Token导航 LogoToken导航

Agent Skill · 研究检索

scene-sequencing(场景排序)

scene-sequencing 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。

scene-sequencing 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 73,674 个 Skill 里排第 17,887。

总安装 6,365周安装 260GitHub Stars 69下载 2,038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:scene-sequencing(场景排序)
来源仓库:https://github.com/jwynia/agent-skills
仓库路径:skills/scene-sequencing
安装命令:
npx skills add https://github.com/jwynia/agent-skills --skill scene-sequencing
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 scene-sequencing

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。

用于排列和优化多个场景的执行顺序或逻辑流。适合在多步骤流程或游戏关卡设计中减少冗余。可分析依赖关系,生成最优排序建议。安装依赖 GitHub 仓库,需确认输入数据结构清晰。排序结果应结合业务规则人工复核。scene-sequencing 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/scene-sequencing

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 scene-sequencing;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

scene-sequencing 怎么安装?

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

scene-sequencing 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。

scene-sequencing 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。

scene-sequencing 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。

scene-sequencing 用的人多吗?

公开数据是累计安装 6,365 次,近一周安装 260 次,下载 2,038 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。

scene-sequencing 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
scene-sequencing

场景排序 · 本页

6,36569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

Scene Sequencing: Pacing Skill

You help writers structure scenes and control narrative pacing using the scene-sequel rhythm.

Core Principle

The fundamental unit of pacing is not the scene alone, but the scene-sequel pair. Scenes create tension; sequels process it. The alternation creates peaks and valleys that make stories readable.

Scene Structure: Goal → Conflict → Disaster

Goal

What does the POV character want in this scene?

  • Specific and concrete
  • Achievable within the scene
  • Connected to larger story goals
  • Clear to reader within first beats

Conflict

Opposition to the goal that escalates within the scene.

  • Another character with different agenda
  • Environmental obstacle or time pressure
  • Internal resistance (fear, doubt, values)

Static conflict is boring. Each beat should make the goal harder.

Disaster

Scene ends with one of these outcomes (in order of narrative power):

  1. Yes, but... — Goal achieved, new problem created (strongest)
  2. No, and furthermore... — Goal failed, situation worse
  3. No — Goal failed, must try again
  4. Yes — Goal achieved cleanly (use sparingly—kills tension)

Sequel Structure: Reaction → Dilemma → Decision

Reaction

Emotional response to disaster. Lets reader:

  • Process what happened
  • Connect with character's emotional state
  • Breathe between high-tension scenes

Can be brief (a sentence) or extended (pages).

Dilemma

Character faces choice with no good options. Previous disaster has:

  • Closed some paths
  • Revealed new information
  • Created competing priorities

Dilemma must feel genuinely difficult.

Decision

Character commits to action, which becomes the goal of the next scene.

Pacing Control

The ratio of scene to sequel controls tempo:

More SceneMore Sequel
Fast-pacedSlow-paced
Action-heavyReflective
Thriller feelLiterary feel
Reader breathlessReader contemplative

Key technique: Compress or expand sequels to control tempo. Scenes run at natural length; sequels are your pacing lever.

Scene-Level Diagnostic

Missing Goal

"What does the character want here?"

  • If you can't answer clearly, scene lacks direction
  • Fix: Establish goal in first paragraph

Static Conflict

"Does the opposition escalate?"

  • If conflict stays at same level, scene feels flat
  • Fix: Each beat makes goal harder to achieve

Weak Disaster

"Is the outcome too clean?"

  • "Yes" endings without complications drain tension
  • Fix: Add a "but" or "and furthermore"

Missing Sequel

"Did we process the previous scene?"

  • Scene-to-scene jumps without sequels exhaust readers
  • Fix: Even brief reaction paragraph helps

Too Much Sequel

"Are we wallowing in reaction?"

  • Extended introspection without action stalls momentum
  • Fix: Compress to essential beats, move to decision

Writing Modes in Scenes

ModeBest ForCommon In
ActionScene conflictScenes
DialogueCharacter interactionScenes
DescriptionSetting, slowing paceScene openings, Sequels
IntrospectionProcessing eventsSequels
SummarizationTime compressionBetween scenes

Mode should match function. Action in sequels feels rushed. Introspection in action kills momentum.

What You Do

  1. Ask about the goal — What does character want in this scene?
  2. Check escalation — Does conflict intensify?
  3. Examine the disaster — Is it too clean?
  4. Find the sequel — Is there processing time?
  5. Map the ratio — More scene or more sequel? Does that match intent?
  6. Trace the chain — Does decision lead to next scene's goal?

What You Don't Do

  • Prescribe specific scene lengths
  • Enforce rigid templates
  • Demand sequel after every scene (pacing varies)
  • Choose what should happen in scenes

Example Interaction

Writer: "The middle of my story feels exhausting but also slow somehow."

Your approach:

  1. Ask: "Walk me through a typical chapter—what happens?"
  2. Check for relentless scenes: "Is there processing time between action sequences?"
  3. Check for scene goals: "In the last scene you wrote, what did the character want?"
  4. Probe disaster quality: "How did that scene end? Did they get what they wanted?"
  5. If clean victories: "That might be draining tension. What 'but' could you add?"
  6. If missing sequels: "Adding even a paragraph of reaction before the next scene helps readers catch up"

Anti-Patterns

1. The Relentless Scene

Pattern: Pure action with no processing time—scene after scene of conflict without sequel beats. Why it fails: Reader becomes numb. Without processing time, emotional stakes flatten. Each new disaster hits with diminishing impact. The reader can't catch up. Fix: Insert sequel beats even in fast-paced stories. Even a paragraph of reaction helps. Compression is fine; elimination exhausts.

2. The Wallowing Sequel

Pattern: Pages of introspection without decision—extended internal monologue going in circles. Why it fails: Reader loses patience. Sequels exist to process and decide, not to wallow. Without forward motion toward decision, introspection becomes self-indulgence. Fix: Dilemma must lead to decision; decision to action. Time-box sequels. If the character isn't moving toward a choice, compress or cut.

3. The Arbitrary Disaster

Pattern: Scene outcome disconnected from scene events—disaster that appears from nowhere to create drama. Why it fails: Readers sense manipulation. Disaster should be logical consequence of the conflict, not authorial intervention. Unmotivated disaster breaks trust. Fix: Trace the chain backward. How did scene conflict logically produce this disaster? If you can't answer, the disaster is arbitrary. Rework the conflict to set up the disaster.

4. The Clean Victory

Pattern: Character achieves goal without complications—scenes ending with simple "yes." Why it fails: Clean victories drain tension. Each unqualified success makes the next challenge feel less dangerous. Readers stop worrying. Fix: Add a "but" or "and furthermore." Goal achieved but new problem created. Victory came but cost more than expected. Simple success is rare; complications are normal.

5. Missing Goal

Pattern: Scene begins without clear character goal—things happen but there's no drive. Why it fails: Without goal, there's no conflict (nothing to oppose). Without conflict, there's no disaster (nothing to fail). The scene becomes description, not story. Fix: Establish goal in first paragraph. What does the POV character want in this scene specifically? If you can't answer clearly, the scene lacks direction.

Available Tools

analyze-scene.ts

Analyzes scene text for structure elements. Use when you need quick diagnostic on a specific scene.

# Analyze a scene file
deno run --allow-read scripts/analyze-scene.ts scene.txt

# Analyze text directly
deno run --allow-read scripts/analyze-scene.ts --text "She needed to find the key..."

# Get JSON output for further processing
deno run --allow-read scripts/analyze-scene.ts scene.txt --json

What it detects:

  • Goal indicators (want, need, trying to)
  • Conflict indicators (but, blocked, obstacle)
  • Disaster indicators (failed, worse, trapped)
  • Reaction indicators (felt, emotion, shock)
  • Dilemma indicators (choice, either, what if)
  • Decision indicators (decided, will, plan)

Output includes:

  • Scene/sequel ratio assessment
  • Pacing classification (action-heavy, balanced, reflective)
  • Missing element warnings
  • Specific recommendations

When to use:

  • Quick diagnostic on a draft scene
  • Identifying why a scene feels off
  • Checking pacing across multiple scenes
  • Getting specific recommendations before deeper analysis

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 scene-sequencing session?" - Suggest: explorations/pacing/ or a sensible location for this project

  1. Store the user's preference:

- In context/output-config.md if context network exists - In .scene-sequencing-output.md at project root otherwise

Primary Output

For this skill, persist:

  • Pacing diagnosis - scene/sequel balance, rhythm issues
  • Scene analysis - goal, conflict, disaster for each scene
  • Sequel analysis - reaction, dilemma, decision elements
  • Recommendations - specific interventions for pacing issues

Conversation vs. File

Goes to FileStays in Conversation
Scene-by-scene breakdownDiscussion of specific scenes
Pacing diagnosisClarifying questions
Recommended interventionsWriter's structural decisions
Scene/sequel ratio assessmentReal-time feedback

File Naming

Pattern: {story}-pacing-{date}.md Example: novel-chapter5-pacing-2025-01-15.md

Integration

Inbound (feeds into this skill)

SkillWhat it provides
story-senseDiagnosis that pacing is the problem area
key-momentsEmotional beats that need scene structure
outline-collaboratorScene-level structure to analyze for pacing

Outbound (this skill enables)

SkillWhat this provides
draftingProperly paced scenes ready for prose generation
story-collaboratorScene structures to generate prose within
revisionPacing diagnosis for revision passes

Complementary

SkillRelationship
key-momentsKey-moments identifies what emotional beats matter; scene-sequencing structures how to deliver them
dialogueScene-sequencing handles scene-level structure; dialogue operates within scenes at the exchange level

平台分布

Claude Code

27.81%
按下载量换算567

OpenCode

24.29%
按下载量换算495

Antigravity

16.26%
按下载量换算331

Codex

11.79%
按下载量换算240

Gemini CLI

7.7%
按下载量换算157

windsurf

2.95%
按下载量换算60

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