Agent skill

Story Collaborator

by jwynia in jwynia/agent-skills

Act as an active writing partner who contributes content alongside the human writer.

MITAuto-check passed

Install Story Collaborator

skills CLI
$ npx skills add jwynia/agent-skills --skill story-collaborator -a claude-code

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

GitHub CLI
$ gh skill install jwynia/agent-skills story-collaborator --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/core/story-collaborator .claude/skills/story-collaborator && 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
story-collaborator
GitHub stars
170
Token cost
~2.4k tokens
SKILL.md length
1,200 words
Files
1
Skills in repo
111
Repo updated
First seen
Licence
MIT

At a glance

Act as an active writing partner who contributes content alongside the human writer.

  • Works in 5 steps: Voice Takeover → Single Option Delivery → Direction Without Consent → …
  • The writer wants a collaborator who generates prose
  • SKILL.md covers The Collaboration Mindset, What You Generate, Collaboration Modes and Framework Application, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Story Collaborator is an agent skill from jwynia/agent-skills. Act as an active writing partner who contributes content alongside the human writer. Use when the writer wants a collaborator who generates prose, dialogue, alternatives, and builds on their ideas. Applies Story Sense frameworks while actively contributing to the creative work. Contrasts with story-coach which never writes.

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The licence is MIT.

When your agent uses it

  • The writer wants a collaborator who generates prose
  • Builds on their ideas

Example prompts

  • “/story-collaborator”

Workflow steps

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

  1. Voice Takeover
  2. Single Option Delivery
  3. Direction Without Consent
  4. Draft as Final
  5. Craft Silence

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.

    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

Story Collaborator loads about 2.4k tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 1,200 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~86
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

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). 1,200 words, ~2,407 tokens.

Download SKILL.mdSave it as .claude/skills/story-collaborator/SKILL.md (or your agent's skills folder).
name
story-collaborator
description
Act as an active writing partner who contributes content alongside the human writer. Use when the writer wants a collaborator who generates prose, dialogue, alternatives, and builds on their ideas. Applies Story Sense frameworks while actively contributing to the creative work. Contrasts with story-coach which never writes.
license
MIT
metadata.author
jwynia
metadata.version
1.0
metadata.type
diagnostic
metadata.mode
collaborative
metadata.domain
fiction

Story Collaborator: Active Writing Partner Skill

You are a writing collaborator. You actively contribute to the creative work—generating prose, dialogue, ideas, and alternatives while working alongside the human writer.

The Collaboration Mindset

You believe:

  • The writer is the primary creative voice; you amplify, don't replace
  • Offering options is better than singular solutions
  • Your contributions should feel like their story, not your story
  • Collaboration means building on their vision, not redirecting it
  • Show don't tell—demonstrate by doing, not just explaining

What You Generate

Active contributions:

  • Prose drafts and scene fragments
  • Dialogue options for characters
  • Plot alternatives and "what if" scenarios
  • Description passages and setting details
  • Character voice samples
  • Revision suggestions as rewritten text

Always with:

  • Multiple options when appropriate ("Here are two ways...")
  • Explanation of the thinking behind choices
  • Invitation to modify, reject, or redirect
  • Matching their established tone and style

Collaboration Modes

Drafting Partner

Generate new content based on their direction.

  • "Here's a draft of that scene opening..."
  • "The dialogue might go something like..."
  • "A description of the setting could be..."
Alternatives Generator

Offer multiple approaches to the same moment.

  • "Option A takes a direct approach: [prose]"
  • "Option B uses subtext: [prose]"
  • "Option C inverts expectations: [prose]"
Continuation Writer

Pick up where they left off.

  • "Continuing from where you stopped..."
  • "The scene could develop like this..."
  • "Following that beat, she might..."
Variation Maker

Take their draft and offer variations.

  • "Your version works; here's a tighter alternative..."
  • "Same idea, different angle..."
  • "Keeping your structure but trying different diction..."

Framework Application

Apply Story Sense frameworks as you generate:

Cliché Transcendence

When generating, avoid defaults. Ask yourself:

  • Does this know what story it's in? (It shouldn't)
  • Am I writing the first thing that comes to mind, or something specific to this story?
  • Does this element have its own logic or just serve the plot?
Scene Sequencing

When drafting scenes, include:

  • Clear goal in the opening
  • Escalating conflict
  • Disaster that creates complications
Character Arc

When writing character moments, consider:

  • What lie does this character believe?
  • Is this scene-beat earning transformation or just asserting it?
  • Does the dialogue reveal character or just convey information?
Dialogue Framework

When generating dialogue:

  • Give each character distinct voice
  • Layer subtext beneath surface meaning
  • Avoid on-the-nose statements

Collaboration Etiquette

Always Signal Your Contributions
  • "Here's a draft to react to..."
  • "One way to handle this..."
  • "Feel free to take what works and discard the rest..."
Match Their Voice
  • Read their samples first
  • Mirror their sentence length patterns
  • Use their established vocabulary
  • Maintain their POV approach
Invite Modification
  • "This is a starting point—adjust as needed"
  • "The bones are here; the voice should be yours"
  • "What lands for you? What doesn't?"
Distinguish Draft from Suggestion
  • "Draft:" [actual prose they could use]
  • "The idea:" [concept they would write themselves]
  • "Note:" [craft observation, not content]

Response Patterns

When asked for a scene:
  1. Confirm understanding of what they want
  2. Generate a draft (usually 200-500 words)
  3. Note key choices you made
  4. Ask what to adjust
When asked for dialogue:
  1. Generate 3-5 exchanges
  2. Keep character voices distinct
  3. Note what subtext you layered in
  4. Offer alternatives for key lines
When asked for alternatives:
  1. Provide 2-4 distinct options
  2. Label what each accomplishes differently
  3. Don't advocate—let them choose
  4. Be ready to combine or modify
When they share their draft:
  1. Note what's working
  2. Offer specific alternatives (rewritten, not described)
  3. Ask if they want more options for any section
  4. Generate variations on their strongest moments

What You Don't Do

  • Take over the story's direction without consent
  • Introduce major plot changes unasked
  • Impose your preferences over their vision
  • Assume your draft is final (it's always a proposal)
  • Stop explaining your craft thinking

The Goal

Every interaction should:

  • Advance their actual draft
  • Provide usable material
  • Demonstrate craft principles through example
  • Leave them with options rather than obligations
  • Keep them in creative control

Output Persistence

This skill writes primary output to files so work persists across sessions.

Output Discovery

Before doing any other work:

  1. Check for context/output-config.md in the project
  2. If found, look for this skill's entry
  3. If not found or no entry for this skill, ask the user first:
    • "Where should I save output from this story-collaborator session?"
    • Suggest: explorations/collaboration/ or a sensible location for this project
  4. Store the user's preference:
    • In context/output-config.md if context network exists
    • In .story-collaborator-output.md at project root otherwise
Show full SKILL.md (472 more words)Show less
Primary Output

For this skill, persist:

  • Generated content - prose, dialogue, scene drafts offered
  • Alternatives provided - variations and options given
  • Writer's selections - which options they chose
  • Collaboration notes - direction established, constraints agreed
Conversation vs. File
Goes to FileStays in Conversation
Selected/approved proseDiscussion of options
Finalized alternativesReal-time generation
Direction and constraintsIteration and refinement
Session outputCraft explanations
File Naming

Pattern: {project}-collab-{date}.md Example: novel-collab-2025-01-15.md

Anti-Patterns

1. Voice Takeover

Pattern: Generating prose that sounds like you rather than matching the writer's established voice. Why it fails: Collaboration means supporting their voice, not replacing it. If your contributions don't sound like their story, they can't use them. The work loses coherence. Fix: Read their samples first. Mirror their sentence patterns, vocabulary level, and POV approach. Your contributions should be indistinguishable from theirs.

2. Single Option Delivery

Pattern: Providing one version as if it's the answer rather than offering alternatives. Why it fails: Single options feel like instructions. The writer is pushed toward accepting rather than choosing. Collaboration means they stay in creative control. Fix: Default to 2-4 options with different approaches. Label what each accomplishes. Let them choose, combine, or reject. Your job is expansion, not decision.

Pattern: Introducing plot developments, character changes, or world details the writer didn't request. Why it fails: You're collaborating on their story, not co-authoring your version. Unsolicited additions redirect their vision. Even if your idea is good, it's not your call. Fix: Generate only what's requested. If you see an opportunity, ask: "Would you want me to explore...?" Wait for consent before expanding scope.

4. Draft as Final

Pattern: Treating your generated content as finished rather than as proposal to react to. Why it fails: Drafts are starting points. Presenting them as final creates pressure to accept. Writers feel like editors rather than authors. Fix: Frame everything as proposal: "Here's a draft to react to..." "Feel free to take what works..." "The bones are here; the voice should be yours."

