Token导航 LogoToken导航TokenDH.com
研究检索external-servicegithub未标认证来源可访问许可证需确认审计提醒

ln-832-bundle-optimizerln 832 捆绑优化器

Agent Skill

ln-832-bundle-optimizer 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。

总安装

3,378

周安装

138

GitHub Stars

441

下载量

1,082
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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:ln-832-bundle-optimizer(ln 832 捆绑优化器)
来源仓库:https://github.com/levnikolaevich/claude-code-skills
仓库路径:skills/ln-832-bundle-optimizer
安装命令:
npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-832-bundle-optimizer
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/levnikolaevich/claude-code-skills --skill ln-832-bundle-optimizer

简介

用于查找、检索和筛选相关信息。ln-832-bundle-optimizer 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

  • 适合根据关键词或任务场景快速定位候选结果。
  • 可结合来源仓库和原始 README 核验具体用法。
  • 安装前建议确认权限范围和维护状态。
  • 注意是否会触发联网、命令执行或文件读写操作。

SKILL.md

Paths: File paths (shared/, references/, ../ln-*) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root. If shared/ is missing, fetch files via WebFetch from https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}.

ln-832-bundle-optimizer

Type: L3 Worker Category: 8XX Optimization

Reduces JavaScript or TypeScript bundle size using keep/discard verification. JS/TS projects only.


Overview

AspectDetails
InputJS/TS project path plus optional optimization scope
OutputSmaller bundle plus a machine-readable modernization summary
ScopeJS/TS only

Workflow

Phases: Pre-flight -> Baseline -> Analyze -> Optimize Loop -> Report


Phase 0: Pre-flight Checks

CheckRequiredAction if Missing
package.json existsYesBlock optimization
Build command availableYesBlock optimization
Output directory (dist/ or build/) detectableYesBuild once to establish baseline
Workspace baseline safeYesIn managed runs coordinator already prepared it; in standalone runs protect rollback locally

MANDATORY READ: Load shared/references/ci_tool_detection.md for build detection. MANDATORY READ: Load shared/references/mcp_tool_preferences.md and shared/references/mcp_integration_patterns.md

Use hex-graph first when hotspots or clone groups materially improve optimization targeting. Use hex-line first for local code and config reads when available. If MCP is unavailable, unsupported, or not indexed, continue with built-in Read/Grep/Glob/Bash and state the fallback in the summary.

Runtime Coordination

Managed runs receive deterministic runId and exact summaryArtifactPath from ln-830. Standalone runs remain supported; if runtime arguments are omitted, generate a standalone run-scoped artifact before returning.


Phase 1: Establish Baseline

1. Run the detected build command.
2. Measure total size of the output directory.
3. Record baseline bytes and per-chunk sizes.
MetricHow
Total sizeSum all bundle output files except source maps
Per-chunk sizesMeasure individual JS and CSS files
Source map handlingExclude .map files

Phase 2: Analyze Opportunities

CheckToolWhat It Finds
Unused dependenciesdepcheck or equivalentPackages not imported anywhere
Bundle compositionBundle analyzerLarge dependencies or duplicates
Tree-shaking gapsManual scanNamespace imports or heavy entrypoints
Code splitting gapsRoute analysisLazy-load candidates

Optimization categories:

CategoryExampleTypical Savings
Remove unused depsdead dependencies10-50KB per package
Named importslodash-es named imports50-200KB
Lighter alternativesreplace heavy date or utility libs50-300KB
Dynamic importslazy-load heavy componentslower initial bundle
CSS optimizationremove unused CSS, minify10-100KB

Phase 3: Optimize Loop (Keep/Discard)

Per-optimization cycle:

FOR each optimization:
  1. APPLY the change
  2. BUILD
     IF build fails -> DISCARD and revert
  3. MEASURE new bundle size
  4. KEEP only if the bundle is smaller than the current baseline
  5. LOG the result

Stop conditions:

ConditionAction
All optimizations processedStop and report
3 consecutive discardsStop for plateau
Build infrastructure breaksRevert to last keep and stop
Bundle already below targetStop and report

Optimization order:

  1. remove unused dependencies
  2. improve tree-shaking and imports
  3. replace heavy libraries
  4. introduce code splitting
  5. optimize CSS

Phase 4: Report Results

FieldDescription
projectProject path
baseline_bytesOriginal bundle size
final_bytesFinal bundle size
reduction_bytesBytes saved
reduction_percentPercentage reduction
optimizations_appliedCount of kept optimizations
optimizations_discardedCount plus reasons
deps_removed[]Dependencies removed
details[]Per-optimization savings
artifact_pathDurable worker report path, if written

Configuration

Options:
  build_command: ""             # Auto-detect
  output_dir: ""                # Auto-detect
  run_depcheck: true
  run_bundle_analyzer: false
  remove_unused_deps: true
  fix_tree_shaking: true
  replace_heavy_libraries: true
  enable_code_splitting: true

Error Handling

ErrorCauseSolution
Build fails after optimizationInvalid code or config changeRevert that optimization
No size reductionOptimization ineffectiveDiscard it
Analyzer unavailableTooling missingContinue with manual inspection

References


Runtime Summary Artifact

MANDATORY READ: Load shared/references/coordinator_summary_contract.md

Emit a modernization-worker summary envelope.

Managed mode:

  • ln-830 passes deterministic runId and exact summaryArtifactPath
  • write the summary to the provided summaryArtifactPath

Standalone mode:

  • omit runId and summaryArtifactPath
  • write .hex-skills/runtime-artifacts/runs/{run_id}/modernization-worker/ln-832--{identifier}.json

Monitor (2.1.98+): For build commands in keep/discard loop expected >30s, use Monitor. Fallback: Bash(run_in_background=true).

Definition of Done

  • Baseline bundle size established from real build output
  • Optimization opportunities analyzed from bundle composition and project usage
  • Each optimization evaluated with keep/discard verification
  • Only size-reducing optimizations kept
  • Final report captures bundle delta, discarded attempts, and removed dependencies
  • modernization-worker summary artifact written to the managed or standalone path

Version: 1.0.0 Last Updated: 2026-03-08

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.07%
按下载量换算390

Claude

31.39%
按下载量换算340

Cursor

17.43%
按下载量换算189

Gemini CLI

9.33%
按下载量换算101

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

Snyk

可疑

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

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。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills