howells

Build an EPUB from your fiction project. Compiles chapters, metadata, and optionally a cover image.

Create or develop a character document.

Generate book cover art prompts for image generation models. Reads project content and produces optimized prompts for Kindle-dimension covers.

Run line-level editing across chapters. Catches spelling, grammar, awkward phrasing, and word echoes.

This skill should be used when the user asks to "write a chapter", "write prose", "continue the story", "develop a character", "review my chapter", "critique my manuscript", "write a synopsis", "summarize my story", "plan my novel", "outline my book", "check for consistency", or mentions fiction writing, novels, short stories, scenes, or narrative craft.

Resume work on a fiction project. Loads context and suggests what to do next.

Generate consistent chapter illustrations using motif series. Creates a visual style from the cover, builds character references, then generates one illustration per chapter with consistent styling.

Verify non-English phrases in your manuscript. Checks grammar, period accuracy, dialect, and translations.

Comprehensive codebase audit with verification and specialized reviewers. Generates actionable reports. Use when asked to "audit the codebase", "review code quality", "check for issues", "security review", or "performance audit". By default, run the complete audit: mechanical checks first, then specialist reviewers, then a scored report.

Comprehensive codebase audit with verification and specialized reviewers. Generates actionable reports. Use when asked to "audit the codebase", "review code quality", "check for issues", "security review", or "performance audit". By default, run the complete audit: mechanical checks first, then specialist reviewers, then a scored report.

Smart commit, push, and npm publish with auto-splitting across domains. Creates atomic commits. Use when asked to "commit", "push changes", "publish", "save my work", or after completing implementation work. Automatically groups changes into logical commits.

Scope-aware implementation workflow with TDD and continuous quality checks. Use when asked to "implement this", "build this feature", "execute the plan", or after /arc:ideate has created a feature spec. For small work it creates a lightweight inline plan; for larger work it creates or loads a full implementation plan and executes task-by-task with build agents.

Go-live and shareability checklist covering the basics needed to make a project visitable, shareable, and ready for a first real audience. Use when asked to "launch", "go live", "make this shareable", "get this ready to show people", or prepare a project for a public URL.

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 daniel-product-engineer`)

Create, review, or revise a concise project vision document that captures what a project is, who it is for, why it exists, success criteria, constraints, non-goals, and decision principles. Use when starting a new project, clarifying product direction, aligning a codebase for future agent work, defining a north star, or turning a vague idea into docs/vision.md.

Internal bridge from /arc:ideate feature specs to /arc:implement execution plans. Creates implementation plans with exact file paths, test code, and TDD cycles. Invoked by /arc:implement, not directly.

Authenticate gauge without launching Chrome by importing Playwright storage-state data.

Mutate local gauge state with dry-run, raw JSON payloads, and structured responses.

Read Claude account usage safely with structured output, field masks, and paginated NDJSON.

Audit and rewrite prose that carries AI-writing tells — inflated significance, negative parallelisms like "not just X, but Y", vague attribution, and assistant leakage. Use when the user asks to "check for AI slop", "rewrite this so it sounds less like ChatGPT", "audit this draft for AI slop", "why does this sound AI-generated", "clean up LLM prose", or wants to identify and fix synthetic writing patterns.

Create or standardize a new Howells project using the scaffold baseline for repo archetypes, pnpm/Turborepo/@howells/lint Oxlint/Oxfmt/TypeScript configuration, package boundaries, UI stack, data and AI defaults, agent workflow, deployment defaults, and launch readiness. Use when starting a new repo, bringing an existing repo onto Howells conventions, choosing a project archetype, drafting baseline files, generating setup plans, or checking a repo against the scaffold launch checklist.

Make software legible to agents and guide production agent-system design. Use when asked for Agent Surface guidance, agent-readable software, agent readiness, AGENTS.md/llms.txt/MCP/OpenAPI/CLI/tool surfaces, agent protocols or tooling, audits or scorecards, transformation plans, or scaffolding agents/tools/workflows/memory/model routing/browser/sandbox capabilities across APIs, CLIs, docs, auth, errors, tests, retrieval, and multi-agent systems.