重写 Skill 安装指引,让 agent 可自主完成安装与鉴权#1058
Closed
mingxingmeng-ctrl wants to merge 1 commit into
Closed
Conversation
Rewrite the Skill installation guide so an AI agent can follow it end-to-end. Replace per-line execution tags with one meta-rule plus intent-driven methods gated on observable conditions (brew presence, auth status, shell availability). Document the real auth model (env-var headless; device-flow login the agent drives, human approves), the sudo/real-terminal install gate, Homebrew fallback to the curl script, and that /plugin commands are interactive-only. Verified end-to-end by fresh agents (install + login + live quote). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Contributor
Author
|
Superseded by #1059 — 已获组织写权限,改为同仓 PR(head 从 fork 切到上游分支)。 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
合入判断
[APPROVE] — 纯文档改写,重构 Skill 安装指引为「agent 可自路由」结构,内容已对 CLI 源码 + changelog + 两轮全新 agent 端到端实测逐条验证。
变更概要
skill/install/index.md(三语言同步):把鉴权章节从一行含糊的「在浏览器完成 OAuth」改写为 agent 可消费的完整模型——env-var headless、device-flow(agent 驱动 + 人浏览器批准)、安装 sudo 需真实终端、Homebrew 缺失回退 curl、/plugin仅交互式。command -v brew、auth status、有无 shell)上,让 agent 自决。<!-- AI INSTRUCTION -->块为权威 checklist;正文人类向内容(示例、restrictions、截图)保留。风险分析
longbridge-terminalv0.22.1 源码(auth.rs/cli/mod.rs/region.rs/context.rs)+ 仓库 changelog 核实;两轮全新 subagent 实测装通 + 登录 + 拉到 AAPL 实时行情设计决策
auth status:已有有效 token 即跳过,避免对已登录机器多弹一次浏览器批准。.cnregion 提示:CLI 自动选区,授权 URL/接口可能落open.longbridge.cn——文档显式说明以免误判为钓鱼链接(已 region.rs 核实 + 实测复现)。代码关注点
npx skills add longbridge/skills -g作为 agent-runnable 的 Skill 安装路径 (docs/*/skill/install/index.mdStep 2)该工具是 Vercel Labs 的跨平台 skills 生态(已核实非 Claude Code 插件系统),装到
~/.claude/skills/;建议 reviewer 确认longbridge/skills仓可被该工具消费(命令沿用原文档已有写法,未改)。open.longbridge.cn(挂在.com入口下)——属longbridge-terminal仓脚本问题,非本 PR 范围,建议单独反馈。验证状态
✅ 命令对 CLI 源码核实 · ✅ 两轮全新 agent 端到端实测(装→登录→实时行情)· 📋 无 CI 代码测试(纯文档)