creative-writing-craft
Skill17 starsChanged 5 months agoApache-2.0Archived repositoryView on GitHub
Craft compelling fiction and creative nonfiction with attention to structure, voice, prose style, and revision. Supports short stories, novel chapters, essays, and hybrid forms. Triggers on creative writing, fiction writing, story craft, prose style, or literary technique requests.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- haowjy/creative-writing-skillstheir own version, first seen Nov 15, 2026
- FiredMosquito831/my-writing-companiontheir own version, first seen Nov 1, 2026
- Abdullokh-N/proza-rutheir own version, first seen Aug 27, 2026
Other versions4 projects use a version of this.
Word for word · 1
- organvm-iv-taxis/a-i--skills★ 17100% same
Edited · 0
None found.
Wrote their own version · 3
- haowjy/creative-writing-skills★ 590same name
- FiredMosquito831/my-writing-companion★ 2same name
- Abdullokh-N/proza-ru★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository170 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- algorithmic-artSkill
- audio-engineering-patternsSkill
- canvas-designSkill
- generative-art-algorithmsSkill
- generative-art-deploymentSkill
- generative-music-composerSkill
- interactive-theatre-designerSkill
- modular-synthesis-philosophySkill
- movement-notation-systemsSkill
- narratological-algorithmsSkill
- natural-center-extractionSkill
- react-three-fiber-patternsSkill
- reality-tv-narrative-analyzerSkill
- script-analysis-dramaturgicalSkill
- theme-factorySkill
- three-js-interactive-builderSkill
- corpus-persona-extractionSkill
- data-ingestion-pipelineSkill
- data-pipeline-architectSkill
- data-storytelling-analystSkill
- market-gap-analysisSkill
- ml-experiment-trackerSkill
- prompt-atom-formalizationSkill
- sql-query-optimizerSkill
- systemic-product-analystSkill
- time-series-analystSkill
- accessibility-patternsSkill
- agent-testing-patternsSkill
- api-design-patternsSkill
- artifacts-builderSkill
- backend-implementation-patternsSkill
- browser-extension-patternsSkill
- cli-tool-designSkill
- code-refactoring-patternsSkill
- code-review-checklistSkill
- coding-standards-enforcerSkill
- community-platform-patternsSkill
- configuration-managementSkill
- continuous-learning-agentSkill
- data-backup-patternsSkill
- database-migration-patternsSkill
- deployment-cicdSkill
- docker-containerizationSkill
- dotfile-systems-architectSkill
- error-handling-logging-patternsSkill
- fastapi-patternsSkill
- feature-workflow-orchestratorSkill
- frontend-design-systemsSkill
- fullstack-starter-packSkill
- gcp-resource-optimizerSkill
- htmx-interaction-patternsSkill
- iterative-code-explorationSkill
- json-schema-designSkill
- mcp-builderSkill
- mcp-server-orchestratorSkill
- mobile-platform-architectSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 36
Stakes: if they fail
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Creative Writing Craft
Transform ideas into compelling prose.
Story Architecture
Three-Act Structure
ACT I (25%) │ ACT II (50%) │ ACT III (25%)
Setup │ Confrontation │ Resolution
────────────────┼────────────────────────────┼─────────────────
Hook │ Rising Action │ Climax
Inciting Event │ Midpoint Shift │ Falling Action
First Plot Point│ Second Plot Point │ ResolutionScene Structure
Goal → Conflict → Disaster → Reaction → Dilemma → DecisionEach scene should have:
- POV character with a clear goal
- Obstacle preventing the goal
- Stakes if they fail
- Outcome (usually not what they wanted)
Story Beats
| Beat | Percentage | Function |
| Opening Image | 0-1% | Establish world/tone |
| Theme Stated | ~5% | Hint at meaning |
| Setup | 1-10% | Ordinary world |
| Catalyst | ~10% | Inciting incident |
| Debate | 10-20% | Hesitation |
| Break into Two | ~25% | Commits to journey |
| B Story | ~30% | Subplot, often thematic |
| Fun and Games | 30-50% | Promise of premise |
| Midpoint | ~50% | False victory/defeat, stakes rise |
| Bad Guys Close In | 50-75% | Increasing pressure |
| All Is Lost | ~75% | Lowest point |
| Dark Night of Soul | 75-80% | Despair |
| Break into Three | ~80% | New plan/revelation |
| Finale | 80-99% | Climax, resolution |
| Final Image | 99-100% | Echo opening, show change |
Character Development
Character Dimensions
| Layer | Question | Example |
| Surface | What do they show? | Confident, funny |
| Behavior | What do they do? | Helps strangers, avoids calls |
| Motive | What do they want? | Success, approval |
| Need | What do they actually need? | Self-acceptance |
| Ghost | What wound drives them? | Abandoned as child |
Character Arc Pattern
Lie they believe → Want (conscious goal) → Need (unconscious)
↓ ↓ ↓
Truth they learn ← Confrontation ← Cost of lieVoice Development
To develop distinct character voice, vary:
- Sentence length and complexity
- Vocabulary level and specificity
- Speech patterns (fragments, run-ons)
- Topics they notice/mention
- What they omit or avoid
- Metaphor domains (what do they compare things to?)
