AI Engineering

Council Execution runs council queries across selected AI providers, prints their responses verbatim, and adds a synthesis of consensus, divergence, and recommendations. Use it for standard non-agent council queries.

Deep Execution spawns parallel Claude subagents to query providers, assess response quality, ask follow-ups, and return structured insights. Use it for agent-enhanced council runs or complex architectural decisions.

Local Council Execution runs a fallback panel of independent Claude subagents when no external providers are available. It gathers role-based perspectives and synthesizes them for the ask command or local-council flow.

Provider Integration adds new AI providers to Claude Council by creating shell scripts, setting API keys, and validating connectivity. Provider Integration also helps troubleshoot discovery, API errors, and response parsing issues.

Long-Form Novel Analysis turns a novel or web serial into a traceable source analysis with chapter indexing, plot-unit aggregation, character merges, and adaptation-value assessment. Use it when you want to judge whether a book is worth adapting into short drama episodes.

Awesome Novel coordinates a multi-agent workflow for writing novels with AI, from project initialization and story setup to chapter planning and archiving. Use it when starting a new novel or importing an existing one.

Soul embodies a digital identity by reading SOUL.md, STYLE.md, memory, and examples before responding in character. Use it when you need an agent to write or think as a specific person.

Agent Research Aggregator scans AI agent cache directories or a chosen folder for experiment logs and turns them into PaperOrchestra-ready idea and experimental log inputs. Use it before PaperOrchestra when your evidence is scattered across agent histories.

Content Refinement Agent refines a paper draft by simulating peer review, applying targeted revisions, and stopping only when the scoring rules or iteration cap are met. It is used for Step 5 of the PaperOrchestra pipeline and keeps snapshots and a worklog so accepted changes can be reverted reliably.

Outline Agent converts idea notes, experiment logs, a LaTeX template, and conference guidelines into a strict JSON paper outline. It is used when drafting the structure, plotting plan, related work plan, and section plan for PaperOrchestra Step 1.

Paper Autoraters runs PaperOrchestra’s four LLM-as-judge evaluators for paper quality, citation coverage, and side-by-side comparisons. Use it to score a draft, compare two papers, or validate a paper-writing pipeline.

Paper Orchestra orchestrates a five-agent pipeline that turns research notes, experiment logs, templates, guidelines, and figures into a LaTeX manuscript and compiled PDF. Use it when you want to generate a conference submission from unstructured research materials.