Token导航 LogoToken导航TokenDH.com
研究检索敏感数据clawhub未标认证来源可访问clear审计通过

ml-roadmap机器学习路线图

Agent Skill

ml-roadmap 用于记录任务执行中的错误、用户纠正、经验和能力缺口,适合在 OpenClaw 中希望让 Agent 持续沉淀问题、修正和最佳实践时使用。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

4,776

周安装

199

GitHub Stars

公开资料未说明

下载量

1,592
OpenClaw

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

MIT-0

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:ml-roadmap(机器学习路线图)
来源仓库:https://github.com/ckchzh/ml-roadmap
安装命令:
openclaw skills install ml-roadmap
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 OpenClaw 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。

ClawHubOpenClaw
openclaw skills install ml-roadmap

简介

该路线图连接了机器学习中许多最重要的概念、如何学习它们以及机器学习路线图、Python、数据、数据科学。

SKILL.md

version
2.0.0
name
Machine Learning Roadmap
description
A roadmap connecting many of the most important concepts in machine learning, how to learn them and machine learning roadmap, python, data, data-science.

Machine Learning Roadmap

A thorough content toolkit for planning and tracking your machine learning learning journey. Draft study plans, organize topics, create outlines, schedule learning sessions, and manage your ML education roadmap — all from the command line.

Commands

CommandDescription
ml-roadmap draft <input>Draft a new ML learning plan or content entry
ml-roadmap edit <input>Edit an existing entry or refine content
ml-roadmap optimize <input>Optimize content for clarity or effectiveness
ml-roadmap schedule <input>Schedule learning sessions or content publication
ml-roadmap hashtags <input>Generate relevant hashtags for ML topics
ml-roadmap hooks <input>Create engaging hooks for ML content
ml-roadmap cta <input>Generate call-to-action text for ML resources
ml-roadmap rewrite <input>Rewrite content with improved structure
ml-roadmap translate <input>Translate ML content between languages
ml-roadmap tone <input>Adjust the tone of ML content (formal, casual, etc.)
ml-roadmap headline <input>Generate compelling headlines for ML topics
ml-roadmap outline <input>Create structured outlines for ML subjects
ml-roadmap statsShow summary statistics across all entry types
ml-roadmap export <fmt>Export all data (formats: json, csv, txt)
ml-roadmap search <term>Search across all entries by keyword
ml-roadmap recentShow the 20 most recent activity log entries
ml-roadmap statusHealth check — version, disk usage, last activity
ml-roadmap helpShow the built-in help message
ml-roadmap versionPrint the current version (v2.0.0)

Each content command (draft, edit, optimize, etc.) works in two modes:

  • Without arguments — displays the 20 most recent entries of that type
  • With arguments — saves the input as a new timestamped entry

Data Storage

All data is stored as plain-text log files in ~/.local/share/ml-roadmap/:

  • Each command type gets its own log file (e.g., draft.log, edit.log, outline.log)
  • Entries are stored in timestamp|value format for easy parsing
  • A unified history.log tracks all activity across command types
  • Export to JSON, CSV, or TXT at any time with the export command

Set the ML_ROADMAP_DIR environment variable to override the default data directory.

Requirements

  • Bash 4.0+ (uses set -euo pipefail)
  • Standard Unix utilities: date, wc, du, tail, grep, sed, cat
  • No external dependencies or API keys required

When to Use

  1. Planning your ML learning path — use outline and draft to structure a study roadmap covering supervised learning, deep learning, NLP, computer vision, and more
  2. Creating ML educational content — use headline, hooks, cta, and hashtags to craft engaging posts or articles about machine learning concepts
  3. Scheduling study sessions — use schedule to log when you plan to study specific ML topics and track your progress over time
  4. Refining technical writing — use rewrite, tone, and optimize to polish ML blog posts, documentation, or course materials
  5. Tracking content creation history — use stats, search, and recent to review what you've written, find past entries, and measure productivity

Examples

# Draft a new learning plan for deep learning fundamentals
ml-roadmap draft "Week 1: Neural network basics — perceptrons, activation functions, backprop"

# Create an outline for a blog post on model selection
ml-roadmap outline "Comparing Random Forest vs XGBoost: when to use each, key hyperparameters, pros/cons"

# Generate a headline for an ML tutorial
ml-roadmap headline "Beginner-friendly guide to building your first image classifier with PyTorch"

# Schedule a study session
ml-roadmap schedule "Saturday 10am: Work through Stanford CS229 Lecture 5 — Support Vector Machines"

# Export all your entries to JSON for backup
ml-roadmap export json

Output

All commands print results to stdout. Redirect to a file if needed:

ml-roadmap stats > roadmap-report.txt
ml-roadmap export csv

Powered by BytesAgain | bytesagain.com | hello@bytesagain.com

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

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

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

OpenClaw

78.26%
按下载量换算1,246

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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。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