issac-story-engine
Write and revise scenes, chapters, and full novels in Issac's style using research-backed craft, canon-aware worldbuilding, and a balanced technical-plus-human narrative voice. Use when drafting fiction, sharpening scenes, adding interludes, preserving tone, or turning research and lore into readable prose.
Best use case
issac-story-engine is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Write and revise scenes, chapters, and full novels in Issac's style using research-backed craft, canon-aware worldbuilding, and a balanced technical-plus-human narrative voice. Use when drafting fiction, sharpening scenes, adding interludes, preserving tone, or turning research and lore into readable prose.
Teams using issac-story-engine 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/issac-story-engine/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How issac-story-engine Compares
| Feature / Agent | issac-story-engine | 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?
Write and revise scenes, chapters, and full novels in Issac's style using research-backed craft, canon-aware worldbuilding, and a balanced technical-plus-human narrative voice. Use when drafting fiction, sharpening scenes, adding interludes, preserving tone, or turning research and lore into readable prose.
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
# Issac Story Engine Use this skill when the user wants fiction written or revised in Issac's style, especially for Aethermoor, Pollyoneth, Spiralverse, or related projects where wonder, humor, emotional clarity, and technical structure must coexist. ## What This Skill Owns - scene drafting - chapter drafting - interlude writing - novel and arc architecture - voice preservation during revision - worldbuilding insertion without lore-dump drag - technical-to-mythic translation for system-heavy fantasy ## When To Use It Trigger this skill for requests like: - "write this scene" - "turn these notes into a chapter" - "make the novel feel more lived in" - "add interludes" - "keep the magic technical but fun" - "preserve Issac's voice" - "use research-backed writing practices" Do not use this skill for pure coding tasks, pure copyediting with no narrative judgment, or factual research that should stay outside the fiction lane until the user asks for prose. ## Core Workflow 1. Lock the unit of work. - Determine whether the request is a scene, chapter, interlude, outline, or full-novel problem. - Identify POV, desired change, emotional target, and output length. 2. Gather only the canon that matters. - For Aethermoor or Pollyoneth work, load `aethermoor-lore` first. - For current SCBE book work, prefer the live manuscript and project notes over older archive branches. - If the request depends on evidence or research claims, use the research lane before drafting. 3. Build a writing packet. - Use the 5 Ws for structure. - Add the 7-sense layer for atmosphere and meaning. - Define one emotional beat, one technical beat, one world detail, and one warmth or humor beat. 4. Draft the minimum correct prose. - Start with the cleanest version that satisfies the brief. - Keep exposition pressure low. - Let character, motion, and setting carry the information load. 5. Run the revision loop. - Voice pass - Clarity pass - Structure pass - Sensory pass - Compression pass 6. Mirror useful notes. - If the user is actively using Obsidian or project notes, leave a compact drafting artifact or canon note instead of burying decisions in chat. ## Style Rules - Lead with human truth before system explanation. - Let characters be funny, irritated, tender, wrong, and alive. - Keep the prose readable even when the idea is technical. - Treat magic as lived reality for natives. - Let outsider or systems-minded characters notice structure without flattening the world. - Prefer precise lines over swollen paragraphs. - End major arcs on durable emotional truth, not abstract cosmology alone. ## Issac Voice Baseline - witty - poetic without trying too hard - irreverent in pressure moments - casually philosophical - emotionally sincere - technical when useful, not performative If the work starts sounding generic, over-luxurious, or like a design document, pull it back toward voice, scene, and people. ## Writing Modes ### Scene Mode Use when a single interaction, reveal, conflict, or emotional turn must land cleanly. Read: - `references/scene-packet.md` - `references/issac-style.md` ### Chapter Mode Use when the task needs pacing, chapter shape, interludes, and end-beat control. Read: - `references/chapter-and-interlude.md` - `references/scene-packet.md` ### Novel Mode Use when the user is planning long arcs, balancing cast density, or repairing structural drift. Read: - `references/novel-architecture.md` - `references/chapter-and-interlude.md` ### Research-Backed Mode Use when the user explicitly asks for research-backed practice, evidence, or theory support. Read: - `references/research-lane.md` If the request is about Aethermoor or related canon, also load `aethermoor-lore`. ## Support Skill Routing Use these support skills deliberately: - `aethermoor-lore` Use for canon, characters, locations, magic systems, and continuity framing. - `aetherbrowser-arxiv-nav` Use when the user explicitly wants research-backed methods or current paper evidence. Prefer abstracts, titles, authors, dates, and concise takeaways. - `development-flow-loop` Use the same loop for writing work: Plan -> Architect -> Evaluate -> Implement -> Test -> Fix -> Test -> Improve -> Test -> Deliver. - `skill-synthesis` Use when the task spans lore, research, writing, notes, and deployment artifacts in one pass. - `scbe-claude-crosstalk-workflow` Use only when Codex and Claude are both active and need deterministic handoff packets. ## Project-Specific Rule For The Six Tongues Protocol When writing `The Six Tongues Protocol`: - the book remains Marcus's isekai - the world remains real to its natives - Marcus may internally translate some structures into systems language - Clay remains a foundational moral proof - Everweave history should deepen the world, not replace the current story For that project, also use the Obsidian notes in: `C:\Users\issda\Documents\Avalon Files\SCBE Research\Writing\The Six Tongues Protocol` ## Deliverable Standard A good output from this skill should usually contain: - clear scene or chapter movement - character voice separation - sensory grounding - at least one memorable line - technical clarity where relevant - no unnecessary lore bloat ## Resources - `references/issac-style.md` Voice, theme, and hard canon tendencies. - `references/scene-packet.md` Build scenes from structure, senses, and change. - `references/chapter-and-interlude.md` Chapter pacing, interlude logic, and end-beat design. - `references/novel-architecture.md` Long-form planning and repair guidance. - `references/research-lane.md` How to use research without drowning the prose.
Related Skills
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-system-engine
Coordinate SCBE-AETHERMOORE math, automation, and service connectors so multi-agent systems can execute work end-to-end. Use when tasks require SCBE dimensional validation, AI-to-AI workflows, browser automation planning, Hugging Face or GitHub/Linear/Notion/Zapier integration, or self-improving skill updates.
scbe-story-canon-writer
Produce publishable narrative chapters that stay canon-aligned with SCBE system mappings, tokenizer concepts, and world rules. Use when drafting or revising story chapters, interludes, codex entries, or litRPG-style status overlays tied to technical systems.
scbe-9d-state-engine
Construct and evolve the 9-dimensional state vector xi = [c(t), tau(t), eta(t), q(t)] that drives SCBE-AETHERMOORE governance decisions. Use when building context vectors, evolving time/entropy/quantum dimensions, or preparing state for the governance gate.
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-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.
scbe-colab-bridge
Control Google Colab notebooks from Claude Code via Chrome extension. Execute cells, run terminal commands, read outputs, and manage GPU compute remotely.
scbe-claim-to-code-evidence
Map SCBE Notion technical claims, proof pages, and patent-facing architecture notes to concrete repository evidence such as code paths, tests, demos, and docs. Use when Codex needs to build a due-diligence packet, claim-to-code audit, implementation crosswalk, patent support note, or proof summary from local Notion exports and repo artifacts.
scbe-autonomous-worker-productizer
Turn SCBE automation, autonomous worker, and revenue-system notes into concrete offers, workflow packs, pilot plans, or SaaS-facing product packets. Use when Codex needs to package Notion automation pages into buyer-ready offerings, n8n/Zapier workflow designs, flock-backed worker systems, or implementation roadmaps tied to existing SCBE repo surfaces.
multi-agent-cloud-offload
Deterministically sort, bundle, verify, and offshore local files through multiple AI/model lanes while capturing training rows and method evidence. Use when Codex needs to inventory folders, batch-process files, upload them to cloud targets such as rclone-backed Google Drive, Hugging Face, or GitHub, and only delete sources after the configured number of verified targets succeed.
long-form-work-orchestrator
Run long-form engineering work in checkpointed phases with deterministic artifacts, resilience handling, and end-of-run reliability reporting.