Token导航 LogoToken导航

Agent Skill · 研究检索

section-dividers(部分分隔线)

section-dividers 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。

section-dividers 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,权限为操作浏览器;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 60,207。

总安装 372周安装 16GitHub Stars 3下载 131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:section-dividers(部分分隔线)
来源仓库:https://github.com/b-open-io/gemskills
仓库路径:skills/section-dividers
安装命令:
npx skills add https://github.com/b-open-io/gemskills --skill section-dividers
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/b-open-io/gemskills --skill section-dividers

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。

用于根据关键词或任务目标查找、筛选相关信息,支持快速定位候选结果。适合在研究、资料整理或知识检索类任务中提高信息获取效率。通过 GitHub 仓库安装,使用 npx 命令调用并传入查询参数执行搜索。搜索结果依赖外部数据源,建议结合上下文判断结果的相关性与准确性。

section-dividers 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/section-dividers

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/b-open-io/gemskills --skill section-dividers;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

    它需要操作浏览器,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

section-dividers 怎么安装?

在终端执行 npx skills add https://github.com/b-open-io/gemskills --skill section-dividers。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

section-dividers 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。

section-dividers 需要什么权限?

权限级别是操作浏览器。该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

section-dividers 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。

section-dividers 用的人多吗?

公开数据是累计安装 372 次,近一周安装 16 次,下载 131 次,GitHub 3 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。

section-dividers 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。

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。

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
section-dividers

部分分隔线 · 本页

3723操作浏览器未明确通过

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

Section Dividers

Generate transparent decorative dividers for web page sections.

CRITICAL RULES - Read Before Generating

1. FULL WIDTH Required

  • Strip MUST extend from LEFT EDGE to RIGHT EDGE of image
  • NO floating islands - content spans entire width
  • Add "FULL WIDTH from left edge to right edge" to prompt

2. Cross-Section NOT Reflection

  • TOP edge: Content pointing UPWARD (houses, trees, rooftops)
  • BOTTOM edge: DIFFERENT content pointing DOWNWARD (pipes, caves, roots)
  • NOT a mirror/reflection of the same scene
  • Add "TOP EDGE has [X] pointing UPWARD. BOTTOM EDGE has [Y] pointing DOWNWARD" - use DIFFERENT X and Y

3. SOLID Filled Strip

  • Strip must be SOLID between top and bottom edges
  • NOT hollow, NOT a cave opening, NOT an arch
  • Add "SOLID FILLED strip - not hollow, not a cave"

4. Clean Boundary Required

  • Sharp, clear edge between silhouette content and background
  • High contrast between the two colors
  • If edges are fuzzy or blended = generation failed

5. Content Must NOT Touch Image Edges

  • Content should float in CENTER with background above and below
  • If content touches TOP or BOTTOM of image = JUNK, do not process
  • Verify raw image BEFORE running bg removal

6. Exact Color Matching

  • Background = EXACT parallax color (use analyze-bg.ts)
  • Silhouette = EXACT section CSS color
  • Both colors must be explicitly stated in prompt with hex values

Background Color Strategy

Use a HIGH CONTRAST color from the parallax image's own palette. This ensures:

  1. Clean edges when removing background (high contrast = sharp removal)
  2. No color fringing or halos (color exists in the parallax)
  3. Seamless blending with the actual parallax

Get the Parallax Color

# Analyze the parallax image to find colors in its palette
bun run --cwd ${CLAUDE_PLUGIN_ROOT} ${CLAUDE_PLUGIN_ROOT}/skills/section-dividers/scripts/analyze-bg.ts /path/to/parallax.png top   # for top border
bun run --cwd ${CLAUDE_PLUGIN_ROOT} ${CLAUDE_PLUGIN_ROOT}/skills/section-dividers/scripts/analyze-bg.ts /path/to/parallax.png bottom # for bottom border

Choose the color from the parallax palette that provides HIGHEST CONTRAST with your silhouette color. For dark silhouettes, pick the lightest color from the parallax. For light silhouettes, pick the darkest.

Background Removal

Use remove-bg.ts (AI-based) for reliable background removal:

bun run --cwd ${CLAUDE_PLUGIN_ROOT} ${CLAUDE_PLUGIN_ROOT}/skills/section-dividers/scripts/remove-bg.ts input.png output.png

Generation Workflow

Step 1: Generate

bun run --cwd ${CLAUDE_PLUGIN_ROOT} ${CLAUDE_PLUGIN_ROOT}/skills/generate-image/scripts/generate.ts "[PROMPT]" --aspect 21:9 --size 2K --negative "[NEGATIVES]" --output divider-raw.png

Prompt template:

ONE THIN horizontal SOLID terrain strip floating in solid [PARALLAX_COLOR].
FULL WIDTH from left edge to right edge.
The strip is SOLID FILLED - not hollow, not a cave.
TOP EDGE silhouette: [SURFACE_CONTENT] pointing UPWARD.
BOTTOM EDGE silhouette: [UNDERGROUND_CONTENT] pointing DOWNWARD.
SOLID MASS between top and bottom edges - filled with [SECTION_COLOR].
JAGGED organic edges on BOTH top AND bottom.
Strip is 12-15% of image height floating in vertical center.
85% solid [PARALLAX_COLOR] background above and below.
Shadow puppet silhouettes.

Negative prompt:

hollow, cave, empty center, arch, tunnel view, flat edges, reflection, mirror, white, pink, magenta, tall, thick, floating island, not full width

Step 2: Verify Raw Image (CRITICAL)

Before processing, verify:

  • Content spans FULL WIDTH (left to right)
  • TOP content points UP, BOTTOM content points DOWN (not reflection)
  • Strip is SOLID (not hollow/cave)
  • Content does NOT touch top/bottom image edges
  • Clear boundary between content and background

If ANY check fails = REGENERATE. Do not process junk.

Step 3: Remove Background

bun run --cwd ${CLAUDE_PLUGIN_ROOT} ${CLAUDE_PLUGIN_ROOT}/skills/section-dividers/scripts/remove-bg.ts divider-raw.png divider.png

Uses cjwbw/rembg model which PRESERVES RESOLUTION.

Step 4: Verify Final Image

  • Transparency is clean (no artifacts)
  • Full resolution preserved
  • Blends with parallax and section on page

Scripts

remove-bg.ts

AI background removal via Replicate (rembg model). Preserves original resolution.

bun run --cwd ${CLAUDE_PLUGIN_ROOT} ${CLAUDE_PLUGIN_ROOT}/skills/section-dividers/scripts/remove-bg.ts input.png output.png

analyze-bg.ts

Extract dominant color from parallax image.

bun run --cwd ${CLAUDE_PLUGIN_ROOT} ${CLAUDE_PLUGIN_ROOT}/skills/section-dividers/scripts/analyze-bg.ts parallax.png bottom

colorize.ts

Tint transparent silhouette to match theme.

bun run --cwd ${CLAUDE_PLUGIN_ROOT} ${CLAUDE_PLUGIN_ROOT}/skills/section-dividers/scripts/colorize.ts input.png output.png "#042f2e"

Context Discipline

Do not read generated divider images back into context. Scripts output file paths. Ask the user to visually verify the divider in their browser against the parallax and section backgrounds. To inspect programmatically, optimize the image first (via the optimize-images skill).

Fixing Existing Dividers (Color Mismatch)

When an existing divider has wrong colors or semi-transparent edges:

Step 1: Remove Background

bun run --cwd ${CLAUDE_PLUGIN_ROOT} ${CLAUDE_PLUGIN_ROOT}/skills/section-dividers/scripts/remove-bg.ts original.png transparent.png

Step 2: Make SOLID with Section Color

The remove-bg output has semi-transparent edges. To make it SOLID and match the section:

from PIL import Image

img = Image.open('transparent.png').convert('RGBA')
pixels = img.load()
width, height = img.size

# Get EXACT section color from CSS/computed style
# Example: oklch(0.12 0.015 260) = RGB(3, 6, 11)
sr, sg, sb = 3, 6, 11

for y in range(height):
    for x in range(width):
        r, g, b, a = pixels[x, y]
        if a > 50:  # Any visible pixel = SOLID section color
            pixels[x, y] = (sr, sg, sb, 255)
        else:  # Transparent stays transparent
            pixels[x, y] = (0, 0, 0, 0)

img.save('final.png')