Point of View
First Person
I walked into the room and immediately regretted it.Pros: Intimacy, voice, unreliable narrator potential Cons: Limited perspective, "I" fatigue
Third Person Limited
She walked into the room and immediately regretted it.Pros: Flexibility, intimacy without "I" Cons: Can drift into head-hopping
Third Person Omniscient
Sarah walked into the room, unaware that three people
were already watching her from the shadows.Pros: God's-eye view, irony Cons: Distance, harder to master
Second Person
You walk into the room. You immediately regret it.Pros: Immediacy, unusual Cons: Can feel gimmicky, reader resistance
POV Rules
- Stay in one head per scene (for limited)
- Only show what POV character perceives
- Filter through their psychology
- Match POV to story needs
Prose Style
Sentence Craft
Vary length:
Short sentences punch. They create urgency. Impact.
But longer sentences, with their flowing clauses and
subordinate phrases, can lull the reader into a rhythm,
carrying them forward on a wave of prose that builds
and builds until—Strong verbs over adverbs:
❌ She walked quickly across the room.
✅ She darted across the room.
✅ She bolted across the room.Concrete over abstract:
❌ He felt sad.
✅ His chest ached. He couldn't swallow.Show vs Tell
Telling (has its place):
She was angry.Showing:
Her jaw tightened. She set down her fork—carefully,
deliberately—and folded her hands in her lap.When to tell:
- Transitions
- Unimportant information
- Pacing through slow periods
- Emotional summary after intense scene
Dialogue
Subtext: Characters rarely say what they mean.
"Nice weather," she said. (Text)
[I don't want to talk about it] (Subtext)Attribution:
✅ "I'm leaving," she said.
✅ "I'm leaving." She grabbed her coat.
⚠️ "I'm leaving," she exclaimed angrily."Said" is invisible. Use it.
Beats over tags:
"I'm leaving." She grabbed her coat. "Don't wait up."Description
Sensory Writing
| Sense | Often Used | Underused |
| Sight | Very common | - |
| Sound | Common | - |
| Touch | Uncommon | Temperature, texture |
| Smell | Rare | Memory trigger |
| Taste | Rare | Atmosphere |
Layer senses:
The bar smelled like spilled beer and regret. Neon
buzzed overhead, painting everyone the same shade of
desperate pink. Someone fed the jukebox, and Patsy
Cline started breaking hearts again.Meaningful Detail
Choose details that do double duty:
❌ The room had a desk, a chair, and a filing cabinet.
[Inventory]
✅ Dust furred the family photos on his desk—all
turned to face the wall.
[Character revelation + atmosphere]Revision Framework
Levels of Revision
| Level | Focus | Questions |
| Structural | Story architecture | Does the plot work? Are scenes in right order? |
| Scene | Individual scenes | Does each scene have conflict? Purpose? |
| Paragraph | Flow and pacing | Transitions smooth? Rhythm varied? |
| Sentence | Prose quality | Verbs strong? Sentences varied? |
| Word | Precision | Right word? Unnecessary words? |
Revision Passes
Pass 1: Story
- Does the beginning hook?
- Is the ending earned?
- Does the middle sag?
- Are stakes clear?
Pass 2: Character
- Distinct voices?
- Consistent motivation?
- Arc completed?
- Relationships clear?
Pass 3: Scene
- Each scene has purpose?
- Conflict present?
- Sensory grounding?
- POV consistent?
Pass 4: Line
- Cut filler words (just, really, very)
- Strengthen verbs
- Vary sentence structure
- Check dialogue tags
Pass 5: Polish
- Read aloud
- Check spelling/grammar
- Format consistency
- Final typo sweep
Common Problems
Pacing Issues
| Symptom | Cause | Fix |
| Drags | Too much description | Cut, add conflict |
| Rushed | Not enough scene | Slow down, add beats |
| Confusing | Time jumps | Add transitions |
| Boring | No stakes | Raise consequences |
Dialogue Issues
| Problem | Example | Fix |
| On-the-nose | "I'm angry at you!" | Subtext |
| Talking heads | Dialogue without action | Add beats |
| Info dump | Explaining plot | Conflict over info |
| Same voice | All characters same | Differentiate |
Description Issues
| Problem | Fix |
| Purple prose | Simplify, cut adjectives |
| No setting | Ground in physical space |
| Floating heads | Add action, gesture |
| Info dump | Distribute, dramatize |
Forms
Short Story
- 1,000-7,500 words typical
- Single effect/impression
- Limited scope
- Often one POV
Flash Fiction
- Under 1,000 words
- Implication over exposition
- Often twist or resonance
- Every word counts
Novel Chapter
- 2,000-5,000 words typical
- Mini-arc or cliffhanger
- Advances plot AND character
- Varies with genre
Personal Essay
- First person reflection
- Particular to universal
- Scene + reflection
- "So what?" answered
References
references/story-structures.md- Alternative structuresreferences/genre-conventions.md- Genre expectationsreferences/revision-checklist.md- Detailed checklist
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

