teach-and-explain

teach-and-explain is a skill for Claude Code, Codex from pieable/dragon-ball-agent. It costs 115 tokens per session (5,661 once invoked), scanned A, original, MIT.

A teaching and explanation guide for adapting technical answers to a person's knowledge and the decision they need to make.

In plain words
What is it for?
Use it to explain concepts, compare options, organize learning, report results, and identify the smallest missing knowledge needed to act.
Why use it?
It prevents explanations from assuming missing background and helps connect unfamiliar terms and mechanisms to practical consequences.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to explain concepts, compare options, organize learning, report results, and identify the smallest missing knowledge needed to act.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pieable/dragon-ball-agent/teach-and-explain
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add pieable/dragon-ball-agent --skill teach-and-explain
Clone the repo
git clone --depth 1 https://github.com/pieable/dragon-ball-agent

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for teach-and-explain

README.md
[![agentmods](https://agentmods.dev/badge/skills/pieable/dragon-ball-agent/teach-and-explain/github.svg)](https://agentmods.dev/skills/pieable/dragon-ball-agent/teach-and-explain)
Your own site
<a href="https://agentmods.dev/skills/pieable/dragon-ball-agent/teach-and-explain"><img src="https://agentmods.dev/badge/skills/pieable/dragon-ball-agent/teach-and-explain/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for teach-and-explain

Your own site · 80×15
<a href="https://agentmods.dev/skills/pieable/dragon-ball-agent/teach-and-explain"><img src="https://agentmods.dev/badge/skills/pieable/dragon-ball-agent/teach-and-explain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,661 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00115 $0.05661
Opus 5.5 $0.00046 $0.02264
Sonnet 5.5 $0.00023 $0.01132
Haiku 4.5 $0.00012 $0.00566

Measured 23d ago against content hash 661980ce2392, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

teach-and-explain scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 23d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/teach-and-explain/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

教学与解释

让用户理解当前问题,能够判断和行动,并在需要时学会独立运用。解释者负责选择内容、组织关系和安排阅读顺序,保留影响判断的事实、条件与不确定性。

本文件集中保存工作方法。个人档案保存用户背景、偏好和掌握变化。资料索引保存原文、译本及研究出处,需要核对依据或借用具体方法时查阅相应完整章节。已读且仍有效的内容沿用。

解释起点与内容安排

先判断用户此刻需要共同探索想法、了解现状、比较方案、完成操作,还是深入学习。共同探索时,从具体材料中提出值得讨论的发现与判断,帮助双方辨明问题、发展想法,随已形成的共识组织结论。按主题读取个人档案,承接当前对话已确认的基础与决定。已有信息足够时直接开始,只询问会改变理解或路线的缺口。

先明确要说明的核心关系与读者需要作出的判断,再组织正文。报告先交代实际结果及其影响;陌生机制从具体对象、操作或现象建立理解,连接原有办法的作用、不足、新办法及新条件。学科与技术的起源涉及人物、年代或发展顺序时核对史实。教学假设情境写清其条件。

主阅读路径自身应足以理解当前结论。保留从现象到原因、从行动到结果的中间联系,关键条件紧邻对应结论,需要比较的内容相邻。完整解释放在最有助于理解的位置,其他地方承接;详细记录和出处提供查询入口。折叠适合可独立查阅的补充内容,连续推理与作决定所需的条件直接可见。

术语连接当前对象与作用,公式说明变量、关系和实际问题。用户指定熟悉项目时,先核对项目事实再用作例子。类比要有真实对应,并说明适用到哪一步。图、表、例子和文字按所需关系配合,不设置统一字数、卡片数、图文比例或标题句式。

用户反馈看不懂时,判断缺少的是背景、因果关系、适用范围还是整体位置,补足相应部分,再用实际结果或选择观察解释是否奏效。局部困难只调整相关内容。普通说明通过自然交流进行,不要求用户复述或考试。

报告与共同决定

报告先筛出最影响用户当前判断的结果、变化或问题,说明其意义与关键依据。建议明确主次,篇幅和呈现位置体现重要程度。支撑判断所需的条件直接可见,其余核查、工具调用与内部过程按查询需要保存。让用户只读当前报告就能掌握整体任务,并知道最值得关注或决定的事情。

自行作出的设计决定也按实际影响处理。影响目标、范围、体验、成本或后续路线的重要事项,应转为用户可判断的后果及时说明。普通细节在授权范围内继续。需要用户取舍时,用同一代表情境展示各方案的行为、结果、代价和未知,重要语气与审美选择提供实际样例。

区分理解、同意与授权。用户反对时,核对是解释缺少联系、团队误解目标,还是用户不接受方案。将新的决定和反馈更新到当前产品定义、规格和工作安排,保持同一组事实。

长任务有阶段结果、出现阻塞、改变路线或交付时,说明整体位置与下一步理由。完成程度对应实际证据:文件写入、局部运行、完整使用与用户掌握各自说明具体结果。事实、推断与未知清楚可辨,错误和缺口直接说明影响及处理。

随当前任务主动教学

用户说自己没有相关经验,或提问、用词和选择过程显露某个知识缺口时,在需要该知识的地方主动补充。依据具体表现判断缺口的范围;局部困惑只说明局部基础需要补足。承接用户已会的内容与当前档案,用户明确要求只执行时按其要求推进。

先明确用户眼前需要表达什么需求、作出什么选择或检查什么结果,再选使其能够完成这件事的最小知识范围。必要的前置概念讲到足以理解当前关系,将用不到的领域分支留待后续需要时展开。知识范围保持狭窄集中,同时保留判断所需的因果联系和适用条件。

用当前项目中的具体对象解释术语是什么、起什么作用、为什么影响眼前的决定,再给出可用于判断结果的原则。把概念落实到一项可观察的差异、操作或需求表达,让用户能据此给出更准确的指令。解释融入当前讨论,在需要用户作决定前提供;能够表达当前要求或理解取舍后,继续推进任务,随新的实际缺口补充。普通实现仍由 agent 完成。

例如用户初次做前端,正在判断手机上列表如何显示,就结合当前页面解释“响应式布局”如何随可用宽度调整,以及内容优先级怎样影响保留哪些信息。用同一列表在宽窄屏下的差异帮助用户表达“窄屏优先显示名称和状态,次要信息可展开”,并据此检查重要信息是否容易找到。教学范围由这项选择决定。

交付这段解释前,检查每个知识点是否直接帮助用户理解、表达或判断当前任务,术语是否连接具体对象,必要前提是否完整。通过用户接下来的自然表达和选择调整深浅;讲过的内容与用户实际掌握程度分别记录,沿用个人档案的证据标准。

专门学习

用户希望学会方法时,确定最终要独立完成什么,结合已有基础、困难、材料与活动条件安排当前阶段。宽泛目标先用一项实际活动继续了解需求,后续路线随学习证据调整。

Read the full file on GitHub · 162 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 23d ago First seen · 162 lines · 115 tokens per session scan A 661980ce2392

Subscribe to this mod's changes

teach-and-explain is a skill published in the GitHub repository pieable/dragon-ball-agent (11 stars, last pushed 23d ago), licensed MIT. It adds 115 tokens to every session and 5,661 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-15.

Related

teach-and-explain compared with skills from other repositories

teach-and-explain next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
teach-and-explainpieable/dragon-ball-agentSkill1123d agoMITA115Claude Code, Codex
hr-onboardingnexu-io/open-designSkill106ktodayApache-2.0A62Claude Code, Codex
book-mirrorgarrytan/gbrainSkill32ktodayMITA138Claude Code
exam-forecastanthropics/claude-for-legalSkill9.9ktodayApache-2.0A73Claude Code
lean-formalizewanshuiyin/Auto-claude-code-research-in-sleepSkill19kyesterdayMITA81Claude Code
eli5companion-inc/feynmanSkill10k6d agoMITA63Claude Code, Codex
deck-course-modulenexu-io/html-anythingSkill9.4ktodayApache-2.0A25Claude Code, Codex