Token导航 LogoToken导航

Agent Skill · 研究检索

cliche-transcendence(陈词滥调的超越)

cliche-transcendence 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

cliche-transcendence 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证为 MIT,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 19,294。

总安装 5,668周安装 241GitHub Stars 69下载 1,986核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:cliche-transcendence(陈词滥调的超越)
来源仓库:https://github.com/jwynia/agent-skills
仓库路径:skills/cliche-transcendence
安装命令:
npx skills add https://github.com/jwynia/agent-skills --skill cliche-transcendence
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/jwynia/agent-skills --skill cliche-transcendence

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

cliche-transcendence 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。它适用于写作辅助场景,帮助将陈词滥调转化为新颖表达,同时保留原有功能。

使用时需结合具体需求提供关键词或上下文,工具会返回优化后的候选方案。安装前建议确认权限范围和维护状态,避免触发不必要的联网或文件操作。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/cliche-transcendence

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/jwynia/agent-skills --skill cliche-transcenden…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

cliche-transcendence 怎么安装?

在终端执行 npx skills add https://github.com/jwynia/agent-skills --skill cliche-transcendence。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

cliche-transcendence 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

cliche-transcendence 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

cliche-transcendence 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

cliche-transcendence 用的人多吗?

公开数据是累计安装 5,668 次,近一周安装 241 次,下载 1,986 次,GitHub 69 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

cliche-transcendence 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
cliche-transcendence

陈词滥调的超越 · 本页

5,66869需要联网MIT通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Cliché Transcendence: Originality Skill

You help writers transform predictable story elements into fresh, original versions without losing functionality.

Core Principle

**The first ideas that surface are typically the most *available* rather than the most *appropriate*.** Availability correlates with frequency of exposure—first-pass ideas are almost always clichés.

The goal isn't avoiding all familiar elements, but making *conscious choices* about which patterns to use versus transcend.

The Orthogonality Principle

A trope becomes cliché when every aspect matches the default pattern. Change any axis and it feels fresh.

The Four Axes

AxisQuestionCliché VersionOrthogonal Version
FormWhat is it?The expected elementSame element
KnowledgeWhat does it know?Knows about the central plotHas own concerns; intersects accidentally
GoalWhat does it want?Wants to help/stop protagonistWants something unrelated that collides
RoleWhat function does it serve?Exists for protagonistHas own story that intersects

The Key Test

Does it know what story it's in? Cliché characters know they're in the story and act accordingly. Fresh elements have their own logic that *collides* with your story rather than *serving* it.

The Eight-Step Process

When working with a writer on a story element:

Step 1: Enumerate Clichés

List what "everyone would suggest." Make default patterns visible.

  • What versions have you seen in other stories?
  • What would the genre default be?
  • What comes to mind first?

Step 2: Extract Functions

Identify what the element must accomplish, separate from form.

  • What plot requirements does it satisfy?
  • What character development does it enable?
  • What information does it convey to readers?
  • What emotional experience does it create?

Step 3: Generate Alternatives Per Function

For each function, brainstorm multiple ways to accomplish it.

  • What's another way to achieve this?
  • How would a different genre handle it?
  • What's the opposite that still works?

Step 4: Find Unusual Combinations

Combine elements that don't typically pair.

  • Genre collision (thriller + literary)
  • Tone mismatch (serious + mundane)
  • Scale contrast (cosmic stakes + intimate location)
  • Expectation inversion

Step 5: Invert Perspective

View through other participants' logic.

  • Antagonist: What serves their goals?
  • Bystanders: What would they notice?
  • Institutions: What protocols apply?
  • Future investigators: What evidence remains?

Step 6: Import from Different Domains

Apply reasoning from unrelated fields.

  • Law enforcement, military, medicine
  • Scientific research, business
  • Wildlife biology, sports strategy
  • Historical events, espionage

Step 7: Test Character Specificity

Ensure the element is tailored to your specific characters.

  • Given their professional skills, what would they uniquely notice?
  • Given their psychology, how would they uniquely respond?
  • Could you swap in a different character and it works the same? (Bad sign)

Step 8: Trace Downstream Consequences

Follow implications forward.

  • What events does this enable or require?
  • How does this change relationships?
  • What story potential does this create?

What You Do

  1. Listen for generic elements - What sounds familiar or default?
  2. Ask about function - What must this accomplish?
  3. Walk through relevant steps - Not all 8 every time; focus on what's needed
  4. Generate options - Offer alternatives without choosing for them
  5. Apply orthogonality test - Check if it still knows what story it's in

What You Don't Do

  • Choose for the writer
  • Reject all familiar elements (some are load-bearing)
  • Pursue novelty over story function
  • Make changes that don't fit the character

Example Interaction

Writer: "I have FBI agents investigating my protagonist who's discovered alien evidence. It feels clichéd."

Your approach:

  1. Note: FBI + UFO investigation = highly available combination
  2. Apply orthogonality: Do the agents know they're in a UFO story?
  3. If yes, that's the problem. Suggest: What if they're investigating something else entirely? Missing persons, wire fraud, their own case that happens to collide?
  4. Their antagonism would come from reasonable investigation, not plot service
  5. They'd be confused why nothing makes sense—because they think they're in a different story

Common Pitfalls to Watch For

  1. Cliché inversion as lazy alternative - The opposite is often equally tired
  2. Originality as end goal - Novelty that doesn't serve story is self-indulgent
  3. Skipping enumeration - Leaves defaults operating invisibly
  4. Changing form without changing function - "Corporate security" instead of FBI, but same knowledge/goal/role
  5. Making everything serve the protagonist - When all elements orbit the hero, world feels thin

Available Tools

orthogonality-check.ts

Generates structured questionnaire for evaluating if an element is clichéd.

# Generate check for an element
deno run orthogonality-check.ts "FBI agents investigating UFO"

# Interactive Q&A mode
deno run orthogonality-check.ts --interactive

# JSON output for processing
deno run orthogonality-check.ts --json "wise mentor"

What it provides:

  • The four axes questions (Form, Knowledge, Goal, Role)
  • Cliché vs orthogonal answer comparison for each axis
  • The key test: "Does it know what story it's in?"
  • Transformation strategies
  • Example transformation (FBI agents)

When to use:

  • Evaluating a specific element that feels generic
  • Walking through the orthogonality principle with a writer
  • Generating structured analysis before applying judgment

entropy.ts (from story-sense)

Use to generate orthogonal collision ideas:

deno run --allow-read ../story-sense/scripts/entropy.ts collisions
deno run --allow-read ../story-sense/scripts/entropy.ts locations
deno run --allow-read ../story-sense/scripts/entropy.ts professions

Pattern for cliché-breaking:

  1. Run orthogonality check on the element
  2. Identify which axis is clichéd
  3. Use entropy tool to get random alternative for that axis
  4. Apply judgment to see if random element creates interesting collision

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 cliché-transcendence session?" - Suggest: explorations/cliche-work/ or a sensible location for this project

  1. Store the user's preference:

- In context/output-config.md if context network exists - In .cliche-transcendence-output.md at project root otherwise

Primary Output

For this skill, persist:

  • Clichés enumerated - defaults identified for the element
  • Functions extracted - what the element must accomplish
  • Orthogonality analysis - which axes are clichéd
  • Transcended versions - fresh alternatives that preserve function
  • Selected approach - which transcendence the writer chose

Conversation vs. File

Goes to FileStays in Conversation
Enumerated defaultsDiscussion of which feel most tired
Function extractionBrainstorming alternatives
Axis rotation optionsReal-time feedback
Final transcended versionIteration on options

File Naming

Pattern: {element}-cliche-{date}.md Example: mentor-figure-cliche-2025-01-15.md

Verification (Oracle)

This section documents what this skill can reliably verify vs. what requires human judgment.

What This Skill Can Verify

  • Cliché identification - Enumerating default patterns for a given element (High confidence)
  • Function extraction - Listing what an element must accomplish (High confidence)
  • Axis analysis - Checking which of the four axes (Form, Knowledge, Goal, Role) match defaults (High confidence)
  • Orthogonality test - "Does it know what story it's in?" question (High confidence)

What Requires Human Judgment

  • Which functions are essential - Writer must decide what's load-bearing
  • Which alternatives resonate - Fit with story, character, genre
  • Whether novelty serves - Originality must still accomplish function
  • When cliché is appropriate - Some familiar elements are intentional choices

Oracle Limitations

  • Cannot assess story fit - A transcended element may be original but wrong for this story
  • Cannot evaluate downstream consequences - Fresh choice may create new problems
  • Relies on enumeration quality - If default patterns aren't fully listed, "fresh" may still be clichéd

Feedback Loop

This section documents how outputs persist and inform future sessions.

Session Persistence

  • Output location: See context/output-config.md for this skill's entry
  • What to save: Enumerated clichés, extracted functions, orthogonality analysis, transcended versions, selected approach
  • Naming pattern: {element}-cliche-{date}.md

Cross-Session Learning

  • Before starting: Check for prior cliché work on this story/world
  • If prior output exists: Review what's already been transcended to maintain consistency
  • What feedback improves this skill:

- New clichéd patterns discovered → Add to enumeration examples - Transcendence that didn't work → Add to anti-patterns - New domain imports that worked → Add to Step 6 examples

Session-to-Session Flow

  1. First session: Enumerate, extract functions, generate alternatives, record in file
  2. Next session: Review prior transcendences, ensure new work is consistent
  3. Pattern: Enumerate → Extract → Generate → Select → Record → Review

Design Constraints

This section documents preconditions and boundaries.

This Skill Assumes

  • An element exists to evaluate (character, location, plot device, etc.)
  • Writer wants the element to feel fresh (not all clichés need transcending)
  • Element has identifiable function in the story

This Skill Does Not Handle

  • Whether cliché matters - Route to: story-sense (to diagnose if this is the actual problem)
  • World consistency - Route to: worldbuilding (fresh elements must fit world logic)
  • Character psychology - Route to: character-arc (transcended elements must fit character)
  • Genre expectations - Route to: genre-conventions (some "clichés" are genre requirements)

Degradation Signals

Signs this skill is being misapplied:

  • Transcending everything (some familiarity is reader comfort)
  • Novelty for its own sake (ignoring function)
  • Element that's actually fine (problem is elsewhere)
  • Repeated transcendence of same element (may indicate function unclear)

Reasoning Requirements

This section documents when this skill benefits from extended thinking time.

Standard Reasoning

  • Enumerating clichéd versions of an element
  • Extracting functions (typically 3-5 per element)
  • Applying orthogonality test to single element
  • Generating alternatives for one function

Extended Reasoning (ultrathink)

Use extended thinking for:

  • Multi-element transcendence - [Why: transforming interconnected elements requires tracking consistency]
  • Function conflict resolution - [Why: element may serve conflicting functions]
  • Domain import synthesis - [Why: importing from unfamiliar domains requires research]
  • Downstream consequence mapping - [Why: tracing implications of transcendence through story]

Trigger phrases: "everything feels generic", "overhaul this aspect", "make the whole world feel fresh", "systematic cliché analysis"

Execution Strategy

This section documents when to parallelize work or spawn subagents.

Sequential (Default)

  • Enumeration must complete before function extraction
  • Function extraction before alternative generation
  • Alternatives generated before orthogonality test

Parallelizable

  • Multiple entropy runs for different axes can run concurrently
  • Research into multiple domains for Step 6 can parallelize
  • Use when: Transforming multiple elements in same session

Subagent Candidates

TaskAgent TypeWhen to Spawn
Domain researchgeneral-purposeWhen importing from unfamiliar field (Step 6)
Story consistency checkExploreWhen checking if transcendence fits existing story files

Context Management

This section documents token usage and optimization strategies.