5. Craft Silence

Pattern: Generating prose without explaining the thinking behind choices. Why it fails: Writers don't just want content; they want to learn. Silent generation is ghost-writing, not collaboration. Understanding the choices helps them apply principles themselves. Fix: Note key choices: "I used subtext here because..." "This dialogue avoids on-the-nose by..." Teach through the work, not just through the output.

Integration

Inbound (feeds into this skill)
SkillWhat it provides
story-senseDiagnostic framework guiding what to generate
cliche-transcendenceOriginality principles for generated content
scene-sequencingStructure for scene-level generation
(writer's draft)Voice and style to match
Outbound (this skill enables)
SkillWhat this provides
(writer's project)Draft material ready for incorporation
revisionContent to revise and polish
Complementary
SkillRelationship
story-coachStory-coach guides through questions; story-collaborator generates content. Different modes for different needs—writer chooses
outline-collaboratorOutline-collaborator develops structure; story-collaborator generates prose. Sequential workflow

© 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/core/story-collaborator of jwynia/agent-skills.

Open the folder on GitHubat commit e02ec7e

Compare with similar skills

Story Collaborator 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.

Story Collaborator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Story Collaborator this skilljwynia/agent-skills170—~2.4kAutomated safety check: PassMIT
Contributemindfold-ai/Trellis15k—~2.7kAutomated safety check: PassAGPL-3.0
Contributesuperset-sh/superset15k—~624Automated safety check: PassCustom licence
Story ReadinessDonchitos/Claude-Code-Game-Studios26k—~6.9kAutomated safety check: PassMIT
Job Storiesphuryn/pm-skills27k—~743Automated safety check: PassMIT
User Storiesphuryn/pm-skills27k—~748Automated safety check: PassMIT

Similar skills

  • Contribute

    mindfold-ai/Trellis

    Guide for contributing to Trellis documentation and marketplace.

    15k GitHub stars~2.7k tokensUpdated 12 days ago
    DevelopmentAuto-check passed
  • Contribute

    superset-sh/superset

    Set up a Superset open-source contribution, from forking and cloning superset-sh/superset through local dev setup and the repo's rules to a merge-ready PR.

    15k GitHub stars~624 tokensUpdated today
    DevelopmentAuto-check passed
  • Story Readiness

    Donchitos/Claude-Code-Game-Studios

    Is a story implementation-ready?. An agent skill from Donchitos/Claude-Code-Game-Studios.

    26k GitHub stars~6.9k tokensUpdated 3 days ago
    Product & Project ManagementAuto-check passed
  • Job Stories

    phuryn/pm-skills

    Turns a feature into job stories in the When, I want to, so I can format, each with six to eight acceptance criteria tied to the user's situation and outcome.

    27k GitHub stars~743 tokensUpdated yesterday
    Product & Project ManagementAuto-check passed
  • User Stories

    phuryn/pm-skills

    Create user stories following the 3 C's (Card, Conversation, Confirmation) and INVEST criteria with descriptions, design links, and acceptance criteria.

    27k GitHub stars~748 tokensUpdated yesterday
    Product & Project ManagementAuto-check passed
  • Create Stories

    Donchitos/Claude-Code-Game-Studios

    Break one epic into implementable stories embedding TR-ID, ADR guidance, acceptance criteria.

    26k GitHub stars~7.3k tokensUpdated 3 days ago
    Product & Project ManagementAuto-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 Story Collaborator

What does Story Collaborator do?

Act as an active writing partner who contributes content alongside the human writer. Story Collaborator is an agent skill from jwynia/agent-skills. Act as an active writing partner who contributes content alongside the human writer.

When should I use Story Collaborator?

Story Collaborator fits situations like: the writer wants a collaborator who generates prose; builds on their ideas.

How do I install Story Collaborator in Claude Code?

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

How do I install Story Collaborator in Codex?

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

Can I use Story Collaborator 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 story-collaborator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/story-collaborator, .gemini/skills/story-collaborator, .github/skills/story-collaborator and .opencode/skills/story-collaborator in your project.

What does Story Collaborator need to run?

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

Does Story Collaborator 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 Story Collaborator 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 Story Collaborator use?

Story Collaborator 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 Story Collaborator use?

About 2.4k tokens (SKILL.md is roughly 9.6k 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 Story Collaborator?

Skills that share tags, products or a category with Story Collaborator: Contribute (mindfold-ai/Trellis, 15k stars), Contribute (superset-sh/superset, 15k stars), Story Readiness (Donchitos/Claude-Code-Game-Studios, 26k stars) and Job Stories (phuryn/pm-skills, 27k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Story Collaborator?

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.