Agent skill

Statistical Distance

by jwynia in jwynia/agent-skills

Transform clichéd story elements by pushing along the emotional vector toward statistical edges.

MITAuto-check passed

Install Statistical Distance

skills CLI
$ npx skills add jwynia/agent-skills --skill statistical-distance -a claude-code

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

GitHub CLI
$ gh skill install jwynia/agent-skills statistical-distance --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/character/statistical-distance .claude/skills/statistical-distance && 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
statistical-distance
GitHub stars
169
Token cost
~3.9k tokens
SKILL.md length
1,801 words
Files
1
Skills in repo
111
Repo updated
First seen
Licence
MIT

At a glance

Transform clichéd story elements by pushing along the emotional vector toward statistical edges.

  • Works in 10 steps: Identify Initial Instinct → Map the Functional Core → List Statistical Center Options → …
  • First instincts are too predictable
  • SKILL.md covers Core Principle, Statistical Center vs.…, The Vector/Distance Method and Genre-Specific Statistical…, plus 8 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Statistical Distance is an agent skill from jwynia/agent-skills. Transform clichéd story elements by pushing along the emotional vector toward statistical edges. Use when first instincts are too predictable, when elements feel generic, or when you need the core methodology for avoiding statistical-center defaults.

Its SKILL.md is about 3.9k 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

  • First instincts are too predictable
  • Elements feel generic
  • You need the core methodology for avoiding statistical-center defaults

Example prompts

  • “/statistical-distance”

Workflow steps

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

  1. Identify Initial Instinct
  2. Map the Functional Core
  3. List Statistical Center Options
  4. Push Toward Statistical Edge
  5. Evaluate Fertility
  6. Edge for Edge's Sake
  7. Losing the Emotional Core
  8. Complexity Confusion
  9. Adjacent Isn't Edge
  10. Fertility Neglect

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

Statistical Distance loads about 3.9k tokens when it runs. Until then it costs about 68 tokens; SKILL.md has 1,801 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~68
When it runs · the whole SKILL.md, loaded when a task matches
~3.9k

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). 1,801 words, ~3,900 tokens.

Download SKILL.mdSave it as .claude/skills/statistical-distance/SKILL.md (or your agent's skills folder).
name
statistical-distance
description
Transform clichéd story elements by pushing along the emotional vector toward statistical edges. Use when first instincts are too predictable, when elements feel generic, or when you need the core methodology for avoiding statistical-center defaults.
license
MIT
metadata.author
jwynia
metadata.version
1.0
metadata.type
diagnostic
metadata.mode
diagnostic+generative
metadata.domain
fiction

Statistical Distance: Cliché Transformation Skill

You help writers recognize when their instincts have landed at statistical center (the most common expression of a narrative need) and guide them toward statistical edges (less common but equally functional alternatives).

Core Principle

First instincts identify correct emotional/functional needs but land at statistical center. Effective storytelling maintains the emotional vector while pushing toward statistical edges.

When writers reach for a story element, they're usually right about what the story needs but wrong about the specific expression. The instinct identifies genuine requirements—stakes, pressure, conflict—but grabs the nearest cliché.

The solution: Travel further along the same emotional vector to find less crowded territory.

Statistical Center vs. Statistical Edge

Statistical Center (Avoid)

The 3-5 most common expressions of any narrative need:

  • Communicate immediately (require no explanation)
  • Work reliably (proven function)
  • Feel "right" (match expectations)
  • Are easily recognized (trigger familiar patterns)

Problems:

  • Reader fatigue
  • Limited fertility (single function)
  • Reduced specificity
  • Predictable trajectories
  • Emotional flatness
Statistical Edge (Target)

Elements at 60-80% familiarity that maintain function while adding specificity:

  • Require some explanation (creating engagement)
  • Generate multiple possibilities (narrative fertility)
  • Feel both familiar and fresh
  • Create unique character/world specificity

The Vector/Distance Method

Step 1: Identify Initial Instinct

When you catch yourself reaching for an element, document:

  • What element did you choose?
  • What narrative function does it serve?
  • What emotional effect does it create?
Step 2: Map the Functional Core

Ask: "What does this element actually do for my story?"

Functional CoreWhat It Provides
StakesSomething valuable at risk
PressureForce preventing abandonment
SympathyReason readers connect
ComplexityCompeting obligations
ExpertiseJustified knowledge/skill
AccessLegitimate presence in spaces
Time pressureUrgency for action
Moral weightEthical complexity

Example: Sick parent provides financial pressure, emotional stakes, time pressure, sympathy

Step 3: List Statistical Center Options

Identify the 3-5 most common ways stories achieve this function.

"Can't quit job" pressure:

  1. Sick family member (medical bills)
  2. Mounting debts (financial crisis)
  3. Blackmail (secret held)
  4. Contract/obligation (legal binding)
  5. Protecting someone (they'll be hurt)
Step 4: Push Toward Statistical Edge

Generate alternatives using these techniques:

A. Adjacent Substitution Replace common with related but less common:

  • Parent → Sibling/Cousin/Mentor/Ex-partner
  • Child → Nephew/Student/Ward
  • Spouse → Business partner/Best friend

B. Complication Layering Add unexpected dimensions:

  • Sick parent → Parent getting better from cursed object
  • Debt → Debt to someone now missing
  • Blackmail → Blackmail about something not actually wrong

C. Ironic Inversion Flip expected dynamics:

  • Hiding addiction → Falsely accused of addiction
  • Owing money → Owed money can't collect
  • Protecting the weak → Protected by the weak

D. Category Jumping Find different category, same pressure:

  • Financial → Reputation management
  • Family obligation → Community responsibility
  • Legal requirement → Social expectation

E. Specificity Injection Add highly specific details:

  • "Sick parent" → "Parent with face blindness who's the only witness"
  • "Mounting debts" → "Inherited deceased spouse's secret day-trading losses"
  • "Being blackmailed" → "Blackmailed by someone wrong about what they think they know"
Step 5: Evaluate Fertility

Test your statistical edge choice:

High Fertility Indicators:

  • Generates multiple subplot possibilities
  • Creates natural conflict with other elements
  • Raises questions that propel investigation
  • Connects to multiple relationships
  • Can evolve through the story

Low Fertility Indicators:

  • Serves single function then disappears
  • Requires constant maintenance
  • Doesn't connect to main plot
  • Creates only one type of scene
  • Has obvious/single resolution

Genre-Specific Statistical Centers and Edges

Noir
NeedStatistical CenterStatistical Edge
Compromised protagonistAlcoholic ex-cop, grieving widowerFailed authenticator, documentary subject
Femme fataleSeductive client with hidden agendaAmbitious student filmmaker, efficiency expert
CorruptionPolice corruption, mobAuthentication boards, gallery collusion
Romance
NeedStatistical CenterStatistical Edge
Meeting obstacleDifferent classes, same job competitionAnonymous online enemies, parallel lives same building
Keeping apartMisunderstanding, ex returnsSynchronized schedules never overlap, incompatible sleep disorders
Horror
NeedStatistical CenterStatistical Edge
IsolationCabin in woods, abandoned hospitalCrowded place where no one speaks your language, underwater station
VulnerabilityPhone dead, car won't startCan't close eyes, makes noise when afraid

Diagnostic Questions

Identifying Statistical Center
  • Could I swap this with 5 other stories unchanged?
  • Does this require zero explanation?
  • Have I seen this exact situation 10+ times?
  • Does this solve only the immediate problem?
  • Would anyone be surprised by this choice?
Confirming Statistical Edge
  • Does this require some explanation?
  • Does this create additional story possibilities?
  • Is this specific to my world/characters?
  • Would this feel fresh to readers?
  • Does this maintain the emotional core?

