Agent skill

Novel Revision

by jwynia in jwynia/agent-skills

Manage multi-level novel revisions while preventing cascade problems.

MITAuto-check passedWriting & Content

Install Novel Revision

skills CLI
$ npx skills add jwynia/agent-skills --skill novel-revision -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jwynia/agent-skills novel-revision --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jwynia/agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/creative/fiction/structure/novel-revision .claude/skills/novel-revision && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
novel-revision
GitHub stars
170
Token cost
~3.6k tokens
SKILL.md length
1,648 words
Files
1
Skills in repo
111
Repo updated
First seen
Licence
MIT

At a glance

Manage multi-level novel revisions while preventing cascade problems.

  • Works in 11 steps: Identify the Change Level → Map Forward Consequences → Create Monitoring Criteria → …
  • Changes at one level break things at others
  • SKILL.md covers Core Principle: Cascade…, The Three Levels, Pre-Change Analysis Protocol and Change Implementation Workflow, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Novel Revision is an agent skill from jwynia/agent-skills. Manage multi-level novel revisions while preventing cascade problems. Use when editing novels, when changes at one level break things at others, when you need systematic change management for long-form fiction, or when revisions keep creating new problems.

Its SKILL.md is about 3.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Writing & Content, covering Creative writing and fiction. The licence is MIT.

When your agent uses it

  • Changes at one level break things at others
  • You need systematic change management for long-form fiction
  • Revisions keep creating new problems

Example prompts

  • “/novel-revision”

Workflow steps

11 steps, taken from the step headings in SKILL.md.

  1. Identify the Change Level
  2. Map Forward Consequences
  3. Create Monitoring Criteria
  4. Impact Assessment
  5. Controlled Implementation
  6. Ripple Management
  7. Unassessed Changes
  8. Warning Sign Blindness
  9. Cascade Debt
  10. Sunk Cost Persistence
  11. Activity Confusion

What it can do on your machine

Read from SKILL.md and the folder at commit e02ec7e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Novel Revision loads about 3.6k tokens when it runs. Until then it costs about 68 tokens; SKILL.md has 1,648 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~68
When it runs · the whole SKILL.md, loaded when a task matches
~3.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jwynia/agent-skills at commit e02ec7e, republished under its MIT licence (© jwynia). 1,648 words, ~3,624 tokens.

Download SKILL.mdSave it as .claude/skills/novel-revision/SKILL.md (or your agent's skills folder).
name
novel-revision
description
Manage multi-level novel revisions while preventing cascade problems. Use when editing novels, when changes at one level break things at others, when you need systematic change management for long-form fiction, or when revisions keep creating new problems.
license
MIT
metadata.author
jwynia
metadata.version
1.0
metadata.type
diagnostic
metadata.mode
diagnostic+assistive
metadata.domain
fiction

Novel Revision: Multi-Level Change Management Skill

You help writers manage revisions across multiple levels of abstraction while preventing unintended consequences from cascading through the narrative. Your role is to implement systematic change management that maintains story coherence.

Core Principle: Cascade Awareness

Any change at one level potentially affects all other levels. Changes propagate both upward (prose discoveries revealing structural problems) and downward (structural changes requiring prose rewrites).

The Three Levels

Every novel operates simultaneously across these levels:

Thematic/Conceptual Level
  • Core themes and meaning
  • Character growth arcs
  • Symbolic elements and motifs
  • Overall message and emotional journey
Structural Level
  • Plot beats and story architecture
  • Scene sequences and chapter organization
  • Pacing and rhythm
  • Tension patterns and resolution cycles
Manuscript Level
  • Actual prose and dialogue
  • Descriptive passages
  • Voice and style consistency
  • Line-level craft elements

Pre-Change Analysis Protocol

Before implementing any revision:

1. Identify the Change Level
  • Conceptual: Changing themes, character motivations, meaning
  • Structural: Altering plot beats, scene order, pacing
  • Prose: Improving language, dialogue, descriptions
2. Map Forward Consequences

For each proposed change, document:

  • Immediate (1-2 chapters): What must change next?
  • Medium-term (3-5 chapters): What implications ripple forward?
  • Story-wide: How might this affect ending or major plot points?
3. Create Monitoring Criteria

Define warning signs that indicate problems:

  • Character behavior inconsistencies
  • Plot logic gaps
  • Pacing anomalies
  • Thematic contradictions

Change Implementation Workflow

Phase 1: Impact Assessment
  1. Document current state: Snapshot relevant story elements
  2. Project consequences: Write expected chain of implications
  3. Set checkpoints: Identify where you'll evaluate
  4. Define rollback triggers: Clear criteria for aborting
Phase 2: Controlled Implementation
  1. Make minimal viable change: Smallest version that tests hypothesis
  2. Monitor immediately: Check for local coherence problems
  3. Document observations: Note unexpected effects
  4. Evaluate against projections: Compare actual to predicted
Phase 3: Ripple Management
  1. Identify required updates: What else must change?
  2. Prioritize cascade tasks: Order by importance and dependency
  3. Track completion: Explicit lists of updated vs. pending
  4. Validate consistency: Check updates work together

Revision Types and Protocols

Character Development Revisions

Triggers: Character feels flat, motivations unclear, arc incomplete

Protocol:

  1. Map current character state across all chapters
  2. Identify scenes where growth should be visible
  3. Project how changes affect dialogue/actions later
  4. Check consistency with other characters' responses

Monitoring: Does behavior remain believable? Do others respond appropriately?

Plot Structure Revisions

Triggers: Pacing off, events disconnected, climax lacks impact

Protocol:

  1. Create timeline of current plot beats
  2. Identify specific structural elements to change
  3. Map how timing changes affect tension
  4. Check causality chains still hold

Monitoring: Does tension build? Do plot points feel connected and inevitable?

Thematic Revisions

Triggers: Theme heavy-handed, unclear, or inconsistent

Protocol:

  1. Audit current thematic elements throughout manuscript
  2. Identify opportunities for subtler integration
  3. Check character actions support thematic development
  4. Ensure climax/resolution reinforce themes

Monitoring: Do themes emerge naturally? Does resolution feel thematically satisfying?

Early Warning Signs

Warning SignWhat It Indicates
Character acts against personality without developmentConsistency break
Events don't follow logicallyPlot logic gap
Scenes feel rushed or drag unexpectedlyPacing anomaly
Story events undermine themesThematic drift

Intervention Protocols

When to Roll Back
  • Multiple warning signs within 2 chapters
  • Fundamental character or plot logic breaks
  • Change creates more problems than it solves
  • Cascade tasks become overwhelming
Rollback Procedure
  1. Identify rollback point: Return to last stable state
  2. Document lessons: What went wrong and why
  3. Revise approach: Alternative strategy based on learning
  4. Add safeguards: Monitoring to prevent recurrence
When to Push Forward
  • Problems are localized and manageable
  • Benefits clearly outweigh complications
  • Cascade tasks are well-defined
  • Core story logic remains intact

Change Record Template

markdown
# Revision: [Brief Description]

## Change Type
- [ ] Conceptual  - [ ] Structural  - [ ] Prose

## Rationale
[Why this change is needed]

## Predicted Consequences
- Immediate (1-2 chapters):
- Medium-term (3-5 chapters):
- Story-wide:

## Monitoring Criteria
- Warning sign 1:
- Warning sign 2:
- Success indicator 1:
- Success indicator 2:

## Implementation Status
- [ ] Initial change complete
- [ ] Cascade tasks identified
- [ ] Cascade tasks completed
- [ ] Validation complete

## Outcome Assessment
[Complete after implementation]

Multi-Agent Collaboration

When working with multiple agents on revision:

Role Boundaries
  • Structure Agent: Plot architecture and pacing
  • Character Agent: Development and consistency
  • Prose Agent: Language and voice
  • Continuity Agent: Cross-level consistency
Communication Protocols
  • Share intentions before implementation
  • Report unexpected discoveries immediately
  • Flag potential cross-level implications
  • Coordinate cascade task assignments
Conflict Resolution
  1. Document what elements are in tension
  2. Escalate to human for creative resolution
  3. Explore alternative approaches
  4. Prioritize based on story goals

Best Practices

Start Small
  • Incremental changes over major overhauls
  • Test one element at a time
  • Build confidence through small wins
Maintain Perspective
  • Remember overall story goals
  • Don't lose sight of what works
  • Balance perfection with completion
Document Everything
  • Capture insights during revision
  • Record what works and doesn't
  • Build knowledge for future projects
Trust the Process
  • Allow time for changes to settle
  • Don't rush to fix every minor issue
  • Some problems resolve as story develops

Diagnostic Questions

When revision feels stuck:

  1. What level is this change really at?
  2. Have I mapped forward consequences?
  3. What would tell me this is working?
  4. What would tell me to roll back?
  5. Am I making minimal viable change?
  6. What cascade tasks does this create?
  7. Am I tracking completions explicitly?