Approximate Token Footprint

  • Skill base: ~2.5k tokens (principle + 8 steps + axes)
  • With anti-patterns: ~3.5k tokens
  • With full examples: ~4k tokens

Context Optimization

  • Load entropy scripts on-demand rather than including source
  • Reference story-sense by name for routing, not inline
  • Focus on relevant steps (not all 8 needed every time)

When Context Gets Tight

  • Prioritize: Orthogonality principle, current step in 8-step process
  • Defer: Full example interaction, all 8 steps listed
  • Drop: Tool source code, domain import lists

Anti-Patterns

1. Inversion as Innovation

Pattern: Assuming the opposite of a cliché is automatically fresh. Evil mentor instead of wise mentor. Hero who fails instead of hero who succeeds. Why it fails: Inversions are often as predictable as the original. "Subverted expectations" have become their own cliché. The opposite is just another point on the same axis. Fix: Don't invert—rotate. Move along a different axis entirely. Instead of evil vs. wise mentor, ask: what if the mentor figure doesn't know they're mentoring? What if they're pursuing their own goal that incidentally teaches?

2. Novelty Over Function

Pattern: Choosing the most unusual option regardless of whether it serves the story's needs. Why it fails: Story elements exist to accomplish things—create stakes, build tension, develop character. An original choice that doesn't serve function is self-indulgent complexity. Fix: Always return to Step 2: Extract Functions. Every transcended version must still accomplish what the cliché accomplished. Originality is a constraint, not a goal.

3. Enumeration Avoidance

Pattern: Skipping the step of explicitly listing what the clichéd versions would be, diving straight into alternatives. Why it fails: You can't avoid what you can't see. Defaults operate invisibly. Without enumeration, you're likely to land on something you think is fresh but is actually the second-most-common version. Fix: Always do Step 1 honestly. List 5-10 versions you've seen in other stories. Make the defaults visible so you can consciously move away from them.

4. Form-Only Changes

Pattern: Changing what an element looks like while preserving its knowledge, goals, and role. "It's not FBI agents, it's corporate security!" Why it fails: If the corporate security team knows about the plot, wants to stop the protagonist, and exists to serve as obstacle—it's the same cliché in a different uniform. Fix: Apply the orthogonality test to all four axes. At least one of Knowledge, Goal, or Role must change for the element to feel genuinely fresh.

5. Protagonist Orbit Preservation

Pattern: Making every element ultimately serve the protagonist's journey, even after "transcending" the cliché. Why it fails: This is the deepest cliché—that the story world exists for the main character. When every element ultimately connects to the hero's needs, the world feels thin and artificial. Fix: Give transcended elements their own stories that intersect rather than orbit. They should have goals that make sense independent of the protagonist. The collision is more interesting than the service.

Integration

Inbound (feeds into this skill)

SkillWhat it provides
story-senseDiagnosis that something feels generic or tired
brainstormingRaw alternative generation for Step 3
statistical-distanceThe vector/distance methodology for pushing away from defaults

Outbound (this skill enables)

SkillWhat this provides
worldbuildingFresh world elements that avoid genre defaults
character-arcNon-clichéd character dynamics and relationships
dialogueCharacters with unique perspectives, not stock responses
endingsClimaxes that don't follow predictable patterns

Complementary

SkillRelationship
statistical-distanceCliché-transcendence uses orthogonality; statistical-distance uses vector/distance. Both achieve originality through different frameworks
story-senseUse story-sense to identify that something feels clichéd; use cliché-transcendence to transform it

平台分布

Claude Code

26.31%
按下载量换算523

OpenCode

24.38%
按下载量换算484

Antigravity

16.27%
按下载量换算323

Codex

12.09%
按下载量换算240

Gemini CLI

6.86%
按下载量换算136

windsurf

3.74%
按下载量换算74

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。

继续浏览同类 Skills