Agent skill

Agent Focus Training

by hezkvectory in hezkvectory/hermes-edu-skills

把“孩子不专心”拆成可观察的学习环境、任务长度和反馈节奏,生成能立刻执行的专注训练方案. An agent skill from hezkvectory/hermes-edu-skills.

MITAuto-check passed

Install Agent Focus Training

skills CLI
$ npx skills add hezkvectory/hermes-edu-skills --skill agent-focus-training -a claude-code

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

GitHub CLI
$ gh skill install hezkvectory/hermes-edu-skills agent-focus-training --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/hezkvectory/hermes-edu-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/learning-core/agent-focus-training .claude/skills/agent-focus-training && 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
agent-focus-training
GitHub stars
109
Token cost
~738 tokens
SKILL.md length
198 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

把“孩子不专心”拆成可观察的学习环境、任务长度和反馈节奏,生成能立刻执行的专注训练方案. An agent skill from hezkvectory/hermes-edu-skills.

  • SKILL.md covers 这个 Skill 解决什么问题 / Problem, 最适合 / Best For, 不适合 / Not For and 使用前请准备 / Inputs, plus 10 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Agent Focus Training is an agent skill from hezkvectory/hermes-edu-skills. 把“孩子不专心”拆成可观察的学习环境、任务长度和反馈节奏,生成能立刻执行的专注训练方案。 Workflow: agentfocustraining.run.

Its SKILL.md is about 740 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: 中文教育 Agent Skill Pack:教材同步、备考复习、拍照答疑、错题复盘、亲子陪学、阅读写作和教师工具,Hermes Agent 可直接使用,也可导出到 OpenClaw/Codex/Cursor/Claude Code。 The licence is MIT.

Example prompts

  • “/agent-focus-training”

What it can do on your machine

Read from SKILL.md and the folder at commit b1c32d7. 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.

    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

Agent Focus Training loads about 738 tokens when it runs. Until then it costs about 25 tokens; SKILL.md has 198 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~25
When it runs · the whole SKILL.md, loaded when a task matches
~738

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

The full file from hezkvectory/hermes-edu-skills at commit b1c32d7, republished under its MIT licence (© hezkvectory). 198 words, ~738 tokens.

Download SKILL.mdSave it as .claude/skills/agent-focus-training/SKILL.md (or your agent's skills folder).
name
agent-focus-training
description
把“孩子不专心”拆成可观察的学习环境、任务长度和反馈节奏,生成能立刻执行的专注训练方案。 Workflow: agent_focus_training.run.
version
0.10.0
author
zhongwei
license
MIT
platforms
windows, linux, macos

专注力训练 Skill

把“孩子不专心”拆成可观察的学习环境、任务长度和反馈节奏,生成能立刻执行的专注训练方案。

这个 Skill 解决什么问题 / Problem

把“孩子不专心”拆成可观察的学习环境、任务长度和反馈节奏,生成能立刻执行的专注训练方案。

最适合 / Best For

  • 写作业拖拉
  • 短时学习容易走神
  • 家长想建立可持续的学习节奏

不适合 / Not For

  • 医学诊断或替代专业评估
  • 用惩罚、羞辱或过度监控来压学生学习

使用前请准备 / Inputs

  • 年龄/年级
  • 当前最容易分心的场景
  • 一次可专注时长
  • 学习任务类型
  • 家庭可执行的规则
  • 识别分心触发点
  • 把任务切成 5-25 分钟小段
  • 设计开始仪式和结束反馈
  • 设置低压力记录方式
  • 一周后根据记录调整

输出格式 / Output Format

  • 专注画像
  • 今日训练流程
  • 环境调整清单
  • 家长提示语
  • 一周跟踪表

质量检查 / Quality Checks

  • 避免贴标签
  • 任务时长要现实
  • 反馈要正向具体
  • 必须给出可观察指标

没有平台工具时 / Standalone Fallback

  • 没有计时工具时,输出手动打勾表。
  • 没有历史数据时,从今天一次学习任务开始记录。

示例提示 / Example Prompts

  • 三年级写作业 10 分钟就走神,帮我设计今晚的专注训练。
  • 孩子复习英语总拖拉,给我一个不吵架的执行方案。

适用场景 / When To Use

当学习者、家长、老师、学校或教育应用开发者需要处理以下场景时,可以使用这个 Skill。

最适合的场景:

  • 每日打卡

适用角色:

  • 学习者
  • 家长
  • 老师

调用信号 / Invocation Signals

意图:

  • agent_focus_training
  • learning_core
  • 每日打卡

示例表达:

  • 开始专注力训练 Skill
  • 帮我做每日打卡
  • 根据当前上下文执行专注力训练 Skill

公开 Skill 契约 / Public Skill Contract

  • Workflow: agent_focus_training.run
  • Category: learning-core
  • Stages: primary, junior, senior
  • Subjects: 学习能力
  • Abilities: 专注
  • Quality Tier: curated
  • Standalone Support: needs_user_input
  • Public Release: recommended
  • Requires Tools: context.load, entitlement.check, workflow.create, memory.write
  • Requires Data: 学习目标, 年级或水平, 用户输入的题目/记录/上下文
  • Export Mode: installable
  • Release Channel: recommended

成熟度备注:

  • 已按精品 Skill 标准补充边界、输入、工作流、输出格式和示例。

参数化使用 / Parameters

这个 Skill 不再把年级、册别、单元、知识点和难度拆成大量独立 Skill。请在调用时通过参数或自然语言补充这些信息。

  • Grades: 一年级, 二年级, 三年级, 四年级, 五年级, 六年级, 七年级, 八年级, 九年级, 高一, 高二, 高三
  • Semesters: 上册, 下册, 上册, 下册, 必修一, 必修二, 选择性必修
  • Scenarios: 每日打卡
  • Difficulties: 基础, 标准, 提高
  • Parameterized Dimensions: grade, semester, unit, lesson, knowledgePointCodes, scenario, difficulty

独立 Hermes 使用方式 / Standalone Hermes Usage

这个 Skill 可以通过 Hermes 的 skills.external_dirs 作为外部 Skill 加载。

如果你有自己的工具、记忆、课程数据或 workflow runner,可以把它们与本 Skill 组合使用。如果没有外部工具,也可以直接使用上面的说明来引导对话,生成有用的学习或教学反馈。

© hezkvectory, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/learning-core/agent-focus-training of hezkvectory/hermes-edu-skills.

Open the folder on GitHubat commit b1c32d7

Compare with similar skills

Agent Focus Training 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.

Agent Focus Training compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent Focus Training this skillhezkvectory/hermes-edu-skills109—~738Automated safety check: PassMIT
Ito Trainingaffaan-m/ECC276k1 repos~1.5kAutomated safety check: PassMIT
Ray Train Distributed TrainingOrchestra-Research/AI-Research-SKILLs13k2 repos~2.7kAutomated safety check: PassMIT
Daily Focus Boardgithub/awesome-copilot40k—~3kAutomated safety check: PassMIT
Fal Trainnexu-io/open-design100k—~293Automated safety check: PassApache-2.0
Train Poseruvnet/RuView97k—~504Automated safety check: PassMIT

Similar skills

  • Ito Training

    affaan-m/ECC

    Inspect the availability of ML training on a completed Itô compute booking and, when the canonical backend becomes available, hand off an explicitly confirmed training manifest.

    276k GitHub starsUsed in 1 repo~1.5k tokens
    AI & LLM EngineeringAuto-check passed
  • Ray Train Distributed Training

    Orchestra-Research/AI-Research-SKILLs

    Scales PyTorch, TensorFlow and Hugging Face training from a single GPU to multi-node clusters with Ray Train, including Ray Tune sweeps and checkpoint recovery.

    13k GitHub starsUsed in 2 repos~2.7k tokens
    AI & LLM EngineeringAuto-check passed
  • Daily Focus Board

    github/awesome-copilot

    Official

    Builds a warm, browser-based daily focus board the user updates by talking to their agent, with Eisenhower priorities, a brain-dump box and kind not-today carryover.

    40k GitHub stars~3k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Fal Train

    nexu-io/open-design

    Train custom AI models (LoRA) on fal.ai for personalized image generation tailored to a brand, character, or style.

    100k GitHub stars~293 tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Train Pose

    ruvnet/RuView

    Train/evaluate WiFi pose models honestly — camera-supervised (MediaPipe + CSI) and camera-free (WiFlow), always checked against the mean-pose baseline before any PCK is quoted.

    97k GitHub stars~504 tokensUpdated today
    DevelopmentAuto-check passed
  • Neural Training

    ruvnet/ruflo

    Neural pattern training with SONA (Self-Optimizing Neural Architecture), MoE (Mixture of Experts), and EWC++ for knowledge consolidation.