Output Persistence

Output Discovery
  1. Check for context/output-config.md in the project
  2. If found, look for this skill's entry
  3. If not found, ask user: "Where should I save revision tracking?"
  4. Suggest: revision/ or explorations/revision/
Primary Output
  • Change records - Using template for each significant change
  • Cascade task lists - Secondary edits required by changes
  • Monitoring log - Warning signs observed and addressed
  • Rollback points - Snapshots of stable states
File Naming

Pattern: {novel-name}-revision-{date}.md

Verification (Oracle)

What This Skill Can Verify
  • Impact assessment complete - Were consequences mapped? (High confidence)
  • Cascade tracking - Are secondary tasks documented? (High confidence)
  • Monitoring active - Are warning signs being watched? (Medium confidence)
What Requires Human Judgment
  • Change necessity - Is this revision actually needed?
  • Rollback decision - When problems outweigh benefits
  • Creative resolution - When changes create conflicts
Oracle Limitations
  • Cannot assess whether changes improve the story
  • Cannot predict creative success of revision approach

Feedback Loop

Session Persistence
  • Output location: See context/output-config.md
  • What to save: Change records, cascade tasks, monitoring log
  • Naming pattern: {novel-name}-revision-{date}.md
Cross-Session Learning
  • Check for prior revision work on this novel
  • Build on lessons from previous change attempts
  • Failed revisions inform anti-patterns

Design Constraints

Show full SKILL.md (660 more words)Show less
This Skill Assumes
  • Novel draft exists to revise
  • Changes potentially affect multiple levels
  • Writer wants systematic change management
This Skill Does Not Handle
  • Problem diagnosis - Route to: story-sense
  • Scene-level revision - Route to: revision
  • Prose-level editing - Route to: prose-style
Degradation Signals
  • Unassessed changes (no consequence mapping)
  • Warning sign blindness (ignoring red flags)
  • Cascade debt (untracked secondary tasks)

Reasoning Requirements

Standard Reasoning
  • Single change assessment
  • Basic cascade identification
  • Simple monitoring setup
Extended Reasoning (ultrathink)
  • Multi-change coordination - [Why: changes interact across levels]
  • Full cascade analysis - [Why: secondary effects compound]
  • Rollback planning - [Why: complex reversions need strategy]

Trigger phrases: "coordinate all revisions", "map full cascade", "plan the rollback"

Execution Strategy

Sequential (Default)
  • Impact assessment before implementation
  • Implementation before cascade tracking
  • Cascade before validation
Parallelizable
  • Assessing multiple independent changes
  • Tracking cascade tasks across different sections
Subagent Candidates
TaskAgent TypeWhen to Spawn
Consistency checkExploreWhen verifying changes across manuscript
Character trackinggeneral-purposeWhen monitoring character consistency

Context Management

Approximate Token Footprint
  • Skill base: ~3.5k tokens (levels + protocols + workflow)
  • With template: ~4.5k tokens
  • With best practices: ~5k tokens
Context Optimization
  • Focus on current revision type and protocol
  • Template is reference for documentation
  • Multi-agent section is optional
When Context Gets Tight
  • Prioritize: Current revision protocol, active change record
  • Defer: Full protocol list, multi-agent coordination
  • Drop: Best practices, diagnostic questions

Anti-Patterns

1. Unassessed Changes

Pattern: Making revisions without first analyzing what else might be affected—jumping straight to implementation. Why it fails: Changes cascade. A character motivation change affects every scene where that character makes choices. Unassessed changes create problems you discover pages later, often after you've built on broken foundation. Fix: Before every significant change, explicitly document: what must change as a result? What might break? Set monitoring criteria before implementation, not after.

2. Warning Sign Blindness

Pattern: Noticing that something feels off after a change but pushing forward anyway, trusting it will resolve itself. Why it fails: Early warnings are cheap signals about expensive problems. Characters acting against established personality, plot logic gaps, pacing anomalies—these compound. The deeper you go, the more expensive the fix. Fix: Treat early warnings as actionable information. Stop, evaluate, decide to either fix now or explicitly accept the risk. Don't let "I'll fix it later" accumulate.

3. Cascade Debt

Pattern: Making changes without tracking the secondary edits they require—accumulating a backlog of unaddressed implications. Why it fails: Untracked cascade tasks become invisible technical debt. You think you made one change; you actually made one change and created ten unfixed inconsistencies. Fix: Maintain explicit cascade task lists. When a change requires follow-up edits, write them down immediately. Track completion. Don't move on until cascade is resolved.

4. Sunk Cost Persistence

Pattern: Continuing with a problematic change because you've already invested significant effort, even when warning signs multiply. Why it fails: The effort is gone either way. Continuing down a broken path just adds more lost effort. Multiple warning signs within two chapters usually indicate fundamental problems. Fix: Define rollback triggers before implementation. When triggers fire, roll back. Document what you learned. The insight is valuable even if the change wasn't.

5. Activity Confusion

Pattern: Measuring progress by pages revised rather than by improvement achieved—conflating work with results. Why it fails: You can revise extensively without making the story better. In fact, you can revise extensively and make it worse. Activity that doesn't serve story goals is waste. Fix: Define what "better" means for each revision pass. Measure against that goal, not against pages touched. Sometimes the best revision is no revision.

Integration

Inbound (feeds into this skill)
SkillWhat it provides
story-senseDiagnosis of what needs revision
character-arcCharacter consistency requirements
scene-sequencingPacing and structure requirements
Outbound (this skill enables)
SkillWhat this provides
prose-styleManuscript-level changes with cascade awareness
revisionScene-level work with multi-level coordination
(completed novel)Final product with maintained coherence
Complementary
SkillRelationship
story-senseStory-sense diagnoses problems; novel-revision manages the fix without creating new problems
revisionRevision handles sentence and scene level; novel-revision coordinates across the whole manuscript

© jwynia, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/creative/fiction/structure/novel-revision of jwynia/agent-skills.

Open the folder on GitHubat commit e02ec7e

Compare with similar skills

Novel Revision next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Novel Revision compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Novel Revision this skilljwynia/agent-skills170—~3.6kAutomated safety check: PassMIT
Story Multi-Perspective Reviewzenstory-ai/oh-story-claudecode7.4k3 repos~3kAutomated safety check: PassMIT
Short Web Fiction Trend Scanzenstory-ai/oh-story-claudecode7.4k2 repos~1.2kAutomated safety check: PassMIT
InkOS Creative HarnessNarcooo/inkos10k1 repos~1.1kAutomated safety check: PassAGPL-3.0
Novel Arteternityspring/shuohao-skills4.3k—~1.1kAutomated safety check: NotesApache-2.0
SepiaNanako0129/sepia3.1k—~3.6kAutomated safety check: PassMIT

Similar skills

  • Story Multi-Perspective Review

    zenstory-ai/oh-story-claudecode

    Reviews Chinese web-novel text with several reviewer agents in parallel, falling back to a single-agent pass, and reports structure, character, prose and setting problems with fixes.

    7.4k GitHub starsUsed in 3 repos~3k tokens
    Writing & ContentAuto-check passed
  • Short Web Fiction Trend Scan

    zenstory-ai/oh-story-claudecode

    Scans popular short web-fiction rankings on Chinese platforms such as Dianzhong and Heiyan to surface trending emotional hooks, themes and topic candidates with an expiry warning.

    7.4k GitHub starsUsed in 2 repos~1.2k tokens
    Writing & ContentAuto-check passed
  • Drives long-form fiction, scripts, storyboards, interactive films and long-document translation through InkOS, with every change made by a typed action.

    10k GitHub starsUsed in 1 repo~1.1k tokens
    Writing & ContentAuto-check passed
  • Novel Art

    eternityspring/shuohao-skills

    给 AI 短剧出美术设定集(场景 + 叙事道具):场景的设计意图、一致性锚点、光照时段变体、 空景提示词;道具的戏剧功能、状态变体、尺度参照、白底无手提示词。

    4.3k GitHub stars~1.1k tokensUpdated 3 days ago
    Writing & ContentAuto-check: notes
  • Sepia

    Nanako0129/sepia

    Make AI-generated writing read as human-written, in fiction and in professional prose.

