Agent skill

Pulp Fiction Writing

by swyxio in swyxio/skills

Write or revise fast-moving, voice-forward serialized pulp fiction with strong hooks, clear character dynamics, escalating complications, compact chapters, and bingeable momentum.

MITAuto-check passedWriting & Content

Install Pulp Fiction Writing

skills CLI
$ npx skills add swyxio/skills --skill pulp-fiction-writing -a claude-code

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

GitHub CLI
$ gh skill install swyxio/skills pulp-fiction-writing --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/swyxio/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/pulp-fiction-writing .claude/skills/pulp-fiction-writing && 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
pulp-fiction-writing
GitHub stars
176
Token cost
~1.9k tokens
SKILL.md length
1,000 words
Files
2
Skills in repo
89
Repo updated
First seen
Licence
MIT

At a glance

Write or revise fast-moving, voice-forward serialized pulp fiction with strong hooks, clear character dynamics, escalating complications, compact chapters, and bingeable momentum.

  • Works in 5 steps: Want: A character pursues a specific… → Friction: Another person, fact, rule, or… → Tactic: The character tries something… → …
  • Drafting genre fiction
  • SKILL.md covers Core contract, Build the story engine, Voice and viewpoint and Scene loop, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Pulp Fiction Writing is an agent skill from swyxio/skills. Write or revise fast-moving, voice-forward serialized pulp fiction with strong hooks, clear character dynamics, escalating complications, compact chapters, and bingeable momentum. Use when drafting genre fiction, outlining a serial, tightening pacing, improving dialogue, designing chapter cliffhangers, or revising prose for readability and reader retention.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Writing & Content, covering Creative writing and fiction and Plain language and style rules. The repository describes itself as: Agent skills for Claude Code and other AI agents. The licence is MIT.

When your agent uses it

  • Drafting genre fiction
  • Outlining a serial
  • Tightening pacing
  • Improving dialogue

Example prompts

  • “/pulp-fiction-writing”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Want: A character pursues a specific short-term objective.
  2. Friction: Another person, fact, rule, or consequence resists it.
  3. Tactic: The character tries something concrete.
  4. Turn: The tactic works partially, fails, or reveals a larger problem.
  5. Exit: The situation is different enough that the next scene has a reason to exist.

What it can do on your machine

Read from SKILL.md and the folder at commit 038ef34. 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.

    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

Pulp Fiction Writing loads about 1.9k tokens when it runs. Until then it costs about 95 tokens; SKILL.md has 1,000 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~95
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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 swyxio/skills at commit 038ef34, republished under its MIT licence (© swyxio). 1,000 words, ~1,854 tokens.

Download SKILL.mdSave it as .claude/skills/pulp-fiction-writing/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
pulp-fiction-writing
description
Write or revise fast-moving, voice-forward serialized pulp fiction with strong hooks, clear character dynamics, escalating complications, compact chapters, and bingeable momentum. Use when drafting genre fiction, outlining a serial, tightening pacing, improving dialogue, designing chapter cliffhangers, or revising prose for readability and reader retention.

Pulp Fiction Writing

Use this skill to make a story difficult to put down without making it shallow. Favor clarity, velocity, emotional legibility, and consequential turns over ornamental prose.

Core contract

  • Open with a person wanting something now.
  • Put pressure on that want within the first scene.
  • Make every scene change the situation, the relationship, or the reader's understanding.
  • Keep the prose transparent enough that the reader never loses the action.
  • End chapters with a changed question, a difficult choice, a reveal, or a new problem.
  • Prefer specific, concrete details over generalized description.

Build the story engine

Define these before drafting:

  • Promise: What recurring pleasure does the story deliver? Examples: advancement, danger, romance, rivalry, mystery, transformation, or social maneuvering.
  • Protagonist drive: What does the protagonist want, and what will they risk to get it?
  • Pressure source: Who or what makes the goal difficult?
  • Escalation ladder: What becomes harder, costlier, more public, or more personal at each stage?
  • Relationship web: Who wants what from whom? Give each important relationship a distinct tension: loyalty, envy, debt, fear, rivalry, admiration, or mistrust.
  • Continuity ledger: Track promises, secrets, injuries, debts, objects, unresolved questions, and changed alliances. Reuse them later with consequences.

If the premise is broad, choose one immediate situation and draft from there. Do not front-load the entire backstory.

Voice and viewpoint

Use a conversational narrative voice with a strong point of view. The narrator should interpret events, not merely report them.

  • Let sentence length follow thought: short for impact, longer for observation or rationalization.
  • Give the narrator opinions, blind spots, habits of attention, and a recognizable way of naming things.
  • Make the voice confident about some things and wrong about others.
  • Use concrete reactions and choices to reveal character instead of explaining every trait.
  • Keep viewpoint stable inside a scene unless a deliberate structural choice requires otherwise.

