claudecodex

velith

Books to the human-quality bar — 6-phase pipeline (onboarding → ideation → outlining → drafting → editing → publishing), 12 agents, full-manuscript context, voice lock, draft-critique-revise, fact-check, beta-reader readiness gate, art bible and model-agnostic image pipeline. Fiction, non-fiction, technical, screenplay, poetry, game, academic, custom.

40 on GitHubby epicsagasv0.7.2Apache-2.0updated 9 days ago

Not in a marketplace yet, so it loads for one session with --plugin-dir.

Plugin velith in epicsagas/Velith. Commands read from the repo's manifest — 8 days ago.

What it installs

Skills (18)

  • book-academic

    Academic writing craft reference: IMRAD and discipline structures, literature review, argument chains, citation integrity, academic register in en/ko/ja, and academic-writing AI tells. Read by all agents on theses, dissertations, monographs, and research reports.

  • book-draft

    Phase 3: Drafting. Voice lock on a sample chapter, then sequential full-context chapter drafting with draft-critique-revise, bible ledger updates, and periodic continuity checks.

  • book-edit

    Phase 4: Editing. Fact-check (nonfiction), assessment, developmental edit, line edit, copy edit, proofread, then a cold read by simulated readers that issues the readiness verdict. Rewrites the manuscript; does not only file reports.

  • book-fiction

    Fiction craft reference for all subgenres: structure options, scene design, character depth, dialogue, POV and distance, the fiction-specific AI tells, and language notes. Read by architect, scene-generator, chapter-writer, editors, and beta-reader on fiction projects.

  • book-game

    Game narrative craft reference: branching architecture, quest design, dialogue systems, lore bible, player agency, and game-writing AI tells. Read by all agents on game scenarios, visual novels, and interactive fiction.

  • book-genre-creator

    Meta-skill for genre selection and custom genre creation. Routes a project to the right built-in genre or composes a genre-custom.md spec from existing patterns, including agent behavior and validation rules.

  • book-ideation

    Phase 1: Ideation. Stress-test the premise, research real comparable titles, generate and rank concepts, offer voice samples, and lock a single concept with a reader promise.

  • book-illustrate

    Alias for /book-visuals limited to diffusion illustrations (scene, header, spot art). Kept for compatibility; new work should use /book-visuals, which also covers diagrams, charts, technical drawings, photos, and the art bible.

  • book-init

    Phase 0: Onboarding. Define genre, reader, language, scope, and voice; capture the author's voice fingerprint; index source material; generate PRD.md and STYLE.md.

  • book-nonfiction

    Nonfiction craft reference: argument architecture, evidence discipline, narrative in nonfiction, chapter design, the nonfiction-specific AI tells. Read by all agents on nonfiction, memoir, business, self-help, essay, and narrative nonfiction projects.

  • book-outline

    Phase 2: Outlining. Build the chapter-by-chapter outline with genre structure, create the book bible, validate structure with book-architect, and get author approval.

  • book-poetry

    Poetry craft reference: forms, the line, image, sound, compression, collection architecture, and poetry-specific AI tells. Read by all agents on poetry collections, chapbooks, and poetry-essay hybrids.

  • book-publish

    Phase 5: Publishing. Gate on readiness, assemble front and back matter, build EPUB/PDF/MOBI/TXT/Markdown with Pandoc, validate with epubcheck, produce metadata, title candidates, cover concepts, and marketing plan. Includes KDP and Korean platform checklists.

  • book-screenplay

    Screenplay craft reference: format, three-act and sequence structure, scene construction, dialogue subtext, A/B/C story weaving, series bibles, and screenplay-specific AI tells. Read by all agents on film, TV, and web-series projects.

  • book-status

    Book project status and progress dashboard. Scans the project, writes status.json for the web UI, and reports phase, chapters, readiness score, and metrics.

  • book-technical

    Technical book craft reference: concept gradient, running project, failure-first teaching, code standards, diagrams, exercises, version handling, the technical-book AI tells. Read by all agents on programming, engineering, and data science books.

  • book-visuals

    Book visual system: art bible and look lock, figure plan per chapter, code-rendered diagrams/charts/technical drawings, diffusion-generated illustrations and spot art, photo sourcing policy, cover, model-agnostic prompt compilation, vision QA, and asset validation for print and EPUB. Every image mat

  • loom

    Velith router. Detects book project state and runs the next phase of the 6-phase pipeline (onboarding → ideation → outlining → drafting → editing → publishing) to the human-quality bar. Trigger: /loom, /velith, or any book-writing request.

Subagents (12)

  • art-director

    Owns the book's visual identity: writes the art bible (look, palette, medium, composition, character and setting constants, figure system, photo policy, backend profile), runs the look lock, interprets author image briefs into specs, reviews every generated image against the art bible using vision,

  • beta-reader

    Cold-reads the complete manuscript as the target readers and one genre professional, records engagement per chapter, put-down points, confusion, AI-feel with quotes, comparison to comparable titles, scores the five axes, and issues the readiness verdict (PASS or REVISE) that gates publishing. Phase

  • book-architect

    Turns an approved concept into a chapter-by-chapter outline and a book bible, chooses and justifies the structure, probes the concept for blind spots, validates the structure with a scored report, and revises. Phase 2, and on request for restructures during editing.

  • chapter-writer

    Drafts one chapter to the human-quality bar: reads the whole manuscript so far, the bible, and the voice lock; drafts; cold-critiques its own draft with quoted lines; revises; saves; updates the bible ledger. Also used for developmental rewrites in editing.

  • continuity-editor

    Reads the whole manuscript against the bible and finds contradictions (facts, character, timeline, terminology, prerequisites) and repetitions (images, phrases, sentence openers, scene shapes). Fixes Minor issues in place; reports Critical and Major with proposed rewrites. Phases 3 and 4.

  • cover-designer

    Book cover design from the art bible: 3-5 concepts with palette, typography, layout, model-agnostic prompts, format specs for ebook, print wrap, audiobook, and marketing variants; executes with an image tool when available and hands art to the art-director for consistency review. Phase 5.

  • fact-checker

    Builds a claim ledger from the manuscript, verifies every factual claim, number, quote, named person, citation, and code block against sources/ and the web, and edits the drafts to correct or remove what cannot be verified. Nonfiction, technical, academic, and real-world claims in fiction. Phase 4,

  • figure-engineer

    Produces every code-rendered figure: diagrams (Mermaid, D2, Graphviz), charts from data (matplotlib, Vega-Lite), technical drawings and floor plans (SVG with real dimensions, TikZ), maps' base layers, tables-as-figures, ornaments. Follows the art bible's figure system, verifies labels against the te

  • illustrator

    Produces diffusion-generated images that match the art bible: scene illustrations, chapter headers, spot art, character and setting reference sheets, map stylization. Compiles model-agnostic prompts through velith.mjs, generates when an image tool is available, runs vision QA on every result, and pl

  • marketing-expert

    Positioning, reader personas, comparable-title framing, channel plan by genre and market, launch timeline, 12-week content calendar, and launch checklist. Uses the readiness report's strengths as the lead. Phase 5.

  • scene-generator

    Plans the scenes of one fiction chapter before drafting: purpose, POV, entry state, goal/conflict/turn/outcome or reaction/dilemma/decision, subtext, what is withheld, sensory anchors, exit hook, and chapter-level emotional trajectory. Produces a plan, never prose. Fiction, screenplay, and game only

  • style-doctor

    Measures and rewrites prose against the voice fingerprint and the 2026 AI-tell taxonomy: rhythm uniformity, structural tells, emotional tells, lexical tells in en/ko/ja, register drift. Edits in place at paragraph and sentence level and reports before/after with metrics. Phase 4 line edit.

View source on GitHub epicsagas.github.io

Similar plugins

hyperframes

claudecodex

Recommended: all published HyperFrames skills in one versioned bundle. Create and render videos from HTML: the contract, film, captions, overlays, motion and look references, the CLI, the registry, media, Figma, slideshows and Remotion ports.

22 skills

heygen-com/hyperframes 83,516

agentdb

claude

AgentDB (external: maintained in ruvnet/agentdb, pinned to commit 27678c3, plugin 3.6.0): agentdb's own standalone MCP server pinned to [email protected] (vector memory with get/list/update/delete for records, patterns and skills, hybrid keyword + vector episode search and an opt-in local cross-encoder, an opt-in aidefence injection guard on memory writes, reflexion, skills, outcome feedback, capabilities report), a memory-specialist agent, 3 skills, /agentdb-status, and the agentdb mod guard that keeps secrets out of memory and refuses delete/reset unless allowed. Complements ruflo-agentdb, which reaches AgentDB through ruflo's server

3 skills · 1 command · 1 agent · 1 MCP server

ruvnet/ruflo 81,589

humanizer

claude

Rewrite AI-sounding text so it reads like the writer without changing what it says.

1 skill

blader/humanizer 68,461

5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.

5 skills · 16 commands · 4 agents · hooks

Imbad0202/academic-research-skills 56,698

OpenAPI specification generation, Mermaid diagram creation, tutorial writing, API reference documentation

3 skills · 1 command · 5 agents

wshobson/agents 42,461

Provision direct cloud access (Vertex AI, Bedrock, or LLM gateway) for the Claude Microsoft 365 add-in. Generates the customized manifest, walks through Azure admin consent, and writes per-user config via Graph extension attributes.

1 skill · 9 commands

anthropics/financial-services 41,259

Maintain velith?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted