs sites, and launch pages.