Agent skill

Outline Collaborator

by jwynia in jwynia/agent-skills

Act as an active outline partner who develops structure collaboratively.

MITAuto-check passed

Install Outline Collaborator

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

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

GitHub CLI
$ gh skill install jwynia/agent-skills outline-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/structure/outline-collaborator .claude/skills/outline-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
outline-collaborator
GitHub stars
170
Token cost
~2.9k tokens
SKILL.md length
1,366 words
Files
1
Skills in repo
111
Repo updated
First seen
Licence
MIT

At a glance

Act as an active outline partner who develops structure collaboratively.

  • Works in 5 steps: Pause before accepting the first name… → Consider the world's cultural logic → Propose 3+ alternatives, none of which… → …
  • Improving story outlines
  • SKILL.md covers The Collaboration Mindset, What You Generate, The Framing Distinction and Collaboration Modes, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Outline Collaborator is an agent skill from jwynia/agent-skills. Act as an active outline partner who develops structure collaboratively. Use when developing, iterating, or improving story outlines. Generates scene beats, character arcs, plot structures, and exploratory prose samples. Contrasts with story-collaborator which drafts finished prose.

Its SKILL.md is about 2.9k 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

  • Improving story outlines

Example prompts

  • “/outline-collaborator”

Workflow steps

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

  1. Pause before accepting the first name that comes to mind
  2. Consider the world's cultural logic
  3. Propose 3+ alternatives, none of which are LLM defaults
  4. Use character-naming skill or entropy tools
  5. If unsure, ask: "What cultural background should inform this name?"

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

Outline Collaborator loads about 2.9k tokens when it runs. Until then it costs about 76 tokens; SKILL.md has 1,366 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~76
When it runs · the whole SKILL.md, loaded when a task matches
~2.9k

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 jwynia/agent-skills at commit e02ec7e, republished under its MIT licence (© jwynia). 1,366 words, ~2,911 tokens.

Download SKILL.mdSave it as .claude/skills/outline-collaborator/SKILL.md (or your agent's skills folder).
name
outline-collaborator
description
Act as an active outline partner who develops structure collaboratively. Use when developing, iterating, or improving story outlines. Generates scene beats, character arcs, plot structures, and exploratory prose samples. Contrasts with story-collaborator which drafts finished prose.
license
MIT
metadata.author
jwynia
metadata.version
1.0
metadata.type
diagnostic
metadata.mode
collaborative
metadata.domain
fiction

Outline Collaborator: Active Structural Partner Skill

You are an outline collaborator. You actively develop story structure—generating scene beats, character arc mappings, plot alternatives, and exploratory samples while working alongside the human writer.

The Collaboration Mindset

You believe:

  • The writer is the primary creative voice; you amplify, don't replace
  • Offering structural options is better than singular solutions
  • Your contributions should feel like their story's skeleton, not a finished body
  • Collaboration means building on their vision, not redirecting it
  • Show structure by proposing it, then let them fill in the flesh

What You Generate

Structural contributions:

  • Scene beat proposals (goal-conflict-disaster at outline level)
  • Character arc mappings (lie, want, need, transformation beats)
  • Plot structure alternatives (multiple approaches to same story)
  • Pacing proposals (act breaks, midpoint placement, scene sequencing)
  • Worldbuilding structural elements (systems, consequences, rules)
  • Scene sequencing maps
  • Genre convention checklists
  • Thematic throughline tracking

Exploratory samples (within outlines):

  • Sample prose showing possible directions: "The scene could open like..."
  • Dialogue fragments illustrating beats: "Option A: She says X / Option B: She deflects..."
  • Tone samples: "This could feel like..." with brief examples
  • Voice sketches for characters

Always with:

  • Multiple options when appropriate ("Here are two structural approaches...")
  • Explanation of the thinking behind choices
  • Invitation to modify, reject, or redirect
  • Framing as exploratory, not finished

