fiction-writing
Write or revise narrative prose — scene structure, character voice, pacing, dialogue.
Skill by quyenanh198
Chalk Labs
Need help deploying fiction-writing?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/quyenanh198-fiction-writing
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/fiction-writing
What's inside
- Skill name
fiction-writing- Description
- Write or revise narrative prose — scene structure, character voice, pacing, dialogue. Use when the user asks to write a scene, chapter, or story, or wants help with fiction/creative prose.
- License
- MIT
- Instructions
- 37 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Fiction Writing
## Overview
Support narrative prose that reads like it was written by someone who knows the craft, not generated to hit a word count. Prioritize: a scene that moves, characters who sound distinct from each other, and information delivered through action/dialogue rather than dumped in exposition.
## Before writing
Check what's already established — existing chapters, character notes, a story bible, prior scenes in the conversation. Match established voice, tense, POV, and canon facts (names, timeline, prior events) rather than reinventing them. If nothing is established yet (a first scene, a one-off piece), ask only what's load-bearing: POV, tense, and tone — don't interrogate the user with a long questionnaire before writing.
## Scene construction
Every scene needs:
- **A hook** — something that creates a question or tension in the first few lines, not throat-clearing scene-setting
- **Movement** — the scene changes something: information revealed, relationship shifted, a decision made, stakes raised. A scene where nothing changes should usually be cut or compressed
- **A landing** — end on tension, a turn, or a beat that pulls toward the next scene, not a summary of what just happened
## Dialogue
- Distinct voices: characters shouldn't be interchangeable if you remove the speaker tags. Vary sentence length, vocabulary, and what each character notices or avoids saying.
- No info-dumping through dialogue — characters shouldn't explain things to each other that both already know, purely to inform the reader. If backstory must surface, let it leak through subtext, conflict, or a concrete detail, not a monologue.
- Subtext over statement — characters often want something other than what they're saying; let the gap show.
## Prose craft
- **Show, don't tell** for emotional beats — ground feelings in physical action, sensory detail, or dialogue rather than naming the emotion outright ("her hands wouldn't stop moving" over "she was anxious").
- Vary sentence rhythm — a string of same-length sentences reads flat; mix short punches with longer flowing ones, especially around tension beats.
- Cut filter words that distance the reader from POV (saw, felt, noticed, realized) when deep in a character's POV — state the perceived thing directly instead.
- Avoid purple prose — one strong concrete image beats three stacked adjectives.
## Boundaries
- Don't summarize a scene when asked to write it — write the actual prose, not a synopsis of the prose.
- Don't resolve conflicts the user hasn't asked to resolve yet; respect where they want tension left open (e.g. a chapter ending on a cliffhanger).
- Flag continuity conflicts you notice against established canon rather than silently overriding them.From quyenanh198/Skills, MIT.
More from quyenanh198/Skills
- 0.529score
analyze-report
quyenanh198
Builds a multi-timeframe technical analysis and change report for any publicly traded stock — current snapshot, entry-point read across 1-hour/daily/weekly…
SkillBFreshness: BClaude Code +9 - 0.529score
chinese-via-hanviet
quyenanh198
Teaches Mandarin Chinese to a Vietnamese-speaking learner by bridging through Hán-Việt (Sino-Vietnamese) readings and vocabulary, and by flagging only the…
SkillBFreshness: BClaude Code +9 - 0.524score
divergent-thinking
quyenanh198
Open-ended ideation — generate a wide spread of distinct options or angles on a problem, breadth before evaluation.
SkillBFreshness: BClaude Code +9 - 0.524score
review-and-test
quyenanh198
Review code for bugs and correctness gaps, then write failing TDD-style tests for each confirmed gap before any fix is applied.
SkillBFreshness: BClaude Code +9 - 0.524score
code-review-checklist
quyenanh198
A general checklist for reviewing code changes for correctness, security, and maintainability.
SkillBFreshness: BClaude Code +9 - 0.520score
notebooklm
quyenanh198
Control NotebookLM (renamed "Gemini Notebook" as of July 2026 — same product, same URL) via browser automation using the Claude Chrome Extension.
SkillBFreshness: BClaude Code +9 - 0.519score
commit-message
quyenanh198
Drafts a conventional commit message from the currently staged git changes.
SkillBFreshness: BClaude Code +9 - 0.499score
learn
quyenanh198
Use this skill when the user wants intellectual understanding — learning how or why something works, not getting a task done or soliciting Claude's judgment.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 13, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/quyenanh198/Skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from quyenanh198
- 0.529score
analyze-report
quyenanh198
Builds a multi-timeframe technical analysis and change report for any publicly traded stock — current snapshot, entry-point read across 1-hour/daily/weekly…
SkillBFreshness: BClaude Code +9 - 0.529score
chinese-via-hanviet
quyenanh198
Teaches Mandarin Chinese to a Vietnamese-speaking learner by bridging through Hán-Việt (Sino-Vietnamese) readings and vocabulary, and by flagging only the…
SkillBFreshness: BClaude Code +9 - 0.524score
divergent-thinking
quyenanh198
Open-ended ideation — generate a wide spread of distinct options or angles on a problem, breadth before evaluation.
SkillBFreshness: BClaude Code +9 - 0.524score
review-and-test
quyenanh198
Review code for bugs and correctness gaps, then write failing TDD-style tests for each confirmed gap before any fix is applied.
SkillBFreshness: BClaude Code +9 - 0.524score
code-review-checklist
quyenanh198
A general checklist for reviewing code changes for correctness, security, and maintainability.
SkillBFreshness: BClaude Code +9 - 0.520score
notebooklm
quyenanh198
Control NotebookLM (renamed "Gemini Notebook" as of July 2026 — same product, same URL) via browser automation using the Claude Chrome Extension.
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get fiction-writing running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
fiction-writing skill. Agent Mart. https://agentmart.dev/skills/quyenanh198-fiction-writing (last updated 2026-10-24)