mirror of
https://github.com/herdrdev/herdr.git
synced 2026-11-06 00:06:18 +00:00
chore: point agents at the source instead of agent-guide and llms.txt
This commit is contained in:
Ogulcan Celik
@@ -7,8 +7,6 @@ Herdr ships a reusable agent skill file at [`skills/herdr/SKILL.md`](https://git
|
||||
|
||||
Install that file into any coding agent that supports reusable skills or custom instructions. The skill teaches the agent how to control Herdr from inside a Herdr pane.
|
||||
|
||||
Herdr also serves a separate guide at [`herdr.dev/agent-guide.md`](https://herdr.dev/agent-guide.md) for a different job: an agent helping a human learn, set up, or troubleshoot Herdr. The skill is for an agent operating Herdr; the guide is for an agent teaching a human.
|
||||
|
||||
## What the skill does
|
||||
|
||||
The skill tells an agent to use the `herdr` CLI when `HERDR_ENV=1` is set. That means the agent is running inside a Herdr-managed pane and can safely talk to the local Herdr socket.
|
||||
|
||||
@@ -36,10 +36,10 @@ import { Card, CardGrid } from '@astrojs/starlight/components';
|
||||
If you already run an AI coding agent, let it handle the onboarding. Paste this prompt:
|
||||
|
||||
```text
|
||||
Help me understand and set up Herdr. Read https://herdr.dev/agent-guide.md first, then walk me through it step by step.
|
||||
Help me understand and set up Herdr. Its source and docs are at https://github.com/herdrdev/herdr. Read what you need there, then walk me through it step by step.
|
||||
```
|
||||
|
||||
The guide covers Herdr's concepts, setup, configuration, and common fixes, so your agent can answer from the docs instead of improvising.
|
||||
Your agent answers from the real source and docs instead of improvising.
|
||||
|
||||
## Core guides
|
||||
|
||||
|
||||
@@ -7,8 +7,6 @@ Herdr は再利用可能なエージェントスキルファイルを [`skills/h
|
||||
|
||||
このファイルを、再利用可能なスキルやカスタム指示に対応した任意のコーディングエージェントにインストールしてください。このスキルは、Herdr のペイン内から Herdr を制御する方法をエージェントに教えます。
|
||||
|
||||
Herdr は別の用途向けに [`herdr.dev/agent-guide.md`](https://herdr.dev/agent-guide.md) というガイドも提供しています。こちらは、人間が Herdr を学習・セットアップ・トラブルシューティングするのをエージェントが手伝うためのものです。スキルは Herdr を操作するエージェントのため、ガイドは人間に教えるエージェントのためのものです。
|
||||
|
||||
## スキルがすること
|
||||
|
||||
このスキルは、`HERDR_ENV=1` が設定されているときに `herdr` CLI を使うようエージェントに指示します。これは、エージェントが Herdr 管理下のペイン内で動作しており、ローカルの Herdr ソケットと安全に通信できることを意味します。
|
||||
|
||||
@@ -36,10 +36,10 @@ import { Card, CardGrid } from '@astrojs/starlight/components';
|
||||
すでに AI コーディングエージェントを使っていますか? オンボーディングはエージェントに任せましょう。このプロンプトを貼り付けてください:
|
||||
|
||||
```text
|
||||
Help me understand and set up Herdr. Read https://herdr.dev/agent-guide.md first, then walk me through it step by step.
|
||||
Help me understand and set up Herdr. Its source and docs are at https://github.com/herdrdev/herdr. Read what you need there, then walk me through it step by step.
|
||||
```
|
||||
|
||||
このガイドはエージェントに Herdr のコンセプト、セットアップ、設定、よくある問題の解決方法を教えるので、エージェントの回答が即興ではなく正確なままになります。
|
||||
エージェントは即興ではなく、実際のソースとドキュメントを読んで答えます。
|
||||
|
||||
## コアガイド
|
||||
|
||||
|
||||
@@ -7,8 +7,6 @@ Herdr 提供了一个可复用的智能体技能文件: [`skills/herdr/SKILL.md`
|
||||
|
||||
把这个文件安装到任何支持可复用技能或自定义指令的编程智能体中。这份技能教智能体如何在 Herdr 窗格内部控制 Herdr。
|
||||
|
||||
Herdr 还提供了另一份用途不同的指南: [`herdr.dev/agent-guide.md`](https://herdr.dev/agent-guide.md),用于让智能体帮助人类学习、安装或排查 Herdr。技能是给操作 Herdr 的智能体用的;指南是给教人类的智能体用的。
|
||||
|
||||
## 这份技能做什么
|
||||
|
||||
这份技能告诉智能体: 当 `HERDR_ENV=1` 已设置时,使用 `herdr` CLI。这意味着智能体运行在 Herdr 管理的窗格内,可以安全地与本地 Herdr socket 通信。
|
||||
|
||||
@@ -36,10 +36,10 @@ import { Card, CardGrid } from '@astrojs/starlight/components';
|
||||
已经在用 AI 编程智能体?让它来帮你完成入门。粘贴这个提示词:
|
||||
|
||||
```text
|
||||
Help me understand and set up Herdr. Read https://herdr.dev/agent-guide.md first, then walk me through it step by step.
|
||||
Help me understand and set up Herdr. Its source and docs are at https://github.com/herdrdev/herdr. Read what you need there, then walk me through it step by step.
|
||||
```
|
||||
|
||||
这份指南会教你的智能体 Herdr 的概念、安装、配置和常见问题的修复方法,让它的回答保持准确,而不是即兴发挥。
|
||||
你的智能体会阅读真实的源码和文档来回答,而不是即兴发挥。
|
||||
|
||||
## 核心指南
|
||||
|
||||
|
||||
+3
-5
@@ -46,12 +46,10 @@ const TERMINAL_SESSION_CONTROL_USAGE: &str =
|
||||
"usage: herdr terminal session control <target> [--takeover] [--cols N] [--rows N]";
|
||||
pub(crate) const AGENT_HELP_FOOTER: &str = concat!(
|
||||
"Are you an AI? Use these resources ONLY IF your task specifically asks you to:\n",
|
||||
" Help a human understand or set up Herdr for the first time:\n",
|
||||
" https://herdr.dev/agent-guide.md\n",
|
||||
" Debug or investigate a problem with Herdr:\n",
|
||||
" https://herdr.dev/llms.txt\n",
|
||||
" Control Herdr panes, agents, or workspaces:\n",
|
||||
" SKIP if a Herdr skill is already in your context. Otherwise run: herdr --skill",
|
||||
" SKIP if a Herdr skill is already in your context. Otherwise run: herdr --skill\n",
|
||||
" Help a human understand or set up Herdr, or debug a problem with it:\n",
|
||||
" read the source and docs: https://github.com/herdrdev/herdr",
|
||||
);
|
||||
|
||||
pub(crate) fn parse_token_assignment(raw: &str) -> Result<(String, Option<String>), String> {
|
||||
|
||||
@@ -287,9 +287,8 @@ fn root_and_command_group_help_point_agents_to_plain_text_docs() {
|
||||
let stdout = String::from_utf8_lossy(&output.stdout);
|
||||
for expected in [
|
||||
"Are you an AI? Use these resources ONLY IF your task specifically asks you to:",
|
||||
"https://herdr.dev/agent-guide.md",
|
||||
"https://herdr.dev/llms.txt",
|
||||
"herdr --skill",
|
||||
"https://github.com/herdrdev/herdr",
|
||||
] {
|
||||
assert!(
|
||||
stdout.contains(expected),
|
||||
|
||||
Reference in New Issue
Block a user