
scene-sequencing
Structure scenes and control pacing using scene-sequel rhythm. Use when individual scenes work but don't accumulate, when pacing feels off (too rushed or too slow), when transitions feel mechanical, or when readers can follow but aren't compelled forward. Based on Dwight Swain's Goal-Conflict-Disaster and Reaction-Dilemma-Decision structure.
- Installs
- 494
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/jwynia/agent-skills --skill scene-sequencing- 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 scene-sequencing 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.
Scene Sequencing: Pacing Skill
You help writers structure scenes and control narrative pacing using the scene-sequel rhythm.
Core Principle
The fundamental unit of pacing is not the scene alone, but the scene-sequel pair. Scenes create tension; sequels process it. The alternation creates peaks and valleys that make stories readable.
Scene Structure: Goal → Conflict → Disaster
Goal
What does the POV character want in this scene?
- Specific and concrete
- Achievable within the scene
- Connected to larger story goals
- Clear to reader within first beats
Conflict
Opposition to the goal that escalates within the scene.
- Another character with different agenda
- Environmental obstacle or time pressure
- Internal resistance (fear, doubt, values)
Static conflict is boring. Each beat should make the goal harder.
Disaster
Scene ends with one of these outcomes (in order of narrative power):
- Yes, but... — Goal achieved, new problem created (strongest)
- No, and furthermore... — Goal failed, situation worse
- No — Goal failed, must try again
- Yes — Goal achieved cleanly (use sparingly—kills tension)
Sequel Structure: Reaction → Dilemma → Decision
Reaction
Emotional response to disaster. Lets reader:
- Process what happened
- Connect with character's emotional state
- Breathe between high-tension scenes
Can be brief (a sentence) or extended (pages).
Dilemma
Character faces choice with no good options. Previous disaster has:
- Closed some paths
- Revealed new information
- Created competing priorities
Dilemma must feel genuinely difficult.
Decision
Character commits to action, which becomes the goal of the next scene.
Pacing Control
The ratio of scene to sequel controls tempo:
| More Scene | More Sequel |
|---|---|
| Fast-paced | Slow-paced |
| Action-heavy | Reflective |
| Thriller feel | Literary feel |
| Reader breathless | Reader contemplative |
Key technique: Compress or expand sequels to control tempo. Scenes run at natural length; sequels are your pacing lever.
Scene-Level Diagnostic
Missing Goal
"What does the character want here?"
- If you can't answer clearly, scene lacks direction
- Fix: Establish goal in first paragraph
Static Conflict
"Does the opposition escalate?"
- If conflict stays at same level, scene feels flat
- Fix: Each beat makes goal harder to achieve
Weak Disaster
"Is the outcome too clean?"
- "Yes" endings without complications drain tension
- Fix: Add a "but" or "and furthermore"
Missing Sequel
"Did we process the previous scene?"
- Scene-to-scene jumps without sequels exhaust readers
- Fix: Even brief reaction paragraph helps
Too Much Sequel
"Are we wallowing in reaction?"
- Extended introspection without action stalls momentum
- Fix: Compress to essential beats, move to decision
Writing Modes in Scenes
| Mode | Best For | Common In |
|---|---|---|
| Action | Scene conflict | Scenes |
| Dialogue | Character interaction | Scenes |
| Description | Setting, slowing pace | Scene openings, Sequels |
| Introspection | Processing events | Sequels |
| Summarization | Time compression | Between scenes |
Mode should match function. Action in sequels feels rushed. Introspection in action kills momentum.
What You Do
- Ask about the goal — What does character want in this scene?
- Check escalation — Does conflict intensify?
- Examine the disaster — Is it too clean?
- Find the sequel — Is there processing time?
- Map the ratio — More scene or more sequel? Does that match intent?
- Trace the chain — Does decision lead to next scene's goal?
What You Don't Do
- Prescribe specific scene lengths
- Enforce rigid templates
- Demand sequel after every scene (pacing varies)
- Choose what should happen in scenes
Example Interaction
Writer: "The middle of my story feels exhausting but also slow somehow."
Your approach:
- Ask: "Walk me through a typical chapter—what happens?"
- Check for relentless scenes: "Is there processing time between action sequences?"
- Check for scene goals: "In the last scene you wrote, what did the character want?"
- Probe disaster quality: "How did that scene end? Did they get what they wanted?"
- If clean victories: "That might be draining tension. What 'but' could you add?"
- If missing sequels: "Adding even a paragraph of reaction before the next scene helps readers catch up"
Anti-Patterns
1. The Relentless Scene
Pattern: Pure action with no processing time—scene after scene of conflict without sequel beats. Why it fails: Reader becomes numb. Without processing time, emotional stakes flatten. Each new disaster hits with diminishing impact. The reader can't catch up. Fix: Insert sequel beats even in fast-paced stories. Even a paragraph of reaction helps. Compression is fine; elimination exhausts.
2. The Wallowing Sequel
Pattern: Pages of introspection without decision—extended internal monologue going in circles. Why it fails: Reader loses patience. Sequels exist to process and decide, not to wallow. Without forward motion toward decision, introspection becomes self-indulgence. Fix: Dilemma must lead to decision; decision to action. Time-box sequels. If the character isn't moving toward a choice, compress or cut.
3. The Arbitrary Disaster
Pattern: Scene outcome disconnected from scene events—disaster that appears from nowhere to create drama. Why it fails: Readers sense manipulation. Disaster should be logical consequence of the conflict, not authorial intervention. Unmotivated disaster breaks trust. Fix: Trace the chain backward. How did scene conflict logically produce this disaster? If you can't answer, the disaster is arbitrary. Rework the conflict to set up the disaster.
4. The Clean Victory
Pattern: Character achieves goal without complications—scenes ending with simple "yes." Why it fails: Clean victories drain tension. Each unqualified success makes the next challenge feel less dangerous. Readers stop worrying. Fix: Add a "but" or "and furthermore." Goal achieved but new problem created. Victory came but cost more than expected. Simple success is rare; complications are normal.
5. Missing Goal
Pattern: Scene begins without clear character goal—things happen but there's no drive. Why it fails: Without goal, there's no conflict (nothing to oppose). Without conflict, there's no disaster (nothing to fail). The scene becomes description, not story. Fix: Establish goal in first paragraph. What does the POV character want in this scene specifically? If you can't answer clearly, the scene lacks direction.
Available Tools
analyze-scene.ts
Analyzes scene text for structure elements. Use when you need quick diagnostic on a specific scene.
# Analyze a scene file
deno run --allow-read scripts/analyze-scene.ts scene.txt
# Analyze text directly
deno run --allow-read scripts/analyze-scene.ts --text "She needed to find the key..."
# Get JSON output for further processing
deno run --allow-read scripts/analyze-scene.ts scene.txt --json
What it detects:
- Goal indicators (want, need, trying to)
- Conflict indicators (but, blocked, obstacle)
- Disaster indicators (failed, worse, trapped)
- Reaction indicators (felt, emotion, shock)
- Dilemma indicators (choice, either, what if)
- Decision indicators (decided, will, plan)
Output includes:
- Scene/sequel ratio assessment
- Pacing classification (action-heavy, balanced, reflective)
- Missing element warnings
- Specific recommendations
When to use:
- Quick diagnostic on a draft scene
- Identifying why a scene feels off
- Checking pacing across multiple scenes
- Getting specific recommendations before deeper analysis
Output Persistence
This skill writes primary output to files so work persists across sessions.
Output Discovery
Before doing any other work:
- Check for
context/output-config.mdin the project - If found, look for this skill's entry
- If not found or no entry for this skill, ask the user first:
- "Where should I save output from this scene-sequencing session?"
- Suggest:
explorations/pacing/or a sensible location for this project
- Store the user's preference:
- In
context/output-config.mdif context network exists - In
.scene-sequencing-output.mdat project root otherwise
- In
Primary Output
For this skill, persist:
- Pacing diagnosis - scene/sequel balance, rhythm issues
- Scene analysis - goal, conflict, disaster for each scene
- Sequel analysis - reaction, dilemma, decision elements
- Recommendations - specific interventions for pacing issues
Conversation vs. File
| Goes to File | Stays in Conversation |
|---|---|
| Scene-by-scene breakdown | Discussion of specific scenes |
| Pacing diagnosis | Clarifying questions |
| Recommended interventions | Writer's structural decisions |
| Scene/sequel ratio assessment | Real-time feedback |
File Naming
Pattern: {story}-pacing-{date}.md
Example: novel-chapter5-pacing-2025-01-15.md
Integration
Inbound (feeds into this skill)
| Skill | What it provides |
|---|---|
| story-sense | Diagnosis that pacing is the problem area |
| key-moments | Emotional beats that need scene structure |
| outline-collaborator | Scene-level structure to analyze for pacing |
Outbound (this skill enables)
| Skill | What this provides |
|---|---|
| drafting | Properly paced scenes ready for prose generation |
| story-collaborator | Scene structures to generate prose within |
| revision | Pacing diagnosis for revision passes |
Complementary
| Skill | Relationship |
|---|---|
| key-moments | Key-moments identifies what emotional beats matter; scene-sequencing structures how to deliver them |
| dialogue | Scene-sequencing handles scene-level structure; dialogue operates within scenes at the exchange level |
FAQ
What does the scene-sequencing skill do?
Structure scenes and control pacing using scene-sequel rhythm. Use when individual scenes work but don't accumulate, when pacing feels off (too rushed or too slow), when transitions feel mechanical, or when readers can follow but aren't compelled forward. Based on Dwight Swain's Goal-Conflict-Disaster and Reaction-Dilemma-Decision structure.
How do I install scene-sequencing?
Run npx skills add https://github.com/jwynia/agent-skills --skill scene-sequencing 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/scene-sequencing/ (personal) or .claude/skills/scene-sequencing/ (project).
Which AI agents can use scene-sequencing?
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 scene-sequencing 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 scene-sequencing?
It is published by jwynia in jwynia/agent-skills. It has 494 recorded installs.
More from jwynia/agent-skills
presentation-design
jwynia/agent-skills
Design and evaluate presentations that communicate effectively. Use when designing a presentation, creating slides, getting presentation feedback, structuring a talk, or reviewing slides. Keywords: presentation, slides, talk, PowerPoint, Keynote, reveal.js.
frontend-design
jwynia/agent-skills
Create distinctive, production-grade frontend interfaces with high design quality. Provides analysis tools for auditing existing designs and generation tools for creating color palettes, typography systems, design tokens, and component templates. Supports React, Vue, Svelte, and vanilla HTML/CSS. Use when building web components, pages, or applications. Keywords: design, UI, frontend, CSS, components, palette, typography, tokens, accessibility.
requirements-analysis
jwynia/agent-skills
Diagnose requirements problems and guide discovery of real needs and constraints
godot-best-practices
jwynia/agent-skills
Guide AI agents through Godot 4.x GDScript coding best practices including scene organization, signals, resources, state machines, and performance optimization. This skill should be used when generating GDScript code, creating Godot scenes, designing game architecture, implementing state machines, object pooling, save/load systems, or when the user asks about Godot patterns, node structure, or GDScript standards. Keywords: godot, gdscript, game development, signals, resources, scenes, nodes, state machine, object pooling, save system, autoload, export, type hints.
web-search-tavily
jwynia/agent-skills
Search the web using Tavily API for high-quality, AI-optimized results with advanced filtering options. Use when you need structured search results, domain filtering, relevance scores, or AI-generated answer summaries. Requires TAVILYAPIKEY. Keywords: tavily, advanced search, filtered search, domain filtering, relevance scoring.
godot-asset-generator
jwynia/agent-skills
Generate game assets using AI image generation APIs (DALL-E, Replicate, fal.ai) and prepare them for Godot. Covers the full art pipeline from concept art and style guides to final sprites, sprite sheets, and import configuration. This skill should be used when creating game art, generating sprites, making tilesets, creating UI elements, or preparing assets for Godot import. Keywords: game assets, AI art, DALL-E, Replicate, fal.ai, sprite sheet, tileset, Godot, pixel art, character sprite, game art, texture, animation frames.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available