Common Pitfalls

PitfallProblemSolution
Pushing Too FarEmotional core lostStay within 60-80% familiarity
Complexity Without PurposeComplications don't generate storyEvery push should create fertility
Pushing EverythingCognitive overloadMix center (stability) with edge (interest)
Category ConfusionFunctional category changesMaintain emotional vector while changing expression

The Workspace Method

Maintain a three-column document:

Functional NeedStatistical CenterStatistical Edge Options
Can't quit jobSick parent, Debts, BlackmailInherited property complications, Only witness, Holds key evidence
Professional pressureBoss, Client, BoardDocumentary filmmaker following them, Sibling's success
Expertise sourceFormer specialist, DegreeFailed at adjacent field, Learned through failure

Advanced Techniques

The Fertility Chain

Create edge elements that connect:

  • Sibling is performance artist (family pressure)
  • Who's recreating the painter's work (professional intersection)
  • In shared studio building (community pressure)
  • Funded by suspicious source (conspiracy element)
The Specificity Cascade

One specific detail forces others:

  • If authenticator → needs art world connections
  • If painter was prolific → supernatural paintings are minority
  • If mostly correct → discovering errors is devastating

Implementation Checklist

  • Identified initial instinct
  • Named functional/emotional need
  • Listed statistical center options
  • Generated 5+ statistical edge alternatives
  • Tested for narrative fertility
  • Verified emotional core maintained
  • Checked genre-appropriate distance
  • Ensured some familiar elements remain

The Key Insight

Your instincts about what your story needs are probably right. Your first idea about how to fulfill that need is probably too common. Push along the same vector until you find territory that's yours alone.

Output Persistence

Output Discovery
  1. Check for context/output-config.md in the project
  2. If found, look for this skill's entry
  3. If not found, ask user: "Where should I save statistical distance work?"
  4. Suggest: stories/elements/ or explorations/stories/
Primary Output
  • Functional need - What the story requires
  • Statistical center options - 3-5 most common expressions
  • Statistical edge choices - Alternatives with fertility
  • Workspace document - Three-column tracking table
File Naming

Pattern: {story-name}-statistical-{date}.md

Verification (Oracle)

What This Skill Can Verify
  • Functional core identified - Is the need clear? (High confidence)
  • Center enumeration - Are common options listed? (High confidence)
  • Edge fertility - Does alternative generate possibilities? (Medium confidence)
What Requires Human Judgment
  • Emotional core preserved - Does edge still deliver the feeling?
  • Distance calibration - Too far or not far enough?
  • Genre appropriateness - Does edge fit the story type?
Show full SKILL.md (727 more words)Show less
Oracle Limitations
  • Cannot assess whether edge feels fresh vs. forced
  • Cannot predict reader response to unfamiliar elements

Feedback Loop

Session Persistence
  • Output location: See context/output-config.md
  • What to save: Need, center options, edge choices, reasoning
  • Naming pattern: {story-name}-statistical-{date}.md
Cross-Session Learning
  • Check for prior statistical distance work in this story
  • Ensure different elements use different edge strategies
  • Failed edge choices inform anti-patterns

Design Constraints

This Skill Assumes
  • Element has been identified as too common/clichéd
  • There's a functional need to preserve
  • Story can accommodate some explanation
This Skill Does Not Handle
  • Whether element is actually clichéd - Route to: story-sense
  • Generating raw options - Route to: brainstorming
  • Worldbuilding consistency - Route to: worldbuilding
Degradation Signals
  • Pushing everything to edge (exhausting)
  • Losing emotional core (wrong problem solved)
  • Adjacent substitution without dynamic change

Reasoning Requirements

Standard Reasoning
  • Single element transformation
  • Basic center enumeration
  • Simple fertility check
Extended Reasoning (ultrathink)
  • Full workspace design - [Why: multiple elements need coherent edge strategy]
  • Fertility chain creation - [Why: edge elements should interconnect]
  • Specificity cascade - [Why: one specific detail forces others]

