mxyhi/ok-skills / deep-research
deep-research
UnverifiedProfessional deep research report generation — multi-agent collaboration with parallel chapter writing, automatic latest-data targeting, multilingual output, and built-in quality checks.
| File | Kind | Size |
|---|---|---|
| LICENSE | other | 1.0 KB |
| RULES.md | markdown | 6.9 KB |
| SKILL.md | skill md | 34.7 KB |
| TYPES.md | markdown | 4.9 KB |
| VERSION | other | 6 B |
| command/research.md | markdown | 751 B |
| command/update.md | markdown | 1.4 KB |
| profiles.json | config | 344 B |
| prompts/task1_outline.md | markdown | 8.8 KB |
| prompts/task2_data_collection.md | markdown | 28.9 KB |
| prompts/task3_chapter_agent.md | markdown | 3.8 KB |
| prompts/task4_assembly.md | markdown | 6.2 KB |
| reports-browser/favicon.svg | other | 241 B |
| reports-browser/html-docx.min.js | script | 406.3 KB |
| reports-browser/html2pdf.bundle.min.js | script | 884.7 KB |
| reports-browser/index.html | other | 19.1 KB |
| reports-browser/marked.min.js | script | 51.6 KB |
| reports-browser/reports.json | config | 2 B |
| scrapling-mcp-server.py | script | 6.6 KB |
| sources.json | config | 7.5 KB |
| tools/dr_check.py | script | 21.2 KB |
| tools/dr_gen.py | script | 36.8 KB |
| tools/dr_tools.py | script | 17.2 KB |
| tools/generate_pages.py | script | 28.4 KB |
| tools/lang_config.py | script | 24.1 KB |
command/update.md
View on GitHub---
description: 从 GitHub 拉取 deep-research skill 最新代码
---
<command-instruction>
你是一个自动更新工具。你的任务是从 GitHub 拉取 deep-research skill 的最新代码,不需要版本检查,不需要用户确认。
## 执行流程
### Step 1 — 定位 skill 目录
通过以下方式查找 skill 目录(不同工具的 skill 安装位置不同,现场探测即可):
- 检查当前工作目录是否就是 skill 根目录(存在 VERSION 文件)
- 或在常见位置查找 deep-research 的 VERSION 文件(如 `~/.opencode/skills`、`~/.claude/skills`、`.cursor/skills` 等)
如果找不到 → 提示"找不到 deep-research skill 目录",给出手动克隆命令后退出。
### Step 2 — 检查 git 仓库
确认目录是 git 仓库(存在 `.git` 目录)。如果不是 → 用 `git clone` 克隆到临时目录再复制过来。
### Step 3 — 直接拉取最新代码
**不需要读取 VERSION,不需要比较版本,不需要用户确认。** 直接执行:
```
git pull origin main
```
如果 pull 失败(网络、冲突等)→ 提示"更新失败: {具体原因}"后退出。
### Step 4 — 完成
提示已更新到最新版本。
### 输出示例
```
[✓] 已从 main 分支拉取最新代码
```
</command-instruction>
<user-request>
$ARGUMENTS
</user-request>
---
```
deep-research by hoolulu · github.com/hoolulu/deep-research
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |