菜单
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.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Search the web using Brave Search API for fast, privacy-respecting results with localization, freshness filtering, and extra snippets. Use when you need web search results with country/language targeting or time-based filtering. Requires BRAVE_API_KEY. Keywords: brave, web search, localized search, privacy search, freshness filtering.
Build and publish npm packages using Bun as the primary toolchain with npm-compatible output. Use when the user wants to create a new npm library, set up a TypeScript package for publishing, configure build/test/lint tooling for a package, fix CJS/ESM interop issues, or publish to npm. Covers scaffolding, strict TypeScript, Biome + ESLint linting, Vitest testing, Bunup bundling, and publishing workflows. Keywords: npm, package, library, publish, bun, bunup, esm, cjs, exports, typescript, biome, vitest, changesets.
Build and publish npx-executable CLI tools using Bun as the primary toolchain with npm-compatible output. Use when the user wants to create a new CLI tool, set up a command-line package for npx execution, configure argument parsing and terminal output, or publish a CLI to npm. Covers scaffolding, citty arg parsing, sub-commands, terminal UX, strict TypeScript, Biome + ESLint linting, Vitest testing, Bunup bundling, and publishing workflows. Keywords: npx, cli, command-line, binary, bin, tool, bun, citty, commander, terminal, publish, typescript, biome, vitest.
Integrate installed skill usage guidance into project CLAUDE.md/AGENTS.md based on project context. Use when skills are installed but agents don't know when to use them, when setting up a new project with skills, or when updating guidance after adding skills.
Synthesize new works from extracted functional DNA documents. Use when adapting a source work to a new context, when combining multiple source extractions, or when generating variations that preserve function while changing form.
Diagnose book marketing copy problems and generate platform-optimized blurbs, descriptions, taglines, and query pitches. Use when marketing copy feels weak, when descriptions aren't converting, or when starting marketing from scratch.
| 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","version":"1.0","type":"diagnostic","mode":"diagnostic+generative","domain":"fiction"} |
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).
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.
The 3-5 most common expressions of any narrative need:
Problems:
Elements at 60-80% familiarity that maintain function while adding specificity:
When you catch yourself reaching for an element, document:
Ask: "What does this element actually do for my story?"
| Functional Core | What It Provides |
|---|---|
| Stakes | Something valuable at risk |
| Pressure | Force preventing abandonment |
| Sympathy | Reason readers connect |
| Complexity | Competing obligations |
| Expertise | Justified knowledge/skill |
| Access | Legitimate presence in spaces |
| Time pressure | Urgency for action |
| Moral weight | Ethical complexity |
Example: Sick parent provides financial pressure, emotional stakes, time pressure, sympathy
Identify the 3-5 most common ways stories achieve this function.
"Can't quit job" pressure:
Generate alternatives using these techniques:
A. Adjacent Substitution Replace common with related but less common:
B. Complication Layering Add unexpected dimensions:
C. Ironic Inversion Flip expected dynamics:
D. Category Jumping Find different category, same pressure:
E. Specificity Injection Add highly specific details:
Test your statistical edge choice:
High Fertility Indicators:
Low Fertility Indicators:
| Need | Statistical Center | Statistical Edge |
|---|---|---|
| Compromised protagonist | Alcoholic ex-cop, grieving widower | Failed authenticator, documentary subject |
| Femme fatale | Seductive client with hidden agenda | Ambitious student filmmaker, efficiency expert |
| Corruption | Police corruption, mob | Authentication boards, gallery collusion |
| Need | Statistical Center | Statistical Edge |
|---|---|---|
| Meeting obstacle | Different classes, same job competition | Anonymous online enemies, parallel lives same building |
| Keeping apart | Misunderstanding, ex returns | Synchronized schedules never overlap, incompatible sleep disorders |
| Need | Statistical Center | Statistical Edge |
|---|---|---|
| Isolation | Cabin in woods, abandoned hospital | Crowded place where no one speaks your language, underwater station |
| Vulnerability | Phone dead, car won't start | Can't close eyes, makes noise when afraid |
| Pitfall | Problem | Solution |
|---|---|---|
| Pushing Too Far | Emotional core lost | Stay within 60-80% familiarity |
| Complexity Without Purpose | Complications don't generate story | Every push should create fertility |
| Pushing Everything | Cognitive overload | Mix center (stability) with edge (interest) |
| Category Confusion | Functional category changes | Maintain emotional vector while changing expression |
Maintain a three-column document:
| Functional Need | Statistical Center | Statistical Edge Options |
|---|---|---|
| Can't quit job | Sick parent, Debts, Blackmail | Inherited property complications, Only witness, Holds key evidence |
| Professional pressure | Boss, Client, Board | Documentary filmmaker following them, Sibling's success |
| Expertise source | Former specialist, Degree | Failed at adjacent field, Learned through failure |
Create edge elements that connect:
One specific detail forces others:
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.
context/output-config.md in the projectstories/elements/ or explorations/stories/Pattern: {story-name}-statistical-{date}.md
context/output-config.md{story-name}-statistical-{date}.mdTrigger phrases: "transform all default elements", "create fertility chains", "full statistical analysis"
| Task | Agent Type | When to Spawn |
|---|---|---|
| Edge research | general-purpose | When seeking unusual expressions of common needs |
| Story consistency | Explore | When checking edge against existing story elements |
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.
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.
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.
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.
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.
| Skill | What it provides |
|---|---|
| story-sense | Diagnosis that elements feel generic or default |
| brainstorming | Raw material for edge alternatives |
| Skill | What this provides |
|---|---|
| worldbuilding | Unique world elements that avoid genre defaults |
| character-arc | Fresh relationship pressures and stakes |
| dialogue | Specific character circumstances to draw from |
| Skill | Relationship |
|---|---|
| cliche-transcendence | Statistical-distance focuses on the vector/distance method; cliche-transcendence uses the orthogonality principle. Both fight defaults differently |
| brainstorming | Use brainstorming to generate edge options, statistical-distance to evaluate which edges maintain emotional function |