Agent skill

Axiom Explainer

by digoal in digoal/blog

Write Chinese Markdown articles for university students and adults with social experience that explain one viewpoint, axiom, theorem, law, principle, or theory system through "求真讲法、求存讲法、思考", with…

GPL-2.0Auto-check passedDocuments & Office

Install Axiom Explainer

skills CLI
$ npx skills add digoal/blog --skill axiom-explainer -a claude-code

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

GitHub CLI
$ gh skill install digoal/blog axiom-explainer --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/digoal/blog.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/axiom-explainer .claude/skills/axiom-explainer && 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
axiom-explainer
GitHub stars
8.6k
Token cost
~3.6k tokens
SKILL.md length
1,804 words
Files
3
Skills in repo
98
Repo updated
First seen
Licence
GPL-2.0

At a glance

Write Chinese Markdown articles for university students and adults with social experience that explain one viewpoint, axiom, theorem, law, principle, or theory system through "求真讲法、求存讲法、思考", with…

  • Works in 3 steps: Identify the input type → Scope the audience → Verify the concept
  • Codex is asked to generate 公理讲解文案、定理讲解、理论体系通俗解读、观点拆解、面向大学生和成年人的图文并茂 Markdown 文章
  • SKILL.md covers Overview, Input Contract, Workflow and Failure Handling, plus 5 more sections
  • Reaches w3.org

What it does

Axiom Explainer is an agent skill from digoal/blog. Write Chinese Markdown articles for university students and adults with social experience that explain one viewpoint, axiom, theorem, law, principle, or theory system through "求真讲法、求存讲法、思考", with text/Mermaid and standalone GitHub-renderable SVG files, assumptions, derivation or motivation, applicability boundaries, positive and negative examples, and save the result under the current project's markdown directory. Use when Codex is asked to generate 公理讲解文案、定理讲解、理论体系通俗解读、观点拆解、面向大学生和成年人的图文并茂 Markdown 文章.

Its SKILL.md is about 3.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `agents/openai.yaml` and `test-prompts.json`).

It sits in Documents & Office, covering Diagrams and Markdown. It works with GitHub and Mermaid. The repository describes itself as: AI,Opensource,Database,Business,Finance,Minds. git clone --depth 1 https://github.com/digoal/blog. The licence is GPL-2.0.

When your agent uses it

  • Codex is asked to generate 公理讲解文案、定理讲解、理论体系通俗解读、观点拆解、面向大学生和成年人的图文并茂 Markdown 文章
  • Tasks that involve Diagrams
  • Tasks that involve Markdown

Example prompts

  • “求真讲法、求存讲法、思考”
  • “/axiom-explainer”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Identify the input type
  2. Scope the audience
  3. Verify the concept

What it can do on your machine

Read from SKILL.md and the folder at commit ad6fcb7. 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 and mermaid).

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • w3.org

    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

Axiom Explainer loads about 3.6k tokens when it runs. Until then it costs about 131 tokens; SKILL.md has 1,804 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~131
When it runs · the whole SKILL.md, loaded when a task matches
~3.6k

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 digoal/blog at commit ad6fcb7, republished under its GPL-2.0 licence (© digoal). 1,804 words, ~3,647 tokens.

Download SKILL.mdSave it as .claude/skills/axiom-explainer/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
axiom-explainer
description
Write Chinese Markdown articles for university students and adults with social experience that explain one viewpoint, axiom, theorem, law, principle, or theory system through "求真讲法、求存讲法、思考", with text/Mermaid and standalone GitHub-renderable SVG files, assumptions, derivation or motivation, applicability boundaries, positive and negative examples, and save the result under the current project's markdown directory. Use when Codex is asked to generate 公理讲解文案、定理讲解、理论体系通俗解读、观点拆解、面向大学生和成年人的图文并茂 Markdown 文章.

Axiom Explainer

Overview

Generate a clear Chinese teaching article for university students and adults with social experience from a single viewpoint, axiom, theorem, law, principle, or theory system. The output must be Markdown, visually rich, and saved under the current project's markdown/ directory.

Input Contract

Required input:

  • One target concept: a viewpoint, axiom, theorem, law, principle, or theory system.