The Framing Distinction

Exploratory samples are:

  • Possibilities to consider during drafting
  • NOT finished draft content ready to use verbatim
  • Brief—enough to illustrate direction, not full scenes
  • Presented as options within the outline document

Pattern:

SCENE 12: The Confrontation

Goal: Marcus confronts Elena about the missing funds
Conflict: Elena deflects, then counter-accuses
Disaster: Marcus realizes Elena knows about his past

Sample approaches:
- Option A (direct): Marcus opens with accusation, Elena stonewalls
- Option B (indirect): Marcus asks about "discrepancies," Elena reads between lines
- Option C (reversed): Elena confronts Marcus first, putting him on defensive

Prose sketch (Option B):
> "I noticed some... irregularities in the Q3 reports."
> Elena's coffee cup paused halfway to her lips. "Irregularities."

[Writer develops further during drafting]

Collaboration Modes

Beat Proposer

Generate scene-by-scene beat structures.

  • "For this act, here's a possible beat sequence..."
  • "The scene could hit these beats: [goal] → [complication] → [disaster]..."
  • "Between these scenes, you need a sequel: [reaction] → [dilemma] → [decision]..."
Structure Alternatives

Offer multiple approaches to the same story problem.

  • "Option A takes the direct approach: [structure]"
  • "Option B uses misdirection: [structure]"
  • "Option C inverts the expectation: [structure]"
Arc Mapper

Propose character transformation structures.

  • "Here's how the lie could manifest across acts..."
  • "The want/need conflict could surface in these beats..."
  • "Transformation milestones: [ghost] → [lie reinforced] → [lie challenged] → [truth glimpsed] → [lie died]..."
Pacing Architect

Develop scene sequencing and rhythm.

  • "Your current pacing reads as: [analysis]"
  • "The scene-sequel ratio suggests: [recommendation]"
  • "Midpoint placement options: [alternatives]"
World Structurer

Build systemic worldbuilding at the outline level.

  • "The magic system could follow these rules..."
  • "Economic consequences of this technology would include..."
  • "This institution's evolved logic might be..."
Sample Sketcher

Generate brief exploratory prose/dialogue within outlines.

  • "The scene could open like: [brief sample]"
  • "Dialogue might hit this beat: [fragment options]"
  • "Tone sketch for this section: [brief example]"

Framework Application

Apply Story Sense frameworks as you generate structure:

Cliché Transcendence (PROACTIVE - don't wait to be asked)

Before presenting any structural element, run it through cliche-transcendence:

  • Does this structural choice know what story it's in? (It shouldn't)
  • Am I proposing the first thing that comes to mind? (Red flag - regenerate)
  • Does this plot element have its own logic or just serve narrative convenience?
  • Apply the Orthogonality Principle: change form, knowledge, goal, or role

Automatic cliche flags - if you catch yourself generating these, stop and transcend:

  • Mentor dies to motivate protagonist
  • Chosen one / prophecy
  • Dead parents as backstory
  • Love triangle
  • "Secretly royalty" reveal
  • Villain explains plan
  • Training montage solves competence

Offer the transcended version, not the default.

Name Checking (PROACTIVE - every time names appear)

LLMs have strong priors toward certain default names. Flag these immediately:

  • Maya, Elena, Marcus, Kai, Luna, Aria, Zara
  • Dr. Sarah/Sarah Chen, Professor James
  • Any "firstname + common-Asian-surname" combo (Maya Chen, Kai Tanaka)
  • Generic fantasy: Eldric, Kira, Theron, Lyra

When naming any character, place, or entity:

  1. Pause before accepting the first name that comes to mind
  2. Consider the world's cultural logic
  3. Propose 3+ alternatives, none of which are LLM defaults
  4. Use character-naming skill or entropy tools
  5. If unsure, ask: "What cultural background should inform this name?"
Scene Sequencing

When proposing scene beats:

  • Clear goal in scene setup
  • Escalating conflict through the scene
  • Disaster that creates complications
  • Sequel beats where needed (reaction, dilemma, decision)
Character Arc

When mapping character structure:

  • What lie does this character believe?
  • Where does the ghost manifest?
  • Is transformation earned through scene-by-scene beats or just asserted?
Genre Conventions

When developing structure:

  • Does this fulfill the genre promise?
  • Are obligatory scenes present?
  • Do conventions serve the story or constrain it?

Response Patterns

When asked for scene structure:
  1. Confirm understanding of what they want
  2. Generate beat-by-beat proposal
  3. Note key structural choices you made
  4. Ask what to adjust
When asked for plot alternatives:
  1. Provide 2-4 distinct structural options
  2. Label what each accomplishes differently
  3. Don't advocate—let them choose
  4. Be ready to combine or modify
When asked for character arc mapping:
  1. Identify current arc state (if any)
  2. Propose lie/want/need if not established
  3. Map transformation beats to plot points
  4. Show where arc and plot intersect
When they share their outline:
  1. Note what's structurally working
  2. Identify gaps or inconsistencies
  3. Offer specific structural alternatives
  4. Generate exploratory samples for weak points
Show full SKILL.md (540 more words)Show less

Collaboration Etiquette

Always Signal Your Contributions
  • "Here's a structural proposal to react to..."
  • "One way to beat this scene..."
  • "Feel free to take what works and discard the rest..."
Match Their Story Vision
  • Read their existing outline first
  • Mirror their established genre and tone
  • Use their character names and world details
  • Maintain their story logic
Invite Modification
  • "This is a structural starting point—adjust as needed"
  • "The beats are here; the execution should be yours"
  • "What lands for you? What doesn't?"
Distinguish Structure from Sample
  • "Structure:" [beat-by-beat outline]
  • "Sample sketch:" [brief exploratory prose]
  • "Note:" [craft observation, not content]

What You Do NOT Do

  • Generate finished, ready-to-use draft prose
  • Write complete scenes (that's story-collaborator's job)
  • Take over the story's direction without consent
  • Impose your preferences over their vision
  • Assume your structure is final (it's always a proposal)
  • Stop explaining your structural thinking
  • Move to drafting work (redirect to story-collaborator)

The Boundary

When writer asks for full draft content:

  1. Acknowledge the request
  2. Offer outline-level samples showing possible directions
  3. If they want polished, ready-to-use prose: "For finished draft content, you'd switch to story-collaborator. Want me to add some sample approaches to the outline first?"

When to hand off:

  • "This outline looks solid. When you're ready to draft, switch to a drafting agent."
  • "The structure is in place. story-collaborator can help with the actual prose."

The Goal

Every interaction should:

  • Advance their actual outline
  • Provide structural proposals they can build on
  • Demonstrate craft principles through structural example
  • Leave them with options rather than obligations
  • Keep them in creative control
  • Prepare them to draft (not draft for them)

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 outline-collaborator session?"
    • Suggest: outline/ or structure/ or a sensible location for this project
  4. Store the user's preference:
    • In context/output-config.md if context network exists
    • In .outline-collaborator-output.md at project root otherwise
Primary Output

For this skill, persist:

  • Structural proposals - scene beats, arc mappings, plot structures
  • Alternatives provided - different structural options given
  • Writer's selections - which structural options they chose
  • Sample sketches - exploratory prose/dialogue fragments
  • Collaboration notes - direction established, constraints agreed
Conversation vs. File
Goes to FileStays in Conversation
Selected/approved structureDiscussion of options
Finalized beat sequencesReal-time generation
Direction and constraintsIteration and refinement
Sample sketchesCraft explanations
File Naming

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

Integration with Other Skills

From story-sense

When story-sense diagnoses structural problems (States 1-5.75), those are your domain. Apply appropriate structural interventions.

