Claude Code plugin: produce long-form content (books, research reports, screenplays and audiobooks) with teams of subagents. Definition, planning, research, parallel unit drafting, review (including a seam reviewer for the joins between units), then a production stage per type: typeset-and-handoff, PDF export, Fountain, or spoken script, per-chapter TTS and a chaptered m4b. Organised so no single agent is ever given a task large enough to degrade. Successor to book-writing.
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin long-form-content in danielrosehill/Long-Form-Content-Plugin. Commands read from the repo's manifest — 10 days ago.
audiobook-productionTake a reviewed audiobook manuscript to a finished, chaptered audiobook. Narration adapters produce spoken scripts in parallel, script-lint and a spoken-layer seam pass check them, each chapter is rendered through the configured TTS command (resumably), and the chapters are joined with chapter marks
create-workspaceCreate a new long-form project workspace (book, report, screenplay or audiobook) from the Long-Form-Content-Workspace-Template repository, or scaffold one locally. Use when starting a new long-form project.
definitionRun the definition stage of a long-form project (book, report, screenplay or audiobook) — record the brief verbatim, interview for the gaps, and settle the spec. Use at the start of a project, before any planning or outlining.
draftingDispatch unit-writing subagents (chapters, report sections, screenplay sequences) in parallel batches to draft the work, and handle research where a chapter's sources are not yet gathered. Use once briefs exist. Enforces the batching rule that keeps parallel writers from colliding.
graphicsProduce the figures for a book or report (screenplays and audiobooks have none) — establish the graphics style guide, spec each figure, and generate them. Use after chapters are drafted, in parallel with review.
planningRun the planning stage — write the style guide, design the structure, and produce one brief per unit, including the Seams section that tells each writer where its neighbours leave off. Use after the spec is settled and before any drafting.
publicationThe production stage, branched by [output] type. Book, assemble, typeset the body and hand off to print geometry. Report, assemble and export a research PDF via pandoc and typst. Screenplay, assemble Fountain and export a PDF. Audiobook, hand to audiobook-production. Use as the final stage, after re
reviewRun the review team over drafted units: proofreading, voice-drift audit, continuity audit and seam review. Use after drafting and before production. Skippable by explicit user choice; the mechanical gates are not.
/long-form-content:lf-assembleProduction stage — assemble and hand off (book), export PDF (report, screenplay); audiobooks go to /lf-narrate and /lf-render
/long-form-content:lf-briefRecord the user's brief for the work exactly as given, asking nothing
/long-form-content:lf-draftDraft chapters with parallel writing subagents
/long-form-content:lf-graphicsEstablish the visual language and produce the work's figures
/long-form-content:lf-interviewInterview the user for the gaps the writing team will need — and only those
/long-form-content:lf-narrateAudiobook — adapt reviewed chapters into spoken scripts, then lint and seam-check them
/long-form-content:lf-newStart a new long-form project — create the workspace repository from the template
/long-form-content:lf-outlineDesign the structure and write one brief per chapter
/long-form-content:lf-renderAudiobook — render chapters through the TTS command and assemble the chaptered m4b
/long-form-content:lf-researchGather the source material a chapter needs
/long-form-content:lf-reviewRun the review team — proofreading, voice drift, continuity
/long-form-content:lf-seamsReview the joins between adjacent units — one seam-reviewer per seam, in parallel
/long-form-content:lf-specSettle the brief and interview into the work spec
/long-form-content:lf-statusShow what is drafted, what is not, and what is blocking production
/long-form-content:lf-styleWrite the style guide — the binding voice reference every agent reads
brief-recorderRecords the user's brief for a book exactly as given, without asking questions or interpreting it. Use as the very first step of a book project, before any interview or planning. Writes spec/brief.md and stops.
chapter-researcherGathers and records the source material one chapter needs, working from that chapter's brief. Use before drafting a chapter whose sources are not already at hand. Writes research/notes/*.md and rows in research/sources.md. Does not draft.
chapter-writerDrafts exactly one chapter from its brief, the style guide and its research notes. Never reads other chapters. Use for every chapter of the book, dispatched in parallel batches. Writes manuscript/<chapter>.md and its rows in the continuity ledger.
continuity-auditorChecks the book for repetition, contradiction and unpaid promises across chapters, using lint output and the continuity ledger rather than full drafts. Use once most chapters are drafted, and again before production. Writes review/reports/continuity-*.md; never edits prose.
figure-makerProduces one figure from its spec, obeying the graphics style guide. Use per figure after specs exist. Writes graphics/diagrams/ sources and graphics/assets/ output.
graphics-directorOwns the book's visual language — writes the graphics style guide and one spec per figure, deciding what each figure must show. Use after chapters are drafted and before any figure is made. Writes guides/graphics-style-guide.md and graphics/specs/*.md.
narration-adapterAdapts one finished chapter of an audiobook's manuscript into the spoken script the TTS engine reads — text normalisation, removal of anything visual, pronunciation applied, plain text or SSML as configured. Use per chapter, in parallel, once chapters are reviewed. Writes audio/script/<id>-<slug>.tx
outline-architectDesigns the book's structure and writes one brief per chapter — the contracts that make parallel drafting possible. Use after the spec and style guide are settled. Writes outline/outline.md, outline/briefs/*.md and the chapter entries in longform.toml.
proofreaderReads one chapter for mechanical correctness — grammar, spelling, punctuation, terminology consistency and style-guide compliance. Use per chapter after drafting. Writes findings to review/reports/; never edits prose.
seam-reviewerReviews one join between two adjacent units (the end of chapter N and the start of N+1) for continuity breaks, using only the seam file cut by `longform.py seams`. Use after a batch of adjacent units is drafted, one agent per seam, in parallel; again on spoken scripts for an audiobook. Writes review
spec-interviewerInterviews the user to fill only the gaps the writing team will actually need — the questions whose answers change the outline, the voice or the scope. Use after the brief has been recorded and before the spec is written. Writes spec/interview.md.
spec-writerSettles the recorded brief and the interview into the book spec — what the book is, who it is for, what it must not become, and its shape. Use after intake and before any planning. Writes spec/spec.md.
voice-auditorChecks the book for tone-of-voice drift against the style guide by sampling across chapters. Use after several chapters are drafted, and again before production. Writes review/reports/voice-*.md; never edits prose.
voice-designerWrites the book's style guide — the binding voice reference every writing and review agent reads. Use after the spec is settled and before the outline. Writes guides/style-guide.md.
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
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
Carta Investors plugin — skills for querying investor data, performance benchmarks, regulatory reporting, AGM deck generation, brand extraction, and more via the Carta MCP Server.
29 skills · hooks
Independent auditing for AI agents, open source. Claude discovers your setup, confirms the cost, and audits your agent against the one question other tools skip: is it doing the job it's supposed to do, given your business rules and org structure? Test any model (Anthropic, OpenAI, Gemini, Azure, Bedrock, …) graded by self, one independent judge, or a cross-vendor panel; each provider is billed to its own account via a key in your settings, never the command line. Results render as an interactive artifact (with a static-report fallback).
1 skill · hooks
Business metrics analysis, KPI tracking, financial reporting, and data-driven decision making
2 skills · 1 agent
Equity research tools: earnings analysis, initiating coverage reports, and research workflows
9 skills · 9 commands
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.