Skip to main content
skillsmp

Menu

kun

Summon Kun to solve your problems. Use on /kun or when asked how Kun thinks, builds, or solves problems.

Ir para a instalaçãoRevisar arquivos

Informações da origem

Repositório
kunchenguid/kun
Última atividade na origem
1 de outubro de 2026 às 03:42
Idioma detectado do SKILL.md
inglês
Estrelas
407
Forks
40

kun: engineering advice from Kun Chen’s public knowledge base

Answers engineering questions using Kun Chen’s public instructions, tools, opinions, and working style.

Examples

In his follow-up post, Kun says the Skill and his Grok bot share the same knowledge base. This is the author’s description of the two interfaces.

Uses

The author’s README gives starting points for improving AGENTS.md, debugging, and thinking through a product idea.

Prerequisites

The agent needs access to the repository’s public instruction files: ENTRY.md, TOOLS.md, OPINIONS.md, and VOICE.md. Read the full files before answering; raw GitHub URLs have a jsDelivr fallback.

How to use

The author provides this first request:

/kun how should I improve my AGENTS.md?

The Skill loads the public instructions before applying them to the question.

Limitations

The instructions live on the repository’s main branch and can change independently of the installed Skill. If the files cannot be fetched, the Skill requires the agent to stop and report the failure.

Sources

Opções de instalação

Por padrão, está selecionado o prompt que primeiro revisa a origem. Você pode mudar para um comando direto ou baixar uma cópia local.

Revise os arquivos de origem

Leia o SKILL.md e os arquivos complementares exibidos pelo SkillsMP antes de decidir se vai instalar.

Exibindo SKILL.md

SKILL.md
Instruções da origem · Visualização somente leitura
name
kun
description
Summon Kun to solve your problems. Use on /kun or when asked how Kun thinks, builds, or solves problems.
user-invocable
true
metadata
{"short-description":"Summon Kun to solve your problems."}
# /kun Load the latest instructions from `kunchenguid/kun` via the public pull script, then answer from the local cache. Do not guess file contents. ## Loading instructions ### 1. Pull (no LLM) Download the public pull script, then run it with Node. Prefer raw GitHub; use jsDelivr only as fallback: - `https://raw.githubusercontent.com/kunchenguid/kun/main/scripts/pull-kun.mjs` - fallback: `https://cdn.jsdelivr.net/gh/kunchenguid/kun@main/scripts/pull-kun.mjs` ```sh # cache defaults to $KUN_PULL_DIR or ~/.cache/kun node /path/to/pull-kun.mjs --dir <cache> ``` The script is incremental via `content/MANIFEST.json`: it syncs root docs (`ENTRY.md`, `TOOLS.md`, `OPINIONS.md`, `VOICE.md`) and only new/changed `content/` files. Do **not** re-fetch every content file by hand. If the pull fails, **stop and say so**. Do not guess. ### 2. Read from the local cache After a successful pull, read the **FULL** local copies from `<cache>`: - `ENTRY.md` - `TOOLS.md` - `OPINIONS.md` - `VOICE.md` When a question needs Kun's actual words, open matching files under `<cache>/content/` (do not dump the whole tree into context). ### 3. Answer Follow `ENTRY.md` exactly to answer the user.
Ver no GitHub
Voltar à pesquisaVoltar à instalação