Token导航 LogoToken导航

Agent Skill · 研究检索

writing-stickiness(书写粘性)

用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。它适合让 Agent 提炼结构、补齐章节、统一术语、检查链接或把零散材料整理成可读文档。使用时应保留项目已有事实、命令和路径,不要把未确认的信息写成确定结论;涉及对外文案时,还需要控制语气,避免过度营销或夸大能力。

writing-stickiness 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,权限为只读;许可证信息还不明确,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 44,750。

总安装 894周安装 38GitHub Stars 85下载 313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
unknown

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:writing-stickiness(书写粘性)
来源仓库:https://github.com/lyndonkl/claude
仓库路径:skills/writing-stickiness
安装命令:
npx skills add https://github.com/lyndonkl/claude --skill writing-stickiness
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。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/lyndonkl/claude --skill writing-stickiness

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。

用于分析并提升内容的吸引力和留存效果。适合产品文案和用户体验相关文档。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。使用时需结合用户行为数据调整策略。建议人工评估实际转化效果。

writing-stickiness 属于研究检索类 Skill,可作为该场景下的辅助能力补充。安装方式:通过 npx 从 GitHub 仓库添加技能。

来源仓库内路径:skills/writing-stickiness

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/lyndonkl/claude --skill writing-stickiness;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

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

writing-stickiness 怎么安装?

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

writing-stickiness 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。

writing-stickiness 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

writing-stickiness 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

writing-stickiness 用的人多吗?

公开数据是累计安装 894 次,近一周安装 38 次,下载 313 次,GitHub 85 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。

writing-stickiness 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。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 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。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 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
writing-stickiness

书写粘性 · 本页

89485只读未明确通过

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

Writing Stickiness Enhancement

Table of Contents

Related skills: Use writing-structure-planner for planning structure, writing-revision for prose revision, writing-pre-publish-checklist for final quality checks.

Core Principles

  1. Six dimensions of stickiness: Simple, Unexpected, Concrete, Credible, Emotional, Stories
  2. Diagnose before treating: Score current stickiness first, then improve weakest areas
  3. Not all principles are equal: Some matter more for certain contexts - prioritize accordingly
  4. Concrete beats abstract: Brains think in images, not abstractions
  5. Individuals beat statistics: One person's story moves people more than millions in data

Workflow

Copy this checklist and track your progress:

Stickiness Enhancement:
- [ ] Step 1: Analyze against SUCCESs framework
- [ ] Step 2: Improve weak principles
- [ ] Step 3: Score and refine

Before starting: Review resources/success-model.md for the complete SUCCESs framework with all 6 principles, stickiness scorecard, and before/after examples.

Analyze the entire document first and output findings to an analysis file in the current directory, then read that file to make improvements. This ensures complete coverage.

Step 1: Analyze against SUCCESs framework

Step 1.1: Read entire draft. Create analysis file writer-stickiness-analysis.md assessing the document against all 6 SUCCESs principles:

  • Simple (0-3): Identify core message in 12 words or fewer. List competing messages. Rate clarity and focus.
  • Unexpected (0-3): Identify surprise elements or curiosity gaps. Note where expectations could be violated. Rate attention-getting power.
  • Concrete (0-3): List visualizable details. Identify abstract sections needing examples. Rate sensory specificity.
  • Credible (0-3): Identify credibility sources (statistics, testability, authority, vivid details). Note unsupported claims. Rate believability.
  • Emotional (0-3): Identify emotional connections and personal benefits. Note where motivation could be strengthened. Rate "care factor."
  • Stories (0-3): Identify story or human elements. Note opportunities to add narrative. Rate mental simulation potential.

Step 1.2: Calculate total current stickiness score out of 18. Present findings to user.

See each principle's section in resources/success-model.md for detailed scoring guidance.

Step 2: Improve weak principles

Step 2.1: Read analysis file. Identify the 2-3 weakest principles (scored 0-1).

Step 2.2: Work through entire draft making targeted improvements for each weak principle:

  • Simple: Refine core message to 12 words or fewer. Strip competing ideas.
  • Unexpected: Add surprise or curiosity gaps. Violate reader expectations.
  • Concrete: Add visualizable details and specific examples. Replace abstractions.
  • Credible: Add statistics (human-scale), testability ("try it yourself"), authority, or vivid details.
  • Emotional: Strengthen personal benefits and emotional connections. Focus on individuals, not masses.
  • Stories: Add narrative or human elements. Use challenge, connection, or creativity plots.

Step 2.3: Present improved version to user with changes highlighted.

See resources/success-model.md for specific techniques and examples for each principle.

Step 3: Score and refine

Step 3.1: Score the revised message using the Stickiness Scorecard.

Step 3.2: Aim for 12+/18 for good stickiness, 15+/18 for excellent. If score is below 12, identify the weakest 2 principles and do another improvement pass focusing on those.

Step 3.3: Present final scored version with before/after comparison.

See resources/success-model.md - Complete Example for transformation patterns.

Validate using resources/evaluators/rubric_stickiness.json. Minimum standard: Average score >= 3.5.

SUCCESs Framework Overview

PrincipleKey QuestionTechnique
SimpleWhat's the ONE core idea?Commander's intent in 12 words
UnexpectedWhat will surprise readers?Schema violation + curiosity gaps
ConcreteCan readers visualize it?Sensory details, specific examples
CredibleWhy should readers believe it?Human-scale stats, testability
EmotionalWhy should readers care?Individual focus, identity appeal
StoriesCan readers simulate the experience?Challenge/connection/creativity plots

Scoring: Each principle rated 0-3. Total out of 18. Target 12+ for good, 15+ for excellent.

Guardrails

Requirements:

  1. Score before improving: Always analyze and score the current state before making changes
  2. Target weakest first: Focus improvements on the lowest-scoring principles
  3. Preserve accuracy: Never sacrifice truthfulness for stickiness - credibility matters
  4. Context-appropriate: Not every piece needs maximum stickiness - match to purpose
  5. Re-score after improving: Always score the revised version to measure improvement

Common pitfalls:

  • Improving already-strong principles while ignoring weak ones
  • Adding surprise that's random rather than relevant to the core message
  • Using statistics that are too large to grasp (billions, trillions)
  • Focusing on masses instead of individuals for emotional appeal
  • Telling instead of showing when adding stories

Quick Reference

Key resources:

Inputs required:

  • Draft text or message to enhance
  • Target audience (if known)
  • Context (presentation, article, email, pitch, etc.)

Outputs produced:

  • Stickiness analysis with per-principle scores
  • Improved version targeting weak principles
  • Before/after comparison with score improvement

平台分布

Codex

35.05%
按下载量换算110

Claude

27.24%
按下载量换算85

Cursor

18.67%
按下载量换算58

Gemini CLI

9.43%
按下载量换算30

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills