Skill Claude CodeCodex
Run expert review on a plan, spec, or implementation approach with parallel reviewer agents. Presents findings as Socratic questions. Use when asked to "review the plan", "check this approach", or before implementation to validate architectural decisions. Optional argument: reviewer name (e.g., /arc:review…
Skill Claude CodeCodex
Characterization testing and safety-net backfill for existing code. Use when legacy, under-tested, or risky code needs tests before a refactor, bug fix, or behavior change. Captures current behavior through public interfaces, identifies coverage gaps, and adds focused unit, integration, or E2E tests without replacing…
Skill Claude CodeCodex
Use when starting any conversation - establishes Arc's skill routing, instruction priority, and bootstrap rules.
Skill Claude CodeCodex
Create or maintain a project's root CONTEXT.md — goals, product boundary, non-goals, decision principles, and a domain language glossary. Use when starting a new project, clarifying product direction, aligning a codebase for future agent work, defining a north star, pinning down domain terminology, or turning a vague…
Plugin Claude Code
Plugin marketplace listing 1 plugin: fiction.
Plugin Claude Code
Write complete novels with Claude and Codex. Literary prose, iterative review, and craft-aware feedback.
Agent
Design high-level story architecture. Use when starting a new project, rethinking structure, or establishing the foundation of a story. Produces premise, theme, arc, ending, and tone.
Agent
Review a chapter after writing. Checks coherence, cheesiness, consistency, pace, tone, and character. Suggests specific rewrites.
Agent
Create or develop character documents. Use when establishing new characters or deepening existing ones.
Agent
Check for consistency issues across chapters. Finds timeline problems, character detail changes, plot holes, and contradictions.
Agent
Generate book cover art prompts from story content. Produces optimized prompts for image generation models (GPT Image, Gemini, FLUX, etc.) that conform to Kindle dimensions.
Agent
Write a full literary critique of a completed manuscript. NYT/New Yorker style. Only use when the manuscript is complete.
Agent
Line-level editing for spelling, grammar, awkward phrasing, word echoes, and polish. Run across chapters for manuscript-wide cleanup.
Agent
Generate consistent chapter illustrations using motif series. Reads chapter content, extracts key scenes, and generates illustration prompts that maintain visual consistency across the book.
Agent
Review like James Wood of The New Yorker. Deeply literate, focused on sentences, consciousness, and the craft of fiction. For literary fiction.
Agent
Verify non-English phrases for grammatical correctness, contextual appropriateness, and translation accuracy. Catches anachronisms, dialect mismatches, and register errors.
Agent
Generate and validate book title options. Reads project content, produces title candidates using proven naming strategies, and checks availability against existing books.
Agent
Create a new fiction project from scratch. Interactive wizard that guides through discovery, architecture, characters, world, and outline. Highly conversational with multiple choice at every step.
Agent
Assess project status and suggest what to work on next. Use when you sit down and don't know where to start.
Agent
Break a story into chapters and scenes. Use after architecture is established to create a working outline.
Agent
Comprehensive chapter analysis with craft observations and quotes. Includes all skim-level data plus arcs, themes, and evidence.
Agent
Coordinate reading an entire manuscript via parallel reader agents. Writes manuscript-digest.md and returns a short summary. Prevents context overflow in parent agents.
Agent
Fast fact extraction from a single chapter. Plot beats, timeline, characters, settings. Designed for parallel spawning.
Agent
Coordinate reviewing multiple chapters via parallel chapter-reviewer agents. Writes review-report.md and returns aggregate summary. Prevents context overflow.