Optional input:

  • Audience level. Default: university students and adults with social experience.
  • Desired length. Default: 1800-3000 Chinese characters.
  • Source material or references supplied by the user.
  • Output filename or topic slug.

If the user gives several concepts, choose the central one only when the concepts clearly form one theory chain. Otherwise ask the user to pick one concept before writing.

Workflow

  1. Identify the input type:

    • Axiom or postulate: explain that it is not proven inside the system. Describe why people choose it, what problem it solves, what assumptions it introduces, and what changes if it is replaced.
    • Theorem or proposition: trace the axioms, definitions, lemmas, and reasoning chain that support it. Give an intuitive proof first, then a concise formal skeleton when useful.
    • Viewpoint, law, principle, or theory system: rewrite it as claims plus assumptions, then explain its evidence chain, mechanism, scope, and failure cases.
  2. Scope the audience:

    • Default to university students and adults with social experience unless the user specifies another level.
    • Use concrete analogies before abstract notation.
    • Prefer examples from investment and personal finance, product management, product operations, marketing, interpersonal relationships, and workplace scenarios unless the concept or user request clearly calls for another domain.
    • Define specialized terms at first use.
    • State any simplifications made for readability.
  3. Verify the concept:

    • Use reliable references when the derivation, history, statement, or applicability is uncertain.
    • Prefer primary sources, standard textbooks, official course notes, or authoritative encyclopedia references.
    • Do not invent historical stories, theorem proofs, or real-world applications.
    • If a topic has multiple versions, name the version being explained.

🔴 CHECKPOINT: Before writing the article, confirm these internal decisions: input type, chosen version, audience level, central question, and the 3-5 named assumptions or boundaries. If any item is unclear and cannot be resolved from the user's prompt or reliable references, ask one concise clarification question.

Write this decision sheet before drafting, then use it as the article's control plan:

ItemRequired content
Input typeOne of: axiom/postulate, theorem/proposition, viewpoint/law/principle, theory system
Chosen versionExact statement or named version being explained; mark "standard textbook version" or "user-supplied wording" when no narrower source is available
Central questionOne sentence in the reader's language, not a broad topic label
Assumptions and boundaries3-5 named premises, each with "成立时" and "不成立时" consequences
Evidence or derivation routeFor axioms: motivation/model/independence route; for theorems: definition -> lemma -> conclusion route; for viewpoints: claim -> evidence -> counterevidence route
Visual planMermaid purpose, SVG purpose, and table/TXT/second-SVG purpose; each must map to one assumption, mechanism, proof step, or failure boundary
  1. Create visuals:

    • Include at least one Mermaid diagram.
    • Include at least one standalone SVG file for mechanism, structure, boundary, geometry, set, coordinate, timeline, or comparison visuals.
    • Include at least one additional visual form: Markdown table, ASCII/TXT diagram, or another standalone SVG file.
    • Use visuals to explain causal chains, assumption boundaries, proof structure, transfer paths, or failure cases.
    • Do not use decorative visuals that do not teach anything.
  2. Write and save:

    • Create markdown/ in the current project if it does not exist.
    • Save the article as markdown/YYYYMMDD-<topic-slug>.md.
    • Save SVG assets under markdown/assets/<topic-slug>/.
    • Reference each SVG from Markdown with a relative image link: ![图名](assets/<topic-slug>/<figure-name>.svg).
    • Use a readable topic slug. Pinyin or short English is preferred; Chinese is acceptable when clearer.
    • In the final response, report the saved file path and a short summary. Do not paste the full article unless the user asks.

🔴 CHECKPOINT: Before saving the final Markdown, run this quality gate. If any row fails, revise the article or asset before responding.

