Token导航 LogoToken导航TokenDH.com
待分类只读github未标认证来源可访问许可证需确认审计提醒

skill-optimize技能优化

Agent Skill

skill-optimize 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。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

297

周安装

12

GitHub Stars

6

下载量

93
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:skill-optimize(技能优化)
来源仓库:https://github.com/duc01226/easyplatform
仓库路径:skills/skill-optimize
安装命令:
npx skills add https://github.com/duc01226/easyplatform --skill skill-optimize
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/duc01226/easyplatform --skill skill-optimize

简介

skill-optimize 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。

  • 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。
  • 安装方式:github,使用 npx skills add 命令添加。
  • 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。

SKILL.md

[IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE starting.
Shared Protocol Duplication Policy — Inline protocol content in skills (wrapped in <!-- SYNC:tag -->) is INTENTIONAL duplication. Do NOT extract, deduplicate, or replace with file references. AI compliance drops significantly when protocols are behind file-read indirection. To update: edit .claude/skills/shared/sync-inline-versions.md first, then grep SYNC:protocol-name and update all occurrences.

Quick Summary

Goal: Optimize an existing skill for token efficiency, AI attention anchoring, and SYNC protocol compliance.

Workflow:

  1. Analyze — Review structure, line count, SYNC tags, attention anchoring
  2. Check SYNC compliance — Verify protocols are inlined (not file references), tags balanced
  3. Optimize — Apply prompt-enhance principles, move details to references, improve clarity
  4. Enhance — Call /prompt-enhance on the optimized SKILL.md
  5. Validate — Verify skill still works correctly after optimization

Key Rules:

  • SKILL.md under 500 lines; reference files under 100 lines each
  • Shared protocols MUST ATTENTION be inlined via <!-- SYNC:tag --> blocks, NEVER MUST ATTENTION READ shared/ references
  • MUST ATTENTION call /prompt-enhance as final quality pass
  • Attention structure: SYNC blocks at top, Quick Summary, detailed steps, Closing Reminders with :reminder blocks at bottom

Arguments

SKILL: $1 (default: *) PROMPT: $2 (default: empty)

Your Mission

Optimize skill at .claude/skills/${SKILL} directory.

Mode detection:

  • If arguments contain "auto" or "trust me": Skip plan approval, implement directly.
  • Otherwise: Propose plan first, ask user to review before implementing.

$PROMPT

Optimization Checklist

1. Structure Check

  • Has ## Quick Summary (Goal/Workflow/Key Rules) within first 30 lines
  • Has ## Closing Reminders at bottom with :reminder SYNC blocks
  • SYNC protocol blocks at top (primacy zone)
  • Critical rules appear in BOTH top and bottom sections (primacy-recency)

2. SYNC Protocol Check

  • No file references to .claude/skills/shared/ — all protocols inlined via SYNC blocks
  • All SYNC tags balanced (every open has matching close)
  • Content matches canonical source: .claude/skills/shared/sync-inline-versions.md
  • :reminder blocks present at bottom for each protocol

3. Token Efficiency Check

  • SKILL.md under 500 lines (target: under 300)
  • No filler phrases, redundant explanations, or TOCs
  • Tables/bullets over prose paragraphs
  • Examples are minimal (1 per pattern, not verbose)

4. Final Enhancement

  • Call /prompt-enhance on the finished SKILL.md
  • Verify no content loss (diff check)
  • Rule density maintained or improved (count MUST ATTENTION/NEVER/ALWAYS before and after)

Closing Reminders

  • IMPORTANT MUST ATTENTION break work into small todo tasks using TaskCreate BEFORE starting
  • IMPORTANT MUST ATTENTION inline shared protocols via <!-- SYNC:tag --> — NEVER use file references
  • IMPORTANT MUST ATTENTION call /prompt-enhance on optimized skill as final quality pass
  • IMPORTANT MUST ATTENTION verify SYNC tag balance and content matches canonical source
  • IMPORTANT MUST ATTENTION follow duplication policy: inline protocols are INTENTIONAL, never extract to file references

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

31.81%
按下载量换算30

Claude

32.67%
按下载量换算30

Cursor

18.15%
按下载量换算17

Gemini CLI

8.99%
按下载量换算8

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

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。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