Agent skill

Universal Learner

by huangserva in huangserva/skill-prompt-generator

通用学习器 - 从任何领域的Prompt中自动提取可复用元素,持续学习和积累知识. An agent skill from huangserva/skill-prompt-generator.

No licenceAuto-check passed

Install Universal Learner

skills CLI
$ npx skills add huangserva/skill-prompt-generator --skill universal-learner -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install huangserva/skill-prompt-generator universal-learner --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/huangserva/skill-prompt-generator.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/universal-learner .claude/skills/universal-learner && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
universal-learner
GitHub stars
1.5k
Used in
1 other repo
Token cost
~1.2k tokens
SKILL.md length
131 words
Files
5
Skills in repo
12
Repo updated
First seen
Licence
None found

At a glance

通用学习器 - 从任何领域的Prompt中自动提取可复用元素,持续学习和积累知识. An agent skill from huangserva/skill-prompt-generator.

  • SKILL.md covers 🎯 核心功能, 📋 使用方式, 🔄 工作流程 and 📊 输出示例, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Universal Learner is an agent skill from huangserva/skill-prompt-generator. 通用学习器 - 从任何领域的Prompt中自动提取可复用元素,持续学习和积累知识

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files (for example `modules/domain_classifier.md`, `modules/element_extractor.md` and `modules/library_updater.md`).

The repository describes itself as: 这是一个基于Claude Skill的AI人像Prompt生成系统,能够从特征库中智能组合生成高质量的人像描述Prompt,并具备自动学习和库扩展能力。 核心能力: Prompt生成、特征提取、自动学习、智能审核、版本控制.

Example prompts

  • “/universal-learner”

What it can do on your machine

Read from SKILL.md and the folder at commit e951249. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Universal Learner loads about 1.2k tokens when it runs. Until then it costs about 15 tokens; SKILL.md has 131 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~15
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 131 words (~1,167 tokens).

“版本: 1.0 架构: Master-Subordinate 学习方式: 半自动(生成报告 + 人工审核)”

— opening of SKILL.md by huangserva
name
universal-learner

Read the full SKILL.md on GitHub

Files

SKILL.md and 4 other files in .codex/skills/universal-learner of huangserva/skill-prompt-generator.

  • SKILL.md
  • modules/domain_classifier.md
  • modules/element_extractor.md
  • modules/library_updater.md
  • modules/tagger.md

Open the folder on GitHubat commit e951249

Used in 1 other repository

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in huangserva/skill-prompt-generator, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Universal Learner next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Universal Learner compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Universal Learner this skillhuangserva/skill-prompt-generator1.5k1 repos~1.2kAutomated safety check: PassNone
Universal Scraping Architectalirezarezvani/claude-skills28k—~1.1kAutomated safety check: PassMIT
Universal Ma Codebookbrycewang-stanford/Auto-Empirical-Research-Skills4.5k—~3.4kAutomated safety check: PassCustom licence
Kaggle LearnerGalaxy-Dawn/claude-scholar5.7k2 repos~940Automated safety check: PassMIT
Journal Of Tianjin University Of Sportbrycewang-stanford/Awesome-Journal-Skills1.2k—~671Automated safety check: PassMIT
Journal Of Chengdu Sport Universitybrycewang-stanford/Awesome-Journal-Skills1.2k—~669Automated safety check: PassMIT

Similar skills

  • Universal Scraping Architect

    alirezarezvani/claude-skills

    A skill your agent uses for web scraping, crawling, document extraction, API parsing, or building validation-heavy data pipelines using Firecrawl or local Python scripts.

    28k GitHub stars~1.1k tokensUpdated 1 mo ago
    Data & AnalyticsAuto-check passed
  • Universal Ma Codebook

    brycewang-stanford/Auto-Empirical-Research-Skills

    Universal Meta-Analysis Codebook v2.2 - AI-Human collaboration for meta-analysis data extraction.

    4.5k GitHub stars~3.4k tokensUpdated 2 days ago
    Research & ScienceAuto-check passed
  • Kaggle Learner

    Galaxy-Dawn/claude-scholar

    This skill should be used when the user asks to "learn from Kaggle", "study Kaggle solutions", "analyze Kaggle competitions", or mentions Kaggle competition URLs.