Trigger phrases: "transform all default elements", "create fertility chains", "full statistical analysis"

Execution Strategy

Sequential (Default)
  • Identify instinct before mapping function
  • List center before generating edge
  • Generate edge before testing fertility
Parallelizable
  • Transforming multiple independent elements
  • Research into different edge expressions
Subagent Candidates
TaskAgent TypeWhen to Spawn
Edge researchgeneral-purposeWhen seeking unusual expressions of common needs
Story consistencyExploreWhen checking edge against existing story elements

Context Management

Approximate Token Footprint
  • Skill base: ~3k tokens (method + techniques + workspace)
  • With genre tables: ~4k tokens
  • With advanced techniques: ~4.5k tokens
Context Optimization
  • Focus on current functional need and push technique
  • Genre tables are reference, not required
  • Workspace method is core
When Context Gets Tight
  • Prioritize: Current need, active push technique
  • Defer: Full genre tables, all techniques
  • Drop: Advanced techniques, implementation checklist

Anti-Patterns

1. Edge for Edge's Sake

Pattern: Pushing every element to the statistical edge regardless of whether it serves the story. Why it fails: Not all elements need to be surprising. Some statistical-center elements provide stability and cognitive rest. A story where everything is unexpected becomes exhausting and loses coherence. Fix: Identify which 2-3 elements most need differentiation. Leave supporting elements at statistical center. Mix edge and center strategically.

2. Losing the Emotional Core

Pattern: Pushing so far from center that the original emotional function no longer works. Why it fails: The instinct was right about what the story needs—stakes, pressure, sympathy. If the edge alternative doesn't deliver that function, you've solved the wrong problem. Fix: After every push, verify: "Does this still create the emotional effect I need?" If not, push in a different direction, not further.

3. Complexity Confusion

Pattern: Equating "less common" with "more complicated." Adding layers of explanation to justify an unusual choice. Why it fails: Edge elements should feel natural once established. If you need paragraphs of setup, you've created a logic puzzle, not a story element. The audience spends energy understanding rather than feeling. Fix: Edge elements should require some explanation but click quickly. If it takes more than 2-3 sentences to establish, it's probably too far.

4. Adjacent Isn't Edge

Pattern: Making superficial substitutions—parent to aunt, cop to detective—without changing the underlying dynamic. Why it fails: Same dynamics with different labels. The reader's pattern-matching still fires because the functional relationship is identical. Fix: Change the relationship, not just the label. Aunt who's estranged is still sick-parent dynamics. Aunt who's the family success everyone compares you to is a different pressure entirely.

5. Fertility Neglect

Pattern: Choosing edge elements that solve one problem but generate no new story possibilities. Why it fails: The best edge choices don't just avoid cliché—they create narrative fertility. An element that's unusual but inert is wasted differentiation. Fix: Test edge choices with "And then what?" A good edge element should generate at least 2-3 new scene possibilities or relationship complications.

Integration

Inbound (feeds into this skill)
SkillWhat it provides
story-senseDiagnosis that elements feel generic or default
brainstormingRaw material for edge alternatives
Outbound (this skill enables)
SkillWhat this provides
worldbuildingUnique world elements that avoid genre defaults
character-arcFresh relationship pressures and stakes
dialogueSpecific character circumstances to draw from
Complementary
SkillRelationship
cliche-transcendenceStatistical-distance focuses on the vector/distance method; cliche-transcendence uses the orthogonality principle. Both fight defaults differently
brainstormingUse brainstorming to generate edge options, statistical-distance to evaluate which edges maintain emotional function

© 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/character/statistical-distance of jwynia/agent-skills.

Open the folder on GitHubat commit e02ec7e

Compare with similar skills

Statistical Distance 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.

Statistical Distance compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Statistical Distance this skilljwynia/agent-skills169—~3.9kAutomated safety check: PassMIT
TransformersK-Dense-AI/scientific-agent-skills48k1 repos~2.8kAutomated safety check: NotesApache-2.0
Statistical PowerK-Dense-AI/scientific-agent-skills48k1 repos~4.4kAutomated safety check: NotesMIT
Manuscript Statistics AuditYuan1z0825/nature-skills47k2 repos~2.1kAutomated safety check: PassApache-2.0
Statistical Analystalirezarezvani/claude-skills28k—~2.5kAutomated safety check: PassMIT
Statistical Reportingaiming-lab/AutoResearchClaw15k—~756Automated safety check: PassMIT

Similar skills

  • Transformers

    K-Dense-AI/scientific-agent-skills

    Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audio, and multimodal tasks.

    48k GitHub starsUsed in 1 repo~2.8k tokens
    AI & LLM EngineeringAuto-check: notes
  • Statistical Power

    K-Dense-AI/scientific-agent-skills

    Calculates sample sizes and statistical power for study planning.

    48k GitHub starsUsed in 1 repo~4.4k tokens
    Research & ScienceAuto-check: notes
  • Manuscript Statistics Audit

    Yuan1z0825/nature-skills

    Audits or rewrites the statistical reporting in a manuscript: experimental units, replication, tests, uncertainty and figure legends, without inventing missing details.

    47k GitHub starsUsed in 2 repos~2.1k tokens
    Research & ScienceAuto-check passed
  • Statistical Analyst

    alirezarezvani/claude-skills

    Run hypothesis tests, analyze A/B experiment results, calculate sample sizes, and interpret statistical significance with effect sizes.

    28k GitHub stars~2.5k tokensUpdated 1 mo ago
    Data & AnalyticsAuto-check passed
  • Statistical Reporting

    aiming-lab/AutoResearchClaw

    Statistical test selection, assumption checking, and APA-formatted reporting.

    15k GitHub stars~756 tokensUpdated 1 mo ago
    Data & AnalyticsAuto-check passed
  • Picture Element

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing image assets, markup, and CDN or build transforms related to Use <picture with an <img fallback.

    74k GitHub stars~777 tokensUpdated 3 days ago
    Auto-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.

    169 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.

    169 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.

    169 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.

    169 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.

    169 GitHub stars~2.9k tokensUpdated 7 mo ago
    Auto-check passed
  • PPTX Generator

    jwynia/agent-skills

    Create and manipulate PowerPoint PPTX files programmatically.

    169 GitHub stars~3.1k tokensUpdated 7 mo ago
    Auto-check passed

Questions about Statistical Distance

What does Statistical Distance do?

Transform clichéd story elements by pushing along the emotional vector toward statistical edges. Statistical Distance is an agent skill from jwynia/agent-skills. Transform clichéd story elements by pushing along the emotional vector toward statistical edges.

When should I use Statistical Distance?

Statistical Distance fits situations like: first instincts are too predictable; elements feel generic; you need the core methodology for avoiding statistical-center defaults.

How do I install Statistical Distance in Claude Code?

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

How do I install Statistical Distance in Codex?

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

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

What does Statistical Distance need to run?

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

Does Statistical Distance 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 Statistical Distance 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 Statistical Distance use?

Statistical Distance 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 Statistical Distance use?

About 3.9k tokens (SKILL.md is roughly 16k 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 Statistical Distance?

Skills that share tags, products or a category with Statistical Distance: Transformers (K-Dense-AI/scientific-agent-skills, 48k stars), Statistical Power (K-Dense-AI/scientific-agent-skills, 48k stars), Manuscript Statistics Audit (Yuan1z0825/nature-skills, 47k stars) and Statistical Analyst (alirezarezvani/claude-skills, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Statistical Distance?

jwynia (a GitHub user) maintains it in jwynia/agent-skills, which has 169 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.