Token导航 LogoToken导航TokenDH.com
研究检索操作浏览器github未标认证来源可访问clear审计提醒

evolving-skill-creator不断发展的技能创建器

Agent Skill

evolving-skill-creator 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

1,048

周安装

42

GitHub Stars

968

下载量

339
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

3

许可证

MIT

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:evolving-skill-creator(不断发展的技能创建器)
来源仓库:https://github.com/massgen/massgen
仓库路径:skills/evolving-skill-creator
安装命令:
npx skills add https://github.com/massgen/massgen --skill evolving-skill-creator
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/massgen/massgen --skill evolving-skill-creator

简介

evolving-skill-creator 帮助创建可迭代的演进型技能,即通过多次使用逐步完善的详细工作流程计划。

  • 适用于需要构建可复用工具链、记录执行经验或形成标准化作业流程的场景。
  • 将技能拆解为具体步骤与配套 Python 脚本,并在每次执行后捕获学习成果供后续参考。
  • 使用时建议保留项目事实信息,避免虚构未验证内容,尤其涉及对外文案时应控制语气。
  • 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

Evolving Skill Creator

Create evolving skills - detailed workflow plans that become reusable through iteration.

What is an Evolving Skill?

An evolving skill is a workflow plan that:

  1. Documents specific steps to accomplish a goal
  2. Lists Python scripts you'll create as reusable tools
  3. Captures learnings after execution for future improvement

Unlike static skills, evolving skills are refined through use.

Directory Structure

tasks/evolving_skill/
├── SKILL.md              # Your workflow plan
└── scripts/              # Python tools you create during execution
    ├── scrape_data.py
    └── generate_output.py

SKILL.md Format

IMPORTANT: YAML Frontmatter is Required

Every evolving skill MUST start with YAML frontmatter containing name and description. These fields are critical for skill discovery - they determine how the skill is identified when loaded in future sessions.

---
name: descriptive-skill-name    # REQUIRED - used for identification
description: Clear explanation of what this workflow does and when to use it  # REQUIRED - used for discovery
---
# Task Name

## Overview
Brief description of the problem this skill solves.

## Workflow
Detailed numbered steps:
1. First step - be specific
2. Second step - include commands/tools to use
3. ...

## Tools to Create
Python scripts you'll write. Document BEFORE writing them:

### scripts/example_tool.py
- **Purpose**: What it does
- **Inputs**: What it takes (args, files, etc.)
- **Outputs**: What it produces
- **Dependencies**: Required packages

## Tools to Use
(Discover what's available, list ones you'll use)
- servers/name: MCP server tools
- custom_tools/name: Python tool implementations

## Skills
- skill_name: how it will help

## Packages
- package_name (pip install package_name)

## Expected Outputs
- Files this workflow produces
- Formats and locations

## Learnings
(Add after execution)

### What Worked Well
- ...

### What Didn't Work
- ...

### Tips for Future Use
- ...

Tools to Create Section

This is the key differentiator. When your workflow involves writing Python scripts, document them upfront:

## Tools to Create

### scripts/fetch_artist_data.py
- **Purpose**: Crawl Wikipedia and extract artist biographical data
- **Inputs**: artist_name (str), output_path (str)
- **Outputs**: JSON file with structured bio data
- **Dependencies**: crawl4ai, json

### scripts/build_site.py
- **Purpose**: Generate static HTML from artist data
- **Inputs**: data_path (str), theme (str), output_dir (str)
- **Outputs**: Complete website in output_dir/
- **Dependencies**: jinja2

After execution, the actual scripts live in scripts/ and can be reused.

Creating an Evolving Skill

  1. Create directory: mkdir -p tasks/evolving_skill
  2. Write SKILL.md with proper YAML frontmatter first:

- name: Use a descriptive, reusable name (e.g., artist-website-builder, not bob-dylan-site) - description: Explain what the workflow does and when to use it

  1. Execute workflow following your plan
  2. Create scripts as documented in Tools to Create
  3. Update SKILL.md with Learnings after completion

Naming Guidelines

Choose names that describe the type of task, not the specific instance:

  • Good: artist-website-builder, data-scraper-to-static-site, pdf-report-generator
  • Bad: bob-dylan-project, session-12345, my-task

The name should make it clear what the skill does when discovered in future sessions.

Updating After Execution

After completing your work:

  1. Refine Workflow - Update steps based on what actually worked
  2. Move scripts - Ensure working scripts are in scripts/
  3. Add Learnings - Document what worked, what didn't, tips

Example: Complete Evolving Skill

---
name: artist-website-builder
description: Build static biographical websites for artists by scraping public sources and generating themed HTML.
---
# Artist Website Builder

## Overview
Create professional artist websites by gathering biographical data and generating themed static HTML.

## Workflow
1. Research artist - gather name variations, active years
2. Scrape data using scripts/fetch_artist_data.py
3. Review and clean extracted data
4. Generate site using scripts/build_site.py with "minimalist-dark" theme
5. Review in browser, check mobile responsiveness
6. Iterate on styling if needed

## Tools to Create

### scripts/fetch_artist_data.py
- **Purpose**: Crawl Wikipedia and extract artist biographical data
- **Inputs**: artist_name (str)
- **Outputs**: artist_data.json
- **Dependencies**: crawl4ai

### scripts/build_site.py
- **Purpose**: Generate static HTML from artist data
- **Inputs**: artist_data.json, theme_name
- **Outputs**: Complete website in output/
- **Dependencies**: jinja2

## Tools to Use
- servers/context7: fetching crawl4ai and jinja2 documentation
- servers/browser: capturing site previews for review
- custom_tools/image_optimizer: compressing generated assets

## Skills
- web-scraping-patterns: structuring the crawl4ai approach

## Packages
- crawl4ai (pip install crawl4ai)
- jinja2 (pip install jinja2)

## Expected Outputs
- output/index.html
- output/discography.html
- output/assets/

## Learnings

### What Worked Well
- Wikipedia infoboxes have consistent structure
- crawl4ai async mode is 3x faster than sync
- "minimalist-dark" theme works best for musicians

### What Didn't Work
- AllMusic requires JS rendering - use Discogs API instead
- Initial theme had poor mobile layout

### Tips for Future Use
- Always check robots.txt before scraping
- Cache scraped data - re-running is slow
- Test on mobile early

Key Principles

  1. Be specific - Workflow steps should be actionable, not vague
  2. Document tools upfront - Plan scripts before writing them
  3. Test like a user - Verify artifacts through interaction, not just observation (click buttons, play games, navigate pages, run with edge cases, etc)
  4. Update with learnings - The skill improves through use
  5. Keep scripts reusable - Design tools to work in similar future tasks

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

04

需要参考平台分布和安装热度时

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

补充不同宿主或平台的使用分布数据

能力 5

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

Claude Code

28.22%
按下载量换算96

Antigravity

23.43%
按下载量换算79

Gemini CLI

16.13%
按下载量换算55

OpenCode

10.93%
按下载量换算37

Codex

6.91%
按下载量换算23

windsurf

3.22%
按下载量换算11

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

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。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。

来源信息

继续浏览同类 Skills