For first person, make the narrator's account selective. What they notice—and what they avoid noticing—should tell the reader who they are.

Scene loop

Draft most scenes around this compact loop:

  1. Want: A character pursues a specific short-term objective.
  2. Friction: Another person, fact, rule, or consequence resists it.
  3. Tactic: The character tries something concrete.
  4. Turn: The tactic works partially, fails, or reveals a larger problem.
  5. Exit: The situation is different enough that the next scene has a reason to exist.

Do not let a scene end where it began. If the scene is primarily connective, compress it or attach it to a scene with a meaningful turn.

Dialogue and character clarity

Make dialogue do at least two jobs: pursue an objective and expose a relationship.

  • Give speakers unequal information or unequal stakes.
  • Let characters evade, reframe, tease, bargain, interrupt, or answer the wrong question.
  • Distinguish voices through priorities and syntax, not cartoon accents.
  • Cut greetings, repeated confirmations, and lines whose only purpose is to restate narration.
  • After an important line, show the physical or strategic consequence.

When several characters share a scene, assign each a role in the pressure pattern: instigator, skeptic, mediator, rival, witness, opportunist, or reluctant ally.

Exposition without drag

Reveal history when it affects the present decision. Use a memory, object, interruption, comparison, or argument to surface the necessary context.

Prefer:

The old photograph mattered because someone had just lied about it.

Over a paragraph explaining the photograph's entire history before the scene begins.

Keep only the backstory that changes how the reader interprets the current moment. Seed the rest later.

Show full SKILL.md (427 more words)Show less

Serialized pacing

Treat each chapter as a small episode with its own movement:

  • Start near a decision, interruption, discovery, arrival, confrontation, or promise.
  • Establish the local objective quickly.
  • Escalate by changing the cost or the audience, not by repeating the same beat louder.
  • Alternate intensity: follow a public crisis with a private reckoning, or a victory with a new obligation.
  • Use short chapters when the story benefits from velocity; use longer chapters when the reader needs accumulation or emotional aftershock.
  • End on a turn that creates forward pull, not merely a dramatic sentence.

Useful chapter endings include:

  • a new fact that changes the meaning of the previous scene;
  • a promise the protagonist cannot comfortably keep;
  • an ally taking an unexpected position;
  • a choice between two costly options;
  • a visible consequence arriving earlier than expected;
  • a new goal that grows naturally from the completed one.

Escalation and payoff

Build a ladder rather than a pile of incidents. Each rung should increase at least one dimension:

  • Scale: private to public, local to institutional;
  • Cost: inconvenience to sacrifice;
  • Exposure: hidden to witnessed;
  • Intimacy: stranger to trusted ally to dangerous rival;
  • Irreversibility: reversible mistake to permanent change.

Plant small promises early and pay them off later. A payoff should feel surprising in the moment and inevitable in retrospect. Reintroduce minor details only when they now carry new meaning.

Revision passes

Run separate passes instead of trying to solve everything at once:

  1. Momentum: Remove delayed starts, repeated explanations, and scenes without turns.
  2. Clarity: Make goals, locations, speakers, chronology, and stakes easy to follow.
  3. Voice: Replace generic phrasing with the narrator's specific judgments and rhythms.
  4. Character: Give major characters distinct wants, tactics, and reactions.
  5. Escalation: Check that each chapter adds cost, exposure, intimacy, scale, or irreversibility.
  6. Payoff: Resolve or deliberately advance the promises and questions created earlier.
  7. Line edit: Fix repetition, filler, weak verbs, accidental ambiguity, and overlong sentences.

Common failure modes

Watch for:

  • opening with biography instead of an active problem;
  • repeating the same description, argument, or emotional beat;
  • explaining a character's feelings after the action already showed them;
  • making every character react with the same voice;
  • escalating only through volume or spectacle;
  • using cliffhangers that do not alter the next decision;
  • adding new characters without assigning them a distinct function;
  • resolving a promise off-page or without a cost;
  • polishing individual sentences while the chapter's objective remains unclear.

When revising, protect the story's forward motion first. A clean, energetic sentence serving a strong turn is more valuable than a beautiful sentence that pauses the story.

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

Files

SKILL.md and 1 other file in pulp-fiction-writing of swyxio/skills.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 038ef34

Compare with similar skills

Pulp Fiction Writing 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.

Pulp Fiction Writing compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pulp Fiction Writing this skillswyxio/skills176—~1.9kAutomated safety check: PassMIT
Orwell Writingtamdogood/builder-essential-skills221—~1.1kAutomated safety check: PassMIT
Story Multi-Perspective Reviewzenstory-ai/oh-story-claudecode7.4k3 repos~3kAutomated safety check: PassMIT
Asd Ste100danyuchn/asd-ste100-skill4.3k—~4.1kAutomated safety check: PassMIT
Technical Writing Standardcursor/plugins11k10 repos~2.3kAutomated safety check: PassNone
Ponytail AuditDietrichGebert/ponytail160k—~1.4kAutomated safety check: PassMIT

Similar skills

  • Orwell Writing

    tamdogood/builder-essential-skills

    A skill your agent uses when an agent is asked to draft, rewrite, edit, review, polish, copyedit, simplify, humanize, or create written prose, including creative writing, essays, posts, scripts…

    221 GitHub stars~1.1k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed
  • 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
  • Asd Ste100

    danyuchn/asd-ste100-skill

    A skill your agent uses when English text must be parsed without a human to resolve ambiguity — tool descriptions, error messages, inter-agent instructions, system prompts, status reports — and…

    4.3k GitHub stars~4.1k tokensUpdated 7 days ago
    Writing & ContentAuto-check passed
  • Official

    Applies four layers of technical-writing rules to docs, RFCs, readmes, PR descriptions and commit messages so a tired engineer follows them on the first read.

    11k GitHub starsUsed in 10 repos~2.3k tokens
    Writing & ContentAuto-check passed
  • Ponytail Audit

    DietrichGebert/ponytail

    Quality audit of a whole repo: bugs, security holes, what breaks under real load, risky code without tests, slow paths, and what to delete, merge or split.

    160k GitHub stars~1.4k tokensUpdated yesterday
    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

More from swyxio/skills

All 89 skills in this repo
  • Programmatic Agents

    swyxio/skills

    Run a selected coding-agent CLI programmatically, with latency, error, usage, cost, and trace logging.

    176 GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • Design, implement, audit, or refresh protected username and handle namespaces for public products.

    176 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • New Mac Setup

    swyxio/skills

    Fully automated new Mac setup for fullstack web developers and AI engineers.

    176 GitHub stars~4.3k tokensUpdated today
    Auto-check passed
  • Youtube API

    swyxio/skills

    Manage YouTube videos programmatically via the YouTube Data API v3 — upload video files, upload custom thumbnails, update video metadata (titles, descriptions, tags), and query video/channel info…

    176 GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • Batch YouTube Studio upload workflow for videos sourced from Airtable, Google Drive, Loom, YouTube, or local files.

    176 GitHub stars~1.5k tokensUpdated today
    Auto-check: warnings
  • Reconstruct and visually analyze paired agent, game, or policy trajectories to determine whether changed actions produced their intended effects.

    176 GitHub stars~1.8k tokensUpdated today
    Auto-check passed

Questions about Pulp Fiction Writing

What does Pulp Fiction Writing do?

Write or revise fast-moving, voice-forward serialized pulp fiction with strong hooks, clear character dynamics, escalating complications, compact chapters, and bingeable momentum. Pulp Fiction Writing is an agent skill from swyxio/skills. Write or revise fast-moving, voice-forward serialized pulp fiction with strong hooks, clear character dynamics, escalating complications, compact chapters, and bingeable momentum.

When should I use Pulp Fiction Writing?

Pulp Fiction Writing fits situations like: drafting genre fiction; outlining a serial; tightening pacing; improving dialogue.

How do I install Pulp Fiction Writing in Claude Code?

Run `npx skills add swyxio/skills --skill pulp-fiction-writing -a claude-code`. Or copy the skill folder (pulp-fiction-writing in swyxio/skills) into .claude/skills/pulp-fiction-writing in your project. Claude Code loads it when a task matches its description.

How do I install Pulp Fiction Writing in Codex?

Run `npx skills add swyxio/skills --skill pulp-fiction-writing -a codex`. Or copy the skill folder (pulp-fiction-writing in swyxio/skills) into .agents/skills/pulp-fiction-writing in your project. Codex loads it when a task matches its description.

Can I use Pulp Fiction Writing 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 swyxio/skills --skill pulp-fiction-writing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pulp-fiction-writing, .gemini/skills/pulp-fiction-writing, .github/skills/pulp-fiction-writing and .opencode/skills/pulp-fiction-writing in your project.

What does Pulp Fiction Writing need to run?

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

Does Pulp Fiction Writing 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 Pulp Fiction Writing 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 Pulp Fiction Writing use?

Pulp Fiction Writing is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Pulp Fiction Writing use?

About 1.9k tokens (SKILL.md is roughly 7.4k 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 Pulp Fiction Writing?

Skills that share tags, products or a category with Pulp Fiction Writing: Orwell Writing (tamdogood/builder-essential-skills, 221 stars), Story Multi-Perspective Review (zenstory-ai/oh-story-claudecode, 7.4k stars), Asd Ste100 (danyuchn/asd-ste100-skill, 4.3k stars) and Technical Writing Standard (cursor/plugins, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pulp Fiction Writing?

swyxio (a GitHub user) maintains it in swyxio/skills, which has 176 GitHub stars. The repository holds 89 skills in this directory. The repository was last updated on October 5, 2026.

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