MCPInstall

flash-fiction

Diagnose and fix problems in flash fiction and micro fiction. Use when flash fiction feels weak, when writing stories under 1500 words, when working with micro fiction, sudden fiction, or compressed narrative forms.

Installs
470
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 flash-fiction
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads flash-fiction automatically when relevant.

  3. 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.

Flash Fiction Diagnostic

Purpose

Diagnose and fix problems in flash fiction and micro fiction (typically under 1500 words). Flash fiction demands exceptional craft efficiency—every word must serve multiple purposes. This skill identifies which dimension needs attention when a piece isn't working.

Quick Reference

StateSignalCore Issue
FF1Opening doesn't hookStructure/Pacing problem
FF2Characters feel thinCharacter compression failure
FF3Beginning/ending disconnectFrame weakness
FF4Everything on surfaceSubtext missing
FF5Prose feels flatImagery/figurative language weak
FF6Setting genericSensory detail lacking
FF7Theme absent or preachyThematic development off
FF8Words don't singLanguage precision/rhythm issues
FF9Something feels "off"Logical consistency breach

Diagnostic States

FF1: Structure & Pacing Failure

Symptoms:

  • Opening doesn't grab
  • Middle sags or rushes
  • Ending feels abrupt or dragged
  • Word count not distributed well
  • Arc feels incomplete

Diagnostic Questions:

  1. Does the first sentence create immediate engagement?
  2. Is there a clear turning point?
  3. Does each paragraph advance multiple purposes (plot + character + theme)?
  4. Is the scope appropriate for the word count?
  5. Is information released at optimal moments?

Interventions:

  • Map the arc: beginning → rising action → climax → resolution
  • Calculate word distribution across sections
  • Strengthen opening hook (in medias res, mystery, declaration)
  • Ensure ending provides closure while leaving resonance
  • Cut any paragraph that only does one thing

Transformation Pattern:

WEAK: "Sarah had been working at the firm for three years when she found the file."
STRONG: "The file had no label—just a smudge of what looked like dried blood along its edge."

FF2: Character Compression Failure

Symptoms:

  • Characters feel generic or interchangeable
  • Too much backstory exposition
  • Character change feels unearned
  • Relationships explained rather than shown
  • No sense of life beyond the page

Diagnostic Questions:

  1. Is each character introduced through revealing action?
  2. Can history be inferred without explicit backstory?
  3. Do defining objects/mannerisms reveal essence?
  4. Is the character arc shown through parallel actions?
  5. Do relationships emerge through interaction, not explanation?

Interventions:

  • Replace generic description with character-specific detail
  • Convert backstory exposition to implications
  • Ensure first action reveals personality
  • Show change through decision pattern shifts
  • Establish relationships through what's unspoken

Transformation Pattern:

WEAK: "James had PTSD from the war. He moved to escape memories."
STRONG: "James flinched at the turkey platter's clatter, hand reaching for the phantom sidearm.
He'd chosen this town for its population sign: 827 souls—small enough to hear rumors
of strangers before meeting them."

FF3: Beginning/Ending Frame Weakness

Symptoms:

  • Opening and closing feel disconnected
  • No sense of journey despite brevity
  • Ending doesn't fulfill opening's promise
  • First/last images don't resonate
  • Structure feels arbitrary

Diagnostic Questions:

  1. What does the opening promise the reader?
  2. Does the ending fulfill or meaningfully subvert that promise?
  3. Is there a first/last image relationship (echo, transformation, contrast)?
  4. Does the ending feel both surprising and inevitable?
  5. What emotion persists after reading?

Interventions:

  • Identify the implicit contract the opening creates
  • Ensure closing image relates to opening image
  • Consider circular structure (return with transformation)
  • Strengthen final sentence for resonance
  • Check that emotional journey is complete

Transformation Pattern:

WEAK ENDING: "So they decided not to sell. They were happy. The end."
STRONG ENDING: "Daniel returned the FOR SALE sign to the garage, laid it beside the smaller
one from his childhood treehouse. Some prices, they'd decided, were too steep to calculate."

FF4: Subtext Missing

Symptoms:

  • Everything stated explicitly
  • No layers beneath surface
  • Readers don't participate in meaning-making
  • Backstory dumped, not implied
  • No iceberg effect

Diagnostic Questions:

  1. What is stated that could be implied?
  2. What is strategically left unsaid?
  3. Are there meaningful gaps for readers to fill?
  4. Does the visible portion suggest invisible depth?
  5. Is ambiguity purposeful or accidental?