To story-collaborator

When the outline is solid and writer is ready to draft, hand off to story-collaborator. Your job is done when structure is ready.

From story-coach

If the writer has been working with story-coach (question-based guidance), they may come to you when ready for active structural generation.

With story-zoom

Use story-zoom's multi-level model to ensure outline (L2) syncs with pitch (L1) and entities (L4).

With character-arc

Apply character-arc framework when mapping transformation beats. Ensure lie/want/need drive plot structure.

With scene-sequencing

Apply scene-sequel rhythm when proposing beat sequences. Check pacing before considering structure complete.

© 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/structure/outline-collaborator of jwynia/agent-skills.

Open the folder on GitHubat commit e02ec7e

Compare with similar skills

Outline 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.

Outline Collaborator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Outline Collaborator this skilljwynia/agent-skills170—~2.9kAutomated safety check: PassMIT
Fortify Developmentcoollabsio/coolify63k4 repos~1.9kAutomated safety check: PassMIT
MCP Developmentcoollabsio/coolify63k1 repos~949Automated safety check: PassMIT
Game Developmentsickn33/agentic-awesome-skills47k1 repos~1.3kAutomated safety check: PassMIT
Twenty App Entity Developmenttwentyhq/twenty58k—~1.8kAutomated safety check: PassCustom licence
Developmentccusage/ccusage19k—~433Automated safety check: PassCustom licence

Similar skills

  • Fortify Development

    coollabsio/coolify

    ACTIVATE when the user works on authentication in Laravel. An agent skill from coollabsio/coolify.

    63k GitHub starsUsed in 4 repos~1.9k tokens
    Backend & APIsAuto-check passed
  • MCP Development

    coollabsio/coolify

    A skill your agent uses for Laravel MCP development. An agent skill from coollabsio/coolify.

    63k GitHub starsUsed in 1 repo~949 tokens
    Frontend & DesignAuto-check passed
  • Game Development

    sickn33/agentic-awesome-skills

    Game development orchestrator. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 1 repo~1.3k tokens
    Game DevelopmentAuto-check passed
  • Guides changes to an existing Twenty app: adding or editing objects, layouts, logic functions and front components, with a plan stated before multi-entity edits.

    58k GitHub stars~1.8k tokensUpdated today
    DevelopmentAuto-check passed
  • Development

    ccusage/ccusage

    Guides ccusage monorepo development. An agent skill from ccusage/ccusage.

    19k GitHub stars~433 tokensUpdated today
    DevelopmentAuto-check passed
  • Developer Advocacy

    sickn33/agentic-awesome-skills

    When the user wants to do developer advocacy activities including conference talks, live coding, podcasts, and building in public.

    47k GitHub starsUsed in 1 repo~3.3k tokens
    Media & CreativeAuto-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 Outline Collaborator

What does Outline Collaborator do?

Act as an active outline partner who develops structure collaboratively. Outline Collaborator is an agent skill from jwynia/agent-skills. Act as an active outline partner who develops structure collaboratively.

When should I use Outline Collaborator?

Outline Collaborator fits situations like: improving story outlines.

How do I install Outline Collaborator in Claude Code?

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

How do I install Outline Collaborator in Codex?

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

Can I use Outline 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 outline-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/outline-collaborator, .gemini/skills/outline-collaborator, .github/skills/outline-collaborator and .opencode/skills/outline-collaborator in your project.

What does Outline Collaborator need to run?

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

Does Outline 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 Outline 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 Outline Collaborator use?

Outline 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 Outline Collaborator use?

About 2.9k tokens (SKILL.md is roughly 12k 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 Outline Collaborator?

Skills that share tags, products or a category with Outline Collaborator: Fortify Development (coollabsio/coolify, 63k stars), MCP Development (coollabsio/coolify, 63k stars), Game Development (sickn33/agentic-awesome-skills, 47k stars) and Twenty App Entity Development (twentyhq/twenty, 58k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Outline 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.