
story-structure
Use when planning or diagnosing a novel's macro plot structure. Trigger on: 'story structure', 'plot point', 'inciting event', 'midpoint', 'structure audit', 'structure map', 'signpost scene', 'mirror moment', or macro-structure analysis.
- Installs
- 287
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/rhavekost/author-toolkit --skill story-structure- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads story-structure automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Story Structure
A percentage-anchored landmark-beat skeleton (K.M. Weiland's 5 Secrets of Story Structure / Structuring Your Novel) overlaid with James Scott Bell's 14-signpost catalog (Super Structure) — plus two modes for using them: mapping a new story's structure before drafting, and auditing an existing manuscript against it.
Weiland's beats answer where a turning point should fall; Bell's signposts answer what psychological or emotional work that turning point needs to do. Together they give a placement skeleton with content diagnostics at each joint, not just a percentage ladder.
When to Use
This skill is for:
- ✅ Fiction manuscripts — novels, novellas, short stories
- ✅ Placing landmark beats (Inciting Event, Plot Points, Pinch Points, Midpoint, Climax) into a new outline before drafting
- ✅ Checking where beats actually land in an existing draft, by approximate percentage
- ✅ Checking whether a beat that's present is doing the psychological work it needs to (via Bell's signposts)
- ✅ Catching two specific, commonly-missed failure modes: Inciting Event/Key Event/First Plot Point confusion, and the Faux Climax trap
When NOT to Use
This skill is NOT for:
- ❌ Scene-level micro-structure (Goal/Conflict/Outcome, Scene/Sequel) — use
fiction-workshop'sreferences/developmental-editing.mdScene-Level section instead. - ❌ Character-arc mechanics (Want, Need, Wound, Lie) — use
fiction-workshop'sreferences/character-work.mdCore Four instead. This skill only notes which structural beat is where the Lie is tested (Third Plot Point) and resolved (Climax). - ❌ Narrative nonfiction structure — use
narrative-nonfiction's transformation-arc guidance instead; this skill's beats assume a plotted fiction conflict. - ❌ Prose-level pacing (sentence rhythm, word choice) — use
prose-mechanics.
Session Continuity
Structure placement is meant to persist in the project's Story Bible, not be re-derived each session.
- At session start: If a Story Bible exists, check its "Plot Foundation" section for an existing Structure Profile block (see
assets/structure-profile-template.md). Don't re-run Map on a story that already has one unless the author asks for a re-check. - When a beat is newly placed or moved: Hand the profile block back to the author to paste into the Story Bible yourself — this skill does not write to the Story Bible directly (see each mode's stop condition below).
The Landmark Beat Skeleton
Full skeleton, percentages, and the two named failure-mode diagnostics (Inciting/Key/First-Plot-Point confusion, Faux Climax): references/landmark-beats.md.
Bell's 14 Signposts
Full catalog, in Bell's own order, cross-referenced to the landmarks above where they overlay one: references/signposts.md.
The Two Modes
| Mode | Invocation | Question | Reference file |
|---|---|---|---|
| Map | "Map the structure for this story" | Where should each beat and signpost land, for a story not yet fully drafted? | references/structure-map.md |
| Audit | "Audit this manuscript's structure" | Where do beats actually land, and is each doing its job? | references/structure-audit.md |
Ordering guidance: Map is for pre-draft planning; Audit is for anything already written. They are not sequential stages of one session — run whichever mode matches the story's current stage.
Load only the reference file matching the currently invoked mode, plus landmark-beats.md and signposts.md (both modes need both). Do not preload mode files you're not running.
Workflow
- Identify the mode the author is invoking (see table above). If unclear, ask.
- Load
references/landmark-beats.mdandreferences/signposts.md, plus the mode file for the identified mode. - Run the mode's workflow exactly as documented in its reference file.
- Stop at the mode's documented stop condition (see Stopping Points below). Hand results back to the author.
- If a new or changed Structure Profile results, offer the
assets/structure-profile-template.mdblock for the author to paste into their Story Bible's Plot Foundation section — do not write it there yourself.
Integration with fiction-workshop
fiction-workshop/references/developmental-editing.md's Act-Level section links here for the deeper percentage-anchored skeleton and signpost content-checks.fiction-workshop/references/character-work.md's Arc Milestones section links here, noting Third Plot Point and Climax as the beats where the Lie is tested and resolved.assets/structure-profile-template.mdis designed to paste directly into the Story Bible's existing "Plot Foundation → Three-Act Structure" section (seefiction-workshop/assets/story-bible-template.md), adding finer beat percentages and signpost notes on top of the existing Act I/Midpoint/Act II-B/Act III placeholders.- This skill never restructures
fiction-workshop/assets/story-bible-template.md— it only adds an optional block.
Stopping Points
Each mode has a defined end. Stop at it. Do not auto-advance to the other mode, do not silently expand scope, do not write to the Story Bible without being asked.
| Mode | Stops when... | Then |
|---|---|---|
| Map | Structure Map block completed for all 11 landmarks | Hand back for author confirmation. Do not auto-write to Story Bible. |
| Audit | Flagged-beat report delivered (missing/mistimed/thin beats, Faux Climax check) | Stop. No auto-rewrite — author decides which flags to act on. |
Finding Format
Audit-mode output (missing/misplaced landmark beats, signpost gaps)
conforms to ../../references/finding-schema.json: audit =
"story-structure-audit", technique = the specific landmark or signpost
involved (e.g. "Weiland Midpoint" or "Bell Pinch Point 1"), severity,
location (chapter-level if no single line applies — use line 1 of the
chapter and describe the gap in issue), confidence: "judgment",
exemplar optional. Map-building mode (not diagnostic) is NOT in scope.
Common Mistakes
| Mistake | Fix |
|---|---|
| Treating the percentages as exact page counts | Weiland's own framing: aim for rough quarters, not surgical precision — a beat within a few points of its mark is fine |
| Conflating Inciting Event, Key Event, and First Plot Point into one beat | They can be three distinct scenes with three distinct jobs — see landmark-beats.md's callout |
| Declaring an early goal-achieved scene "the climax" | Check for Faux Climax — is there a bigger obstacle still standing between the protagonist and the true goal? |
| Running Audit on a story with no draft yet | Audit needs actual manuscript text to locate beats in — use Map instead for pre-draft planning |
| Checking only placement, not content | A beat can land at the right percentage and still be hollow — always run the matching Bell signpost content-check too |
Quick Reference Commands
| Need | Command |
|---|---|
| Plan a new story's structure | "Map the structure for this story" |
| Check an existing draft | "Audit this manuscript's structure" |
| Check one beat's placement | "Where does the Midpoint land in this draft?" |
| Check for a specific trap | "Check this manuscript for a Faux Climax" |
Files
references/landmark-beats.md- The 11-beat percentage skeleton, diagnostics, two failure-mode calloutsreferences/signposts.md- Bell's full 14-signpost catalog, cross-referenced to the landmarksreferences/structure-map.md- Map mode workflowreferences/structure-audit.md- Audit mode workflowassets/structure-profile-template.md- Story Bible block for a story's structure profile
FAQ
What does the story-structure skill do?
Use when planning or diagnosing a novel's macro plot structure. Trigger on: 'story structure', 'plot point', 'inciting event', 'midpoint', 'structure audit', 'structure map', 'signpost scene', 'mirror moment', or macro-structure analysis.
How do I install story-structure?
Run npx skills add https://github.com/rhavekost/author-toolkit --skill story-structure in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/story-structure/ (personal) or .claude/skills/story-structure/ (project).
Which AI agents can use story-structure?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is story-structure safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains story-structure?
It is published by rhavekost in rhavekost/author-toolkit. It has 287 recorded installs.
More from rhavekost/author-toolkit
fiction-workshop
rhavekost/author-toolkit
Use when writing or editing novels, short stories, or any fiction manuscript. Trigger on: 'write fiction', 'edit my novel', 'developmental edit', 'line edit', 'character voice', 'plot hole', 'brainstorm', or fiction writing tasks.
narrative-nonfiction
rhavekost/author-toolkit
Use when writing self-help books, memoirs, or prescriptive guides with story elements. Trigger on: 'self-help book', 'transformation arc', 'metaphor consistency', 'reader journey', 'exercise design', or narrative nonfiction projects.
avoid-ai-writing
rhavekost/author-toolkit
Open the skill to read its SKILL.md instructions.
prose-mechanics
rhavekost/author-toolkit
Open the skill to read its SKILL.md instructions.
character-archetypes
rhavekost/author-toolkit
Use when identifying, auditing, or tracking character archetypes in fiction. Trigger on: 'character archetype', 'archetype audit', 'what archetype is this character', 'archetype conformance', 'Hero's Journey character role', 'Jungian archetype', or archetype-based character analysis.
Popular code quality & workflow skills
grill-me
mattpocock/skills
A relentless interview to sharpen a plan or design.
improve-codebase-architecture
mattpocock/skills
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
handoff
mattpocock/skills
Compact the current conversation into a handoff document for another agent to pick up.
domain-modeling
mattpocock/skills
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.
codebase-design
mattpocock/skills
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
diagnosing-bugs
mattpocock/skills
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.