Interventions:

  • Convert explicit statements to implications
  • Create strategic gaps (narrative ellipsis)
  • Withhold information for revelation impact
  • Apply iceberg theory: show tip, imply mass below
  • Ensure backstory emerges through objects/actions, not explanation

Transformation Pattern:

EXPLICIT: "John never recovered from his divorce. He felt bitter about Maria leaving him."
IMPLIED: "John twisted his wedding ring finger, a reflex unchanged by three years and
the absence of metal. The man at the next table laughed, and John recognized
the laugh before the face."

FF5: Imagery & Figurative Language Weak

Symptoms:

  • Prose feels flat or utilitarian
  • Metaphors cliched or absent
  • No pattern to imagery
  • Symbols heavy-handed or missing
  • Descriptions don't resonate

Diagnostic Questions:

  1. Are comparisons fresh and precise?
  2. Do metaphors/similes serve multiple purposes (character + theme + emotion)?
  3. Is there an imagery pattern that develops?
  4. Are symbolic objects naturally integrated?
  5. Is there balance between concrete and abstract?

Interventions:

  • Replace clichéd comparisons with original ones
  • Ensure figurative language reveals character perspective
  • Build related image patterns that develop
  • Select symbolic objects that can transform meaning
  • Ground abstract concepts in concrete imagery

Transformation Pattern:

FLAT: "The factory was abandoned and looked sad."
RICH: "Machinery hulked under dust shrouds, metal teeth gleaming in fractured light
between boarded windows. No one suggested splitting up."

FF6: Setting & Sensory Detail Lacking

Symptoms:

  • Location generic or absent
  • Only visual sense engaged
  • Setting doesn't serve character/theme
  • Atmosphere missing
  • Environment feels like backdrop, not participant

Diagnostic Questions:

  1. How quickly is the reader oriented in specific time/place?
  2. Are multiple senses engaged?
  3. Does setting reveal character without stating it?
  4. Does environment reinforce theme?
  5. Is atmospheric mood established through concrete detail?

Interventions:

  • Replace generic settings with specific, revealing locations
  • Incorporate non-visual senses (sound, smell, touch, taste)
  • Make setting details reveal character relationship to place
  • Align physical environment with thematic concerns
  • Embed mood in concrete details, not stated atmosphere

Transformation Pattern:

GENERIC: "The coffee shop was busy. People sat drinking coffee."
SPECIFIC: "The Fallout Shelter Café's concrete walls trapped steam from twenty
underemployed grad students' laptops, their whispered theories competing
with grinding beans and Ella Fitzgerald's crackled vinyl."

FF7: Thematic Development Off

Symptoms:

  • Theme absent or unclear
  • Theme stated, not embodied
  • Didactic/preachy tone
  • Single perspective dominates
  • Ending oversimplifies

Diagnostic Questions:

  1. Is the theme identifiable without being heavy-handed?
  2. Does theme emerge from character and situation (not imposed)?
  3. Are multiple perspectives on the theme represented?
  4. Is thematic content conveyed through concrete details?
  5. Does the conclusion deepen rather than simplify?

Interventions:

  • Embody theme in action and object, not statement
  • Show theme through specific circumstances, then let readers generalize
  • Include multiple viewpoints on the thematic question
  • Replace "character realized that..." with demonstrating action
  • Preserve complexity in the conclusion

Transformation Pattern:

STATED: "Carl realized that trust was essential for relationships."
EMBODIED: "Carl handed her the combination to the safe where he kept
his mother's letters, then turned away so he wouldn't see her expression."

FF8: Language Precision & Rhythm Issues

Symptoms:

  • Weak verbs (walked, went, was)
  • Vague nouns (thing, stuff, area)
  • Unnecessary modifiers
  • Sentence monotony
  • No musicality

Diagnostic Questions:

  1. Does each verb precisely capture the specific action?
  2. Are nouns concrete and specific?
  3. Does each modifier meaningfully sharpen understanding?
  4. Are sentence lengths and structures varied?
  5. Do sound patterns enhance (alliteration, rhythm, cadence)?

Interventions:

  • Replace weak verbs with precise, energetic alternatives
  • Substitute general nouns with specific, sensory-rich ones
  • Eliminate redundant or decorative modifiers
  • Vary sentence structure for rhythm and emphasis
  • Develop sound patterns that match meaning

Transformation Pattern:

WEAK: "She went across the field quickly."
PRECISE: "She slashed through the wheat, scattering husks."

MONOTONOUS: "He opened the door. He looked inside. He saw nothing. He closed the door."
VARIED: "He opened the door and looked inside. Nothing. The door clicked shut as he turned."