    5.7k GitHub starsUsed in 2 repos~940 tokens
    Data & AnalyticsAuto-check passed
  • Journal Of Tianjin University Of Sport

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when targeting 《天津体育学院学报》(Journal of Tianjin University of Sport) — a CSSCI comprehensive sport-science journal hosted by Tianjin University of Sport, with a recognized tilt…

    1.2k GitHub stars~671 tokensUpdated 11 days ago
    Auto-check passed
  • Journal Of Chengdu Sport University

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when targeting 《成都体育学院学报》(Journal of Chengdu Sport University) — a CSSCI comprehensive sport-science journal hosted by Chengdu Sport University, distinctively strong in sport…

    1.2k GitHub stars~669 tokensUpdated 11 days ago
    Auto-check passed
  • Journal Of Shenyang Sport University

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when targeting 《沈阳体育学院学报》(Journal of Shenyang Sport University) — a CSSCI comprehensive sport-science journal hosted by Shenyang Sport University in northeast China, covering…

    1.2k GitHub stars~665 tokensUpdated 11 days ago
    Auto-check passed

More from huangserva/skill-prompt-generator

All 12 skills in this repo
  • Domain Classifier

    huangserva/skill-prompt-generator

    AI领域分类器 - 智能分析提示词内容,准确判断所属领域(人像/艺术/设计/产品/视频). An agent skill from huangserva/skill-prompt-generator.

    1.5k GitHub starsUsed in 1 repo~1k tokens
    Auto-check passed
  • Prompt Analyzer

    huangserva/skill-prompt-generator

    提示词分析与洞察 - 查看Prompt详情、对比差异、推荐相似提示词、元素库统计. An agent skill from huangserva/skill-prompt-generator.

    1.5k GitHub starsUsed in 1 repo~2.7k tokens
    Auto-check passed
  • Prompt Master

    huangserva/skill-prompt-generator

    提示词主控 - 智能选择合适的领域skill并生成提示词,支持自动领域分类和调度. An agent skill from huangserva/skill-prompt-generator.

    1.5k GitHub starsUsed in 1 repo~1.8k tokens
    Auto-check passed
  • Design Master

    huangserva/skill-prompt-generator

    平面设计主控 - 自动生成平面设计提示词,支持海报、logo、插画等多种设计类型. An agent skill from huangserva/skill-prompt-generator.

    1.5k GitHub stars~728 tokensUpdated 5 mo ago
    Auto-check passed
  • Art Master

    huangserva/skill-prompt-generator

    艺术风格主控 - 自动生成艺术风格提示词,支持水墨画、油画、超现实、插画等多种艺术风格. An agent skill from huangserva/skill-prompt-generator.

    1.5k GitHub stars~329 tokensUpdated 5 mo ago
    Auto-check passed
  • Intelligent Prompt Generator

    huangserva/skill-prompt-generator

    智能提示词生成器 v2.0 - 支持人像/跨domain/设计三种模式,语义理解、常识推理、一致性检查. An agent skill from huangserva/skill-prompt-generator.

    1.5k GitHub stars~6.6k tokensUpdated 5 mo ago
    Auto-check passed

Questions about Universal Learner

What does Universal Learner do?

通用学习器 - 从任何领域的Prompt中自动提取可复用元素,持续学习和积累知识. An agent skill from huangserva/skill-prompt-generator. Universal Learner is an agent skill from huangserva/skill-prompt-generator.

How do I install Universal Learner in Claude Code?

Run `npx skills add huangserva/skill-prompt-generator --skill universal-learner -a claude-code`. Or copy the skill folder (.codex/skills/universal-learner in huangserva/skill-prompt-generator) into .claude/skills/universal-learner in your project. Claude Code loads it when a task matches its description.

How do I install Universal Learner in Codex?

Run `npx skills add huangserva/skill-prompt-generator --skill universal-learner -a codex`. Or copy the skill folder (.codex/skills/universal-learner in huangserva/skill-prompt-generator) into .agents/skills/universal-learner in your project. Codex loads it when a task matches its description.

Can I use Universal Learner in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add huangserva/skill-prompt-generator --skill universal-learner -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/universal-learner, .gemini/skills/universal-learner, .github/skills/universal-learner and .opencode/skills/universal-learner in your project.

What does Universal Learner need to run?

SKILL.md names no scripts, command-line tools or credentials: Universal Learner is instructions for the agent only.

Does Universal Learner access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Universal Learner safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Universal Learner use?

No licence was found for Universal Learner or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Universal Learner use?

About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Universal Learner?

Skills that share tags, products or a category with Universal Learner: Universal Scraping Architect (alirezarezvani/claude-skills, 28k stars), Universal Ma Codebook (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars), Kaggle Learner (Galaxy-Dawn/claude-scholar, 5.7k stars) and Journal Of Tianjin University Of Sport (brycewang-stanford/Awesome-Journal-Skills, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Universal Learner?

huangserva (a GitHub user) maintains it in huangserva/skill-prompt-generator, which has 1,500 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on May 10, 2026.

Source: huangserva/skill-prompt-generator on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.