novel-editor-flow
Assess fiction manuscripts and run a staged developmental-to-publication edit flow. Use when reading a novel draft or compiled manuscript to diagnose scene thinness, pacing, subtext, foreshadowing, emotional payoff, relationship arcs, or publication readiness, especially when turning a PDF or rough draft into an edited source, review packet, EPUB, and print-ready files.
Best use case
novel-editor-flow is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Assess fiction manuscripts and run a staged developmental-to-publication edit flow. Use when reading a novel draft or compiled manuscript to diagnose scene thinness, pacing, subtext, foreshadowing, emotional payoff, relationship arcs, or publication readiness, especially when turning a PDF or rough draft into an edited source, review packet, EPUB, and print-ready files.
Teams using novel-editor-flow should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/novel-editor-flow/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How novel-editor-flow Compares
| Feature / Agent | novel-editor-flow | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Assess fiction manuscripts and run a staged developmental-to-publication edit flow. Use when reading a novel draft or compiled manuscript to diagnose scene thinness, pacing, subtext, foreshadowing, emotional payoff, relationship arcs, or publication readiness, especially when turning a PDF or rough draft into an edited source, review packet, EPUB, and print-ready files.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Novel Editor Flow ## Overview Use this skill to move a novel from "promising draft" to "edited, staged, and package-ready" without mixing every kind of edit into one pass. Read enough of the manuscript to diagnose the real problem first, then pick one editing lane at a time from macro to micro. ## Workflow ### 1. Lock the edit contract Capture: - author and ownership - target outcome: private gift, beta read, KDP, wide release - source-of-truth file - current compiled formats - current blockers: weak scenes, pacing, line polish, formatting, cover, metadata If the text is not locked, default to: - `editorial passes first` - `packaging second` ### 2. Sample the book before prescribing edits Read at least: - opening hook - first world-expansion chapter - one middle chapter - one emotional relationship chapter - climax or final battle - ending or epilogue Return: - what works immediately - what feels thin or rushed - what repeats - what the book is already good at Do not prescribe a full rewrite from the opening chapters alone. For pass order and diagnosis labels, read: - `references/pass-order.md` ### 3. Diagnose the dominant problem Pick the single leading issue before editing: - `developmental` - `scene-depth` - `subtext/foreshadowing` - `line-level copy` - `format/package` If the manuscript is emotionally working but reads thin, prefer: - `scene-depth` first - `subtext/foreshadowing` second - `copy` third If the manuscript is structurally broken, do not hide that behind line edits. ### 4. Run one editorial lane at a time Allowed order: 1. developmental 2. scene-depth 3. subtext and foreshadowing 4. line and copy 5. ebook and print formatting 6. upload packet Never combine all six in one pass. ### 5. Use restrained scene-thickening When scenes feel thin: - add 1 to 3 concrete sensory details, not whole paragraphs of filler - give the viewpoint character a short reaction beat after major reveals - make environments feel inhabited - sharpen verbs before adding adjectives - expand only scenes that carry plot, intimacy, dread, wonder, or payoff Do not inflate the manuscript just to make it longer. ### 6. Seed subtext and foreshadowing quietly Use: - repeated image systems - small contradictions in dialogue or self-perception - loaded sensory motifs - emotional logic that points ahead before plot logic explains it Avoid: - prophecy dumping - obvious teaser lines that announce future events - late-book themes pasted into early chapters without natural fit For subtext rules and examples, read: - `references/subtext-foreshadowing.md` ### 7. Convert only after the text lane is clear Once the current editorial lane is done: - update the canonical source - regenerate the review DOCX - regenerate the EPUB - regenerate the print DOCX or PDF Prefer the repo's existing builder if one exists. For packaging expectations, align with the publication workflow already in use. ### 8. Run review lanes separately Use distinct checks for: - format - device - copy - reader-response Do not ask one review pass to answer everything. For the review split, read: - `references/review-lane-template.md` ### 9. Emit a compact decision note After each meaningful pass, record: - what lane was run - what changed - what was intentionally deferred - what the next lane should be If the session may pause, write a handoff note immediately. ## Output Contract When using this skill, return: - manuscript state - dominant editorial issue - recommended next pass - concrete files to edit - publication status ## References - `references/pass-order.md` - Read when deciding which editing lane comes next. - `references/subtext-foreshadowing.md` - Read when the book needs deeper setup without heavy rewrites. - `references/review-lane-template.md` - Read when splitting QA across copy, device, format, and reader-response lanes.
Related Skills
scbe-shopify-money-flow
Execute revenue-focused Shopify operations using SCBE and HYDRA command lanes with deterministic evidence, cross-talk dispatch, and workflow tuning. Use when the goal is to improve Shopify conversion, publish or refresh digital offers, coordinate monetization agents, or run pre-launch smoke checks before live store actions.
scbe-internet-workflow-synthesis
Synthesize and operate SCBE end-to-end internet workflows by discovering local and GitHub architecture templates, generating a baseline web pipeline profile, running ingestion and governance scans, and tuning system variables after the first run. Use when users ask to build, repair, or optimize internet workflow pipelines, workflow architecture maps, n8n or agent orchestration flows, or post-baseline threshold and concurrency tuning.
scbe-gh-powershell-workflow
Manage GitHub workflows and SCBE-AETHERMOORE repository operations from PowerShell 7 preview. Use for authenticated gh CLI actions, PR and branch workflows, CI triage, and SCBE code-aware repository inspections.
scbe-docker-workflow
Coordinate SCBE Docker workflows from build to runtime. Use for SCBE container commands, docker-compose service startup, health checks, and troubleshooting of image/build failures, port conflicts, and container startup issues in SCBE repos.
scbe-claude-crosstalk-workflow
Use when two AI lanes (Codex and Claude) work in parallel and need deterministic handoff packets with session IDs, lane-bus appends, and repairable delivery checks.
polyhedral-workflow-mesh
Coordinate sub-agent communication, relay workflows, n8n-style automations, triggers, and cross-surface handoffs as one governed mesh. Use when a goal spans multiple agents, browser and terminal surfaces, automation hooks, or periodic and aperiodic work loops that need packets, scoreboards, relays, and proof-backed checkpoints instead of loose AI-to-AI chat.
hf-publish-workflow
Automate Hugging Face model/dataset/space publishing from PowerShell with one-time auth, README card generation, `hf upload` commands, and optional `--create-pr` review flow. Use when users ask to log in to Hugging Face CLI, publish artifacts, add or update model/dataset/space cards, wire a reusable profile publish function (for example `scbe-hf-publish`), or troubleshoot common `hf` command usage.
development-flow-loop
Structured software delivery lifecycle for coding tasks that should move from planning to production with repeated quality gates. Use when building features, refactors, integrations, automations, or systems work where the expected flow is Plan, Architect, Evaluate, Implement, Test, Fix, Test, Improve, Test, Fix or Launch, Launch.
scbe-training-pair-authoring
Create prompt and response and metadata training pairs from SCBE documents, repair traces, terminal sessions, and operational workflows using the repository's canonical dataset contract and provenance rules.
scbe-spin-conversation-engine
Generate SFT training data via radial matrix conversation pivots with D&D-style combat research mode. Produces diverse, cost-effective training pairs with Sacred Tongue encoding, golden spiral problem distribution, and harmonic re-attunement.
scbe-research-training-bridge
Stage arXiv evidence and Obsidian markdown into source-grounded Hugging Face training bundles for research, review, and later SFT runs.
scbe-document-management
Consolidate overlapping docs, classify files by authority, and keep SCBE repo documents aligned with runtime truth. Use when the repo has drift between canonical docs, public docs, proposal notes, research branches, and generated evidence.