    3.1k GitHub stars~3.6k tokensUpdated 2 days ago
    Writing & ContentAuto-check passed
  • Story Toolbox Router

    zenstory-ai/oh-story-claudecode

    Routes a Chinese web-novel writing request to the matching tool in a 13-skill toolbox, covers author habit memory, and can launch a local dashboard for browsing a project.

    7.4k GitHub stars~1.7k tokensUpdated yesterday
    Writing & ContentAuto-check passed

More from jwynia/agent-skills

All 111 skills in this repo
  • Devcontainer

    jwynia/agent-skills

    Diagnose devcontainer configuration problems and guide development environment setup.

    170 GitHub stars~1.2k tokensUpdated 7 mo ago
    Auto-check: notes
  • Frontend Design

    jwynia/agent-skills

    Create distinctive, production-grade frontend interfaces with high design quality.

    170 GitHub stars~3.2k tokensUpdated 7 mo ago
    Auto-check passed
  • Gitea Workflow

    jwynia/agent-skills

    Orchestrate agile development workflows for Gitea repositories using the tea CLI.

    170 GitHub stars~3.8k tokensUpdated 7 mo ago
    Auto-check passed
  • Godot Asset Generator

    jwynia/agent-skills

    Generate game assets using AI image generation APIs (DALL-E, Replicate, fal.ai) and prepare them for Godot.

    170 GitHub stars~3.8k tokensUpdated 7 mo ago
    Auto-check passed
  • Mastra Hono

    jwynia/agent-skills

    Develop AI agents, tools, and workflows with Mastra v1 Beta and Hono servers.

    170 GitHub stars~2.9k tokensUpdated 7 mo ago
    Auto-check passed
  • PPTX Generator

    jwynia/agent-skills

    Create and manipulate PowerPoint PPTX files programmatically.

    170 GitHub stars~3.1k tokensUpdated 7 mo ago
    Auto-check passed

Questions about Novel Revision

What does Novel Revision do?

Manage multi-level novel revisions while preventing cascade problems. Novel Revision is an agent skill from jwynia/agent-skills. Manage multi-level novel revisions while preventing cascade problems.

When should I use Novel Revision?

Novel Revision fits situations like: changes at one level break things at others; you need systematic change management for long-form fiction; revisions keep creating new problems.

How do I install Novel Revision in Claude Code?

Run `npx skills add jwynia/agent-skills --skill novel-revision -a claude-code`. Or copy the skill folder (skills/creative/fiction/structure/novel-revision in jwynia/agent-skills) into .claude/skills/novel-revision in your project. Claude Code loads it when a task matches its description.

How do I install Novel Revision in Codex?

Run `npx skills add jwynia/agent-skills --skill novel-revision -a codex`. Or copy the skill folder (skills/creative/fiction/structure/novel-revision in jwynia/agent-skills) into .agents/skills/novel-revision in your project. Codex loads it when a task matches its description.

Can I use Novel Revision in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jwynia/agent-skills --skill novel-revision -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/novel-revision, .gemini/skills/novel-revision, .github/skills/novel-revision and .opencode/skills/novel-revision in your project.

What does Novel Revision need to run?

SKILL.md names no scripts, command-line tools or credentials: Novel Revision is instructions for the agent only.

Does Novel Revision access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Novel Revision safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Novel Revision use?

Novel Revision is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Novel Revision use?

About 3.6k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Novel Revision?

Skills that share tags, products or a category with Novel Revision: Story Multi-Perspective Review (zenstory-ai/oh-story-claudecode, 7.4k stars), Short Web Fiction Trend Scan (zenstory-ai/oh-story-claudecode, 7.4k stars), InkOS Creative Harness (Narcooo/inkos, 10k stars) and Novel Art (eternityspring/shuohao-skills, 4.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Novel Revision?

jwynia (a GitHub user) maintains it in jwynia/agent-skills, which has 170 GitHub stars. The repository holds 111 skills in this directory. The repository was last updated on February 24, 2026.

Source: jwynia/agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.