    74k GitHub starsUsed in 2 repos~432 tokens
    Auto-check passed

More from hezkvectory/hermes-edu-skills

All 11 skills in this repo
  • Adult Language Learning

    hezkvectory/hermes-edu-skills

    把成人语言学习从收藏资料变成真实场景输入、主动输出、纠错和复现。核心不是再推荐一堆资料,而是让用户今天能完成一个可检查的小成果。

    109 GitHub stars~737 tokensUpdated 4 mo ago
    Auto-check passed
  • Adult Vocational Certificate

    hezkvectory/hermes-edu-skills

    把职业证书备考从买课和刷题变成考纲拆解、知识框架、练习、错题和复测计划。核心不是再推荐一堆资料,而是让用户今天能完成一个可检查的小成果。

    109 GitHub stars~732 tokensUpdated 4 mo ago
    Auto-check passed
  • Adult Workplace Writing

    hezkvectory/hermes-edu-skills

    把职场写作从漂亮话变成目标明确、对象清楚、行动可落地的沟通文本。核心不是再推荐一堆资料,而是让用户今天能完成一个可检查的小成果。

    109 GitHub stars~731 tokensUpdated 4 mo ago
    Auto-check passed
  • Agent Holiday Plan

    hezkvectory/hermes-edu-skills

    把寒暑假从“报复性补课”改成有节奏的巩固、预习、阅读和休息计划. An agent skill from hezkvectory/hermes-edu-skills.

    109 GitHub stars~731 tokensUpdated 4 mo ago
    Auto-check passed
  • Agent Homework Companion

    hezkvectory/hermes-edu-skills

    陪学生完成作业全过程:先规划顺序,再在卡住时提示,不替写,最后做自查和订正. An agent skill from hezkvectory/hermes-edu-skills.

    109 GitHub stars~759 tokensUpdated 4 mo ago
    Auto-check passed
  • Agent Learning Habit

    hezkvectory/hermes-edu-skills

    把抽象的“养成学习习惯”落到固定触发、最小动作、即时反馈和家庭协作上. An agent skill from hezkvectory/hermes-edu-skills.

    109 GitHub stars~726 tokensUpdated 4 mo ago
    Auto-check passed

Questions about Agent Focus Training

What does Agent Focus Training do?

把“孩子不专心”拆成可观察的学习环境、任务长度和反馈节奏,生成能立刻执行的专注训练方案. An agent skill from hezkvectory/hermes-edu-skills. Agent Focus Training is an agent skill from hezkvectory/hermes-edu-skills.run.

How do I install Agent Focus Training in Claude Code?

Run `npx skills add hezkvectory/hermes-edu-skills --skill agent-focus-training -a claude-code`. Or copy the skill folder (skills/learning-core/agent-focus-training in hezkvectory/hermes-edu-skills) into .claude/skills/agent-focus-training in your project. Claude Code loads it when a task matches its description.

How do I install Agent Focus Training in Codex?

Run `npx skills add hezkvectory/hermes-edu-skills --skill agent-focus-training -a codex`. Or copy the skill folder (skills/learning-core/agent-focus-training in hezkvectory/hermes-edu-skills) into .agents/skills/agent-focus-training in your project. Codex loads it when a task matches its description.

Can I use Agent Focus Training 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 hezkvectory/hermes-edu-skills --skill agent-focus-training -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-focus-training, .gemini/skills/agent-focus-training, .github/skills/agent-focus-training and .opencode/skills/agent-focus-training in your project.

What does Agent Focus Training need to run?

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

Does Agent Focus Training 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 Agent Focus Training 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 Agent Focus Training use?

Agent Focus Training is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agent Focus Training use?

About 738 tokens (SKILL.md is roughly 3k 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 Agent Focus Training?

Skills that share tags, products or a category with Agent Focus Training: Ito Training (affaan-m/ECC, 276k stars), Ray Train Distributed Training (Orchestra-Research/AI-Research-SKILLs, 13k stars), Daily Focus Board (github/awesome-copilot, 40k stars) and Fal Train (nexu-io/open-design, 100k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Focus Training?

hezkvectory (a GitHub user) maintains it in hezkvectory/hermes-edu-skills, which has 109 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on May 21, 2026.

Source: hezkvectory/hermes-edu-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.