GatePass condition
Concept controlThe article explains one target concept, or explicitly states why several concepts form one theory chain
求真/求存 separation"求真讲法" explains truth, acceptance, proof, derivation, or evidence; "求存讲法" explains use, transfer, boundary, and decision value
Assumption linkageEvery positive example and negative example names the assumption or boundary that makes it work or fail
Visual usefulnessMermaid, SVG, and the additional visual each teach a different mechanism, boundary, proof step, or comparison
Asset integrityEvery SVG file exists under markdown/assets/<topic-slug>/, has a valid <svg xmlns="http://www.w3.org/2000/svg" viewBox="...">, and is referenced with a relative path
Source honestyReferences distinguish user-supplied material, textbook/common knowledge, web-verified sources, and unverified claims

Failure Handling

TriggerFirst actionFallback if still unresolved
Topic is too broad, such as "explain economics" or "explain mathematics"Narrow it to one named concept in one sentence and ask the user to confirmIf the user wants a broad overview, write a map article and clearly mark that it is not a deep axiom/theorem explanation
The statement has multiple versions or disputed wordingName the selected version and cite the basis for choosing itAdd a "版本差异" paragraph and explain only the version used in the article
The proof, history, or attribution is uncertainUse cautious wording and verify with reliable referencesOmit the uncertain story or proof detail; explain the intuition and state what remains unverified
Network or source access is unavailableUse known textbook-level knowledge and mark "未联网核验" in referencesAvoid dates, quotations, origin stories, and named attributions that depend on fresh verification
The concept is advanced for the requested audienceUse analogy and intuition first, then a small formal skeletonMove advanced proof details to "进一步学习", and do not pretend the full proof was shown
The requested format conflicts with required partsPreserve 求真讲法, 求存讲法, and 思考 as sections or clearly named equivalentsIf the conflict is explicit, follow the user format but mention which required parts were mapped where
The visual plan cannot be made meaningfulReplace the weak visual with a table, boundary diagram, proof skeleton, set relation, timeline, or counterexample map tied to a named assumptionIf only one meaningful visual exists, keep it and state why the extra visual requirement would be decorative
SVG creation or validation failsRepair the SVG syntax, escape special characters, and re-check the relative Markdown linkFall back to one valid SVG plus a Markdown table; report the limitation in the final summary
References cannot verify an attribution or quoteRemove the attribution or quote and explain the concept without itMark the claim as "未联网核验" only when the claim is not central to the explanation
Show full SKILL.md (722 more words)Show less

Article Structure

Use this structure unless the user asks for a different format:

markdown
# <主题>: 一句话讲透

> 面向对象: <大学生及有一定社会阅历的成年人>
> 核心问题: <这篇文章要解决的困惑>
> 先说结论: <用一两句话说清楚它到底是什么>

## 一张图先看懂

<Mermaid 概念图、推导图、边界图或迁移图>

![<SVG 图名>](assets/<topic-slug>/<figure-name>.svg)