FF9: Logical Consistency Breach

Symptoms:

  • Something feels "off" even if hard to identify
  • Physical impossibilities
  • Timeline contradictions
  • Characters know things they shouldn't
  • Rules established then broken

Diagnostic Questions:

  1. Do objects function consistently?
  2. Does the timeline allow events as described?
  3. Do characters know only what they could realistically know?
  4. Are physical limitations respected?
  5. If rules are bent, is it consistent?

Interventions:

  • Map physical movement and verify possibility
  • Chart events chronologically with durations
  • Check character knowledge boundaries
  • Verify cause-effect proportionality
  • Document world rules and check consistent application

Transformation Pattern:

IMPOSSIBLE: "She finished her shift at midnight, drove 30 miles home,
cooked dinner, and was in bed by 12:15."
POSSIBLE: "She finished at midnight. The apartment she'd rented
closer to the hospital meant she could be cooking within minutes."

Evaluation Checklist

For any flash fiction piece:

Structure (FF1)

  • First sentence hooks
  • Each paragraph serves multiple purposes
  • Clear arc despite compression
  • Scope matches word count

Character (FF2)

  • Characters introduced through revealing action
  • History inferred, not explained
  • Change shown through action

Frame (FF3)

  • Opening/closing images relate
  • Ending fulfills or transforms promise
  • Emotional journey complete

Subtext (FF4)

  • More implied than stated
  • Strategic gaps for reader participation
  • Iceberg effect achieved

Imagery (FF5)

  • Fresh figurative language
  • Imagery patterns develop
  • Symbols naturally integrated

Setting (FF6)

  • Specific time/place established quickly
  • Multiple senses engaged
  • Setting serves theme

Theme (FF7)

  • Theme emerges, not stated
  • Multiple perspectives present
  • Complexity preserved

Language (FF8)

  • Precise verbs
  • Concrete nouns
  • Sentence variety
  • Musicality present

Consistency (FF9)

  • Physics work
  • Timeline possible
  • Knowledge boundaries respected

Anti-Patterns

The Miniature Novel

Trying to compress a novel-length story into flash length. Flash fiction is not a summary—it's a complete experience in miniature. Choose a scope that fits.

The Twist Dependency

Relying entirely on a surprise ending. If the story only works with the twist, the preceding content isn't pulling weight. The journey should matter.

The Vignette Trap

Beautiful prose without narrative movement. Flash fiction still needs change—something must be different by the end, even if subtle.


Integration Points

Inbound:

  • From story-sense: After identifying story state
  • From drafting: During first draft creation
  • From revision: For line-level polish

Outbound:

  • To prose-style: For deeper language work
  • To dialogue: For conversation problems
  • To endings: For closure issues

Complementary:

  • scene-sequencing: Single-scene pacing
  • character-arc: Compressed transformation
  • cliche-transcendence: Fresh imagery generation

Word Count Guidance

LengthNameFocus Priority
<100DrabbleSingle image, single moment, maximum compression
100-500Micro fictionOne scene, one shift, implication over statement
500-1000Flash fictionSmall arc, 1-2 scenes, full iceberg effect
1000-1500Sudden fictionMultiple scenes possible, more character room
1500-2500Short shortApproaching short story territory

Sources

Frameworks synthesized from flash fiction craft analysis, incorporating principles from:

  • Hemingway's iceberg theory
  • John Gardner on the "vivid and continuous dream"
  • Compression techniques from poetry applied to prose

FAQ

What does the flash-fiction skill do?

Diagnose and fix problems in flash fiction and micro fiction. Use when flash fiction feels weak, when writing stories under 1500 words, when working with micro fiction, sudden fiction, or compressed narrative forms.

How do I install flash-fiction?

Run npx skills add https://github.com/jwynia/agent-skills --skill flash-fiction 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/flash-fiction/ (personal) or .claude/skills/flash-fiction/ (project).

Which AI agents can use flash-fiction?

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 flash-fiction 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 flash-fiction?

It is published by jwynia in jwynia/agent-skills. It has 470 recorded installs.

More from jwynia/agent-skills

View all →

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.

Docs & Writing2.5K installs

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.

Frontend & Design2.3K installs

requirements-analysis

jwynia/agent-skills

Diagnose requirements problems and guide discovery of real needs and constraints

AI & Agents2.3K installs

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.

Media & Creative1K installs

Popular ai & agents skills

View category →

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).

AI & Agents513.9K installs

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).

AI & Agents513.5K installs

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.

OfficialAI & Agents416.4K installs

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.

AI & Agents402.1K installs

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.

AI & Agents401K installs

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

AI & Agents245.7K installs