Key points:

  • Alpha > 50 = make fully opaque (255) with section color
  • Alpha <= 50 = make fully transparent (0)
  • This eliminates semi-transparent edges from AI removal
  • Section color must EXACTLY match the adjacent section's background

Getting Exact Section Color

// In browser console on the page:
const el = document.querySelector('#section-id');
const canvas = document.createElement('canvas');
canvas.width = 1; canvas.height = 1;
const ctx = canvas.getContext('2d');
ctx.fillStyle = getComputedStyle(el).backgroundColor;
ctx.fillRect(0, 0, 1, 1);
const data = ctx.getImageData(0, 0, 1, 1).data;
console.log(`RGB(${data[0]}, ${data[1]}, ${data[2]})`);

Troubleshooting

ProblemCauseFix
Content doesn't span full widthMissing "FULL WIDTH"Add "FULL WIDTH from left edge to right edge"
Bottom is mirror of topReflection not cross-sectionUse DIFFERENT content for top and bottom
Hollow/cave shapeWrong shape promptAdd "SOLID FILLED - not hollow, not a cave"
Content touches edgesStrip too tallAdd "12-15% height, 85% background above/below"
Fuzzy edges after removalBackground color mismatchEnsure background EXACTLY matches parallax color
AI removed too muchComplex edgesTry regenerating with cleaner silhouette shapes
Wrong colorsDidn't match exactlyUse exact hex values from analyze-bg and CSS
Ghosting/semi-transparent edgesSoft edges in generationRegenerate with sharper silhouette style
Semi-transparent silhouetteAI removal creates soft alphaUse "Fixing Existing Dividers" workflow above
Color doesn't match sectionWrong RGB valuesGet exact color from browser computed style

CSS Positioning

Animated vs Static Dividers

For ANIMATED dividers (with .float or other CSS animations):

  • Use fixed pixel values: top: -20px
  • DO NOT use translateY(-50%)

For STATIC dividers (no animation):

  • translateY(-50%) works fine
  • Centers element on the seam

Why Transforms Fail with Animations

When an element has a CSS animation that uses transform in its keyframes:

@keyframes float {
  0%, 100% { transform: translateY(0px); }
  50% { transform: translateY(-10px); }
}

The animation's transform completely overrides any inline transform:

  • Your style={{transform: "translateY(-50%)"}} gets replaced
  • Element renders with animation's translateY(0px) instead

Also note: percentage margins (margin-top: -50%) are based on parent WIDTH, not height.

Correct Approach: Simple Negative Top

/* Position divider on seam between sections */
.divider-top {
  position: absolute;
  top: -20px;  /* Adjust until CENTER sits on seam */
  left: 0;
  right: 0;
  z-index: 50;
  pointer-events: none;
}

Layout Structure

SECTION (solid background)
    ↓
    SEAM ← divider CENTER should align HERE
    ↓
PARALLAX CONTAINER
  └── DIVIDER (absolute, top: -20px, adjusts per image)
  └── PARALLAX IMAGE
  └── DIVIDER (absolute, bottom: 0, transform for bottom)
    ↓
    SEAM
    ↓
SECTION (solid background)

Implementation Pattern

From tokenpass-web/src/components/BorderedParallax.tsx:

{/* Top divider - sits on seam above parallax */}
<div
  className="absolute left-0 right-0 z-50 pointer-events-none float"
  style={{ top: "-20px" }}  // Simple fixed value
>
  <img src={borders.top} className="w-full h-auto" />
</div>

Positioning Tips

  1. Start with top: -20px and adjust visually
  2. Goal: CENTER of divider image sits on the SEAM
  3. If image has transparent space, account for it
  4. Test on both mobile AND desktop
  5. Fixed pixel values work consistently across screen sizes

平台分布

Codex

36.5%
按下载量换算48

Claude

28.75%
按下载量换算38

Cursor

17.81%
按下载量换算23

Gemini CLI

9.45%
按下载量换算12

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

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