## 求真讲法

### 它到底说了什么

<用受过高等教育或有现实经验的成年人能听懂的语言重述>

### 它是怎么来的

<公理讲动机和选择理由;定理讲推导链;观点讲证据链>

### 它依赖哪些假设

<列出前提、定义、理想化条件、隐含边界>

### 常见误解

<说明哪些说法看似相近但其实不对>

## 求存讲法

### 它有什么用

<原生领域的作用>

### 它怎么迁移到熟悉领域

<从诞生领域迁移到学习、工作、生活、管理、技术或商业等领域>

### 它的适用范围和边界

<说明什么条件下有效,什么条件下不能乱用>

### 正例: 怎么用它提升能力

<优先使用投资理财、产品经理、产品运营、营销、人际交往或职场中的可操作例子>

### 反例: 前提不成立会怎样

<优先使用投资理财、产品经理、产品运营、营销、人际交往或职场中的失败例子,突出逻辑判断和洞察>

## 思考

<发人深省的拓展问题、反事实设问、跨学科联系>

## 最后记住

<3-5 条可复述要点>

## 参考资料

<列出参考来源;没有联网时说明基于通用知识和已知教材体系>

Explanation Standards

  • Teach from concrete to abstract: story or现象 -> intuition -> formal statement -> example -> boundary.
  • Keep "求真" and "求存" separate: first explain why it is true or why it is accepted, then explain why it matters and where it works.
  • For axioms, never say the axiom was "proved" from inside the same axiom system. Use "动机、选择理由、等价表达、独立性、模型解释" instead.
  • For theorems, separate "直观理解" from "严格证明". If the full proof is too long, provide a reliable proof skeleton and name the missing lemmas.
  • For viewpoints, expose the hidden assumptions and show what evidence would make the viewpoint stronger or weaker.
  • Explain assumptions twice when useful: once in "求真讲法" as logical premises, once in "求存讲法" as practical boundaries.
  • Use examples that adults can observe, summarize, and reuse. Prefer investment and personal finance, product management, product operations, marketing, interpersonal relationships, and workplace examples. Use university learning, technology, health, or other domains only when they better fit the concept or the user's request.
  • Include at least one positive example and one negative example. The negative example must fail because a named assumption is false, not because the person "did it wrong" vaguely.
  • Use concise headings and short paragraphs. Avoid empty motivational language.
  • Mark uncertain claims explicitly instead of overstating them.

Anti-Patterns

Do not:

  • Prove an axiom from inside the same axiom system.
  • Present a slogan, aphorism, or famous quote as true without exposing its assumptions.
  • Invent historical anecdotes, named attributions, theorem proofs, textbook references, or real-world cases.
  • Treat a famous attribution as evidence for a principle.
  • Use a Mermaid chart, SVG, or table as decoration; every visual must teach a mechanism, boundary, proof chain, or counterexample.
  • Put inline SVG markup directly inside the Markdown article.
  • Reference SVG files with absolute local paths, file:// URLs, remote placeholder URLs, or paths outside markdown/assets/<topic-slug>/.
  • Collapse "why it is true or accepted" and "why it is useful" into one mixed explanation.
  • Give a negative example where the only reason for failure is "the person did not work hard" or another vague moral judgment.
  • Write a broad motivational essay instead of explaining the target concept.
  • Let examples float without naming which assumption, boundary, or proof step they illustrate.
  • Say "this is useful everywhere" or imply universal transfer without listing failure conditions.
  • Paste the full article in the final response after saving it, unless the user explicitly asks.

Visual Standards

Use diagrams as teaching tools:

mermaid
flowchart LR
  A["前提假设"] --> B["推导/选择理由"]
  B --> C["结论"]
  C --> D["可迁移应用"]
  A -. "不成立" .-> E["反例/失效边界"]

Useful visual patterns:

  • Mermaid flowchart for assumption -> reasoning -> conclusion -> application.
  • Mermaid timeline for historical development.
  • Standalone SVG for geometric, spatial, set, coordinate, mechanism, layered-system, payoff, probability, or boundary diagrams.
  • Markdown table for "前提成立/前提不成立" comparisons.
  • TXT/ASCII diagram only for simple contrasts or before/after relationships.

SVG file rules:

  • Create markdown/assets/<topic-slug>/ before writing SVG files.
  • Use lowercase hyphenated SVG filenames, such as assumption-boundary.svg or proof-chain.svg.
  • Keep each SVG self-contained: include <svg xmlns="http://www.w3.org/2000/svg" viewBox="...">, embedded text, shapes, labels, and arrows; do not depend on external fonts, CSS, scripts, or remote images.
  • Use readable dimensions through viewBox; avoid fixed tiny canvases.
  • Escape special characters in SVG text, especially &, <, and >.
  • Reference the SVG in Markdown with relative syntax only: ![假设边界图](assets/<topic-slug>/assumption-boundary.svg).
  • Use SVG aggressively when it improves comprehension: prefer 2-4 standalone SVG figures for complex topics, especially when explaining boundaries, set relations, geometric intuition, proof skeletons, feedback loops, tradeoff curves, or counterexamples.

Do not add fake image URLs. If using an external image, cite its source and make sure it directly supports the explanation.

Final Checks

Before finishing, verify:

  • The article is saved under the current project's markdown/ directory.
  • SVG assets are saved under markdown/assets/<topic-slug>/ and referenced from the article with relative links.
  • The Markdown contains the three required parts: 求真讲法, 求存讲法, and 思考.
  • The explanation names the assumptions behind the concept.
  • The article includes at least one Mermaid diagram, at least one standalone SVG file reference, and one additional visual/table/SVG/TXT figure.
  • The article includes positive and negative examples tied to the assumptions.
  • Positive and negative examples preferentially come from investment and personal finance, product management, product operations, marketing, interpersonal relationships, or workplace scenarios unless another domain is clearly more suitable.
  • The article distinguishes derivation, proof, motivation, and applicability boundaries correctly.
  • Any uncertain statement is marked or removed.
  • The article does not contain any anti-pattern listed above.
  • The final response gives the saved path and does not flood the user with the full article.

© digoal, GPL-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files in skills/axiom-explainer of digoal/blog.

  • SKILL.md
  • agents/openai.yaml
  • test-prompts.json

Open the folder on GitHubat commit ad6fcb7

Compare with similar skills

Axiom Explainer 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.

Axiom Explainer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Axiom Explainer this skilldigoal/blog8.6k—~3.6kAutomated safety check: PassGPL-2.0
Markdown Report WritingNeuroAIHub/BrainPilot1.1k—~2.6kAutomated safety check: WarnAGPL-3.0
Markdown Syntax Guideantdigital-ai/agentic-ui224—~3.1kAutomated safety check: PassMIT
Bm Mdmiantiao-me/bm.md617—~2.1kAutomated safety check: PassLGPL-3.0
Chatbot Mvp Distillationpdsuwwz/chatgpt-vue3-light-mvp578—~722Automated safety check: PassMIT
Chatbot Mvp Distillation Zhpdsuwwz/chatgpt-vue3-light-mvp578—~414Automated safety check: PassMIT

Similar skills

  • Markdown Report Writing

    NeuroAIHub/BrainPilot

    Guide AI agents to write beautifully formatted, well-illustrated Markdown reports with proper structure, diagrams, and compatibility across GitHub and Obsidian.

    1.1k GitHub stars~2.6k tokensUpdated 6 days ago
    Documents & OfficeAuto-check: warnings
  • Markdown Syntax Guide

    antdigital-ai/agentic-ui

    指导用户使用 @ant-design/agentic-ui 的 Markdown Editor / Renderer 扩展语法。图表场景优先使用内置 chart(HTML 注释 chartType + 表格),只有当内置 chartType 都不能表达诉求时才回退 Mermaid。Triggers on keywords like 表格, 视频, 图表, 卡片, 提示块, 流程图, 语法…

    224 GitHub stars~3.1k tokensUpdated today
    Documents & OfficeAuto-check passed
  • Bm Md

    miantiao-me/bm.md

    使用 bm.md 写作、改写、排版或渲染 Markdown;生成 Mermaid 与 AntV Infographic,设置图片尺寸、高亮重点,以及执行 HTML/纯文本转换和 Markdown lint

    617 GitHub stars~2.1k tokensUpdated 9 days ago
    Media & CreativeAuto-check passed
  • Chatbot Mvp Distillation

    pdsuwwz/chatgpt-vue3-light-mvp

    Distill the chatgpt-vue3-light-mvp project into reusable architecture for building similar ChatGPT-style web products in other repositories.

    578 GitHub stars~722 tokensUpdated 2 mo ago
    DevelopmentAuto-check passed
  • Chatbot Mvp Distillation Zh

    pdsuwwz/chatgpt-vue3-light-mvp

    将 chatgpt-vue3-light-mvp 项目蒸馏为可迁移到其他项目的中文架构指南。适用于设计或实现类似 ChatGPT 的 Web 对话产品,包括 SSE/fetch 流式响应、模型适配器契约、打字机渲染、Markdown/代码/KaTeX/Mermaid 渲染、推理过程展示,以及从本 Vue 3 MVP 迁移到其他项目的方案规划。

    578 GitHub stars~414 tokensUpdated 2 mo ago
    DevelopmentAuto-check passed
  • Markdown Mermaid Writing

    K-Dense-AI/scientific-agent-skills

    Writes scientific Markdown documentation and Mermaid diagrams for workflows, relationships, timelines, and schemas.

    48k GitHub starsUsed in 1 repo~4.2k tokens
    DevelopmentAuto-check: notes

More from digoal/blog

All 98 skills in this repo
  • 三层审查模型,逐段逐句验证文章真伪、证据链与逻辑结构。Use when the user asks to fact-check, verify, audit, or evaluate the credibility of an article, essay, report, opinion piece, social-media post, or any written claim —…

    8.6k GitHub stars~939 tokensUpdated today
    Auto-check passed
  • Find latent bugs in a local PostgreSQL source tree (RELxxSTABLE branch or HEAD) the way a core hacker does: build a heavily-poisoned debug instance (cassert + cache-discard + -O0/-ggdb3 + core…

    8.6k GitHub stars~4k tokensUpdated today
    Auto-check passed
  • Digoal

    digoal/blog

    Portable digital employee distilled from digoal's personal blog for PostgreSQL, PolarDB, DuckDB, AI+database, vector/RAG, database operations, source-code reading, technical content creation…

    8.6k GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • 从论文 PDF 文件或论文 PDF URL 生成通俗易懂、图文并茂、带批判性评估的中文 Markdown 解读,并保存到当前项目的 markdown 目录。Use when the user asks to interpret,精读,解读,summarize,explain,analyze, or write an article from an academic paper PDF…

    8.6k GitHub stars~1.5k tokensUpdated today
    Auto-check passed
  • Analyze a product from documentation, websites, PDFs, articles, release notes, pricing pages, app listings, reviews, filings, or related links; save separate intermediate analyses from seven roles…

    8.6k GitHub stars~1.8k tokensUpdated today
    Auto-check passed
  • Turn a blog post, article, notes, or any source material into a set of vertical poster images — one cover plus several coherent content slides that explain the core points.

    8.6k GitHub stars~1.4k tokensUpdated today
    Auto-check passed

Works with

Questions about Axiom Explainer

What does Axiom Explainer do?

Write Chinese Markdown articles for university students and adults with social experience that explain one viewpoint, axiom, theorem, law, principle, or theory system through "求真讲法、求存讲法、思考", with…. Axiom Explainer is an agent skill from digoal/blog. Write Chinese Markdown articles for university students and adults with social experience that explain one viewpoint, axiom, theorem, law, principle, or theory system through "求真讲法、求存讲法、思考", with text/Mermaid and standalone GitHub-renderable SVG files, assumptions, derivation or motivation, applicability boundaries, positive and negative examples, and save the result under the current project's markdown directory.

When should I use Axiom Explainer?

Axiom Explainer fits situations like: Codex is asked to generate 公理讲解文案、定理讲解、理论体系通俗解读、观点拆解、面向大学生和成年人的图文并茂 Markdown 文章; tasks that involve Diagrams; tasks that involve Markdown.

How do I install Axiom Explainer in Claude Code?

Run `npx skills add digoal/blog --skill axiom-explainer -a claude-code`. Or copy the skill folder (skills/axiom-explainer in digoal/blog) into .claude/skills/axiom-explainer in your project. Claude Code loads it when a task matches its description.

How do I install Axiom Explainer in Codex?

Run `npx skills add digoal/blog --skill axiom-explainer -a codex`. Or copy the skill folder (skills/axiom-explainer in digoal/blog) into .agents/skills/axiom-explainer in your project. Codex loads it when a task matches its description.

Can I use Axiom Explainer 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 digoal/blog --skill axiom-explainer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/axiom-explainer, .gemini/skills/axiom-explainer, .github/skills/axiom-explainer and .opencode/skills/axiom-explainer in your project.

What does Axiom Explainer need to run?

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

Does Axiom Explainer access the network?

SKILL.md names 1 domain. In commands or code: w3.org; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Axiom Explainer 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 Axiom Explainer use?

Axiom Explainer is published under the GPL-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Axiom Explainer use?

About 3.6k tokens (SKILL.md is roughly 15k 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 Axiom Explainer?

Skills that share tags, products or a category with Axiom Explainer: Markdown Report Writing (NeuroAIHub/BrainPilot, 1.1k stars), Markdown Syntax Guide (antdigital-ai/agentic-ui, 224 stars), Bm Md (miantiao-me/bm.md, 617 stars) and Chatbot Mvp Distillation (pdsuwwz/chatgpt-vue3-light-mvp, 578 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Axiom Explainer?

digoal (a GitHub user) maintains it in digoal/blog, which has 8,586 GitHub stars. The repository holds 98 skills in this directory. The repository was last updated on October 9, 2026.

Source: digoal/blog on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.