Web Research
Juncai22/spring-ai-agent-learning
A skill your agent uses for requests related to web research; it provides a structured approach to conducting comprehensive web research
Parallel multi-AI cross-validation research workflow (大版本). An agent skill from majiayu000/spellbook.
Install Multi AI Research
$ npx skills add majiayu000/spellbook --skill multi-ai-research -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install majiayu000/spellbook multi-ai-research --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/majiayu000/spellbook.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/multi-ai-research .claude/skills/multi-ai-research && rm -rf skills-srcUse ~/.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/
Install the "multi-ai-research" agent skill from https://github.com/majiayu000/spellbook/tree/main/skills/multi-ai-research into .claude/skills/multi-ai-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "multi-ai-research", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/majiayu000/spellbook/tree/main/skills/multi-ai-researchType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add majiayu000/spellbook --skill multi-ai-research -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install majiayu000/spellbook multi-ai-research --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/majiayu000/spellbook.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/multi-ai-research .agents/skills/multi-ai-research && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "multi-ai-research" agent skill from https://github.com/majiayu000/spellbook/tree/main/skills/multi-ai-research into .agents/skills/multi-ai-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "multi-ai-research", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add majiayu000/spellbook --skill multi-ai-research -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install majiayu000/spellbook multi-ai-research --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/majiayu000/spellbook.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/multi-ai-research .cursor/skills/multi-ai-research && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "multi-ai-research" agent skill from https://github.com/majiayu000/spellbook/tree/main/skills/multi-ai-research into .cursor/skills/multi-ai-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "multi-ai-research", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/majiayu000/spellbook.git --path skills/multi-ai-research--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add majiayu000/spellbook --skill multi-ai-research -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install majiayu000/spellbook multi-ai-research --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/majiayu000/spellbook.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/multi-ai-research .gemini/skills/multi-ai-research && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "multi-ai-research" agent skill from https://github.com/majiayu000/spellbook/tree/main/skills/multi-ai-research into .gemini/skills/multi-ai-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "multi-ai-research", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install majiayu000/spellbook multi-ai-researchInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add majiayu000/spellbook --skill multi-ai-research -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/majiayu000/spellbook.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/multi-ai-research .github/skills/multi-ai-research && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "multi-ai-research" agent skill from https://github.com/majiayu000/spellbook/tree/main/skills/multi-ai-research into .github/skills/multi-ai-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "multi-ai-research", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add majiayu000/spellbook --skill multi-ai-research -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install majiayu000/spellbook multi-ai-research --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/majiayu000/spellbook.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/multi-ai-research .opencode/skills/multi-ai-research && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "multi-ai-research" agent skill from https://github.com/majiayu000/spellbook/tree/main/skills/multi-ai-research into .opencode/skills/multi-ai-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "multi-ai-research", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
multi-ai-research- GitHub stars
- 287
- Token cost
- ~2k tokens
- SKILL.md length
- 605 words
- Files
- 2
- Skills in repo
- 97
- Repo updated
- First seen
- Licence
- MIT
At a glance
Parallel multi-AI cross-validation research workflow (大版本). An agent skill from majiayu000/spellbook.
- Works in 8 steps: ：问题分解（Claude 自动 + 用户可覆盖） → ：Prompt 自动生成 → ：并行派发（一条消息多个工具调用） → …
- User says 多 AI 调研
- SKILL.md covers 何时触发, 工作流（7 Phase）, ⚠️ 命令速查（防呆，最先看这个） and 首次使用：安装 opencli（5 分钟一次性）, plus 1 more section
- Calls npm and npx
What it does
Multi AI Research is an agent skill from majiayu000/spellbook. Parallel multi-AI cross-validation research workflow (大版本). Dispatch N internal sub-agents + grok + gemini in parallel, automatically cross-validate findings, tier by confidence (strong consensus / partial / conflict / insufficient), generate tiered action items with arbitration. Use when user says "多 AI 调研", "交叉验证", "独立共识", "三脑调研", "multi-ai research", "parallel research", "cross-validate", or needs deep research that benefits from internal data + external 2026 consensus. NOT for quick factual Q&A, pure code…
Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `reference/extended.md`).
It sits in Research & Science, covering Subagents, Machine learning and Deep research. The repository describes itself as: Cross-runtime skills for Claude Code, Codex, and multi-agent workflows. The licence is MIT.
When your agent uses it
- User says 多 AI 调研
- Multi-ai research
- Parallel research
- Needs deep research that benefits from internal data + external 2026 consensus
Example prompts
- “多 AI 调研”
- “multi-ai research”
- “parallel research”
- “/multi-ai-research”
Requirements
- Node.js
Workflow steps
8 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit ed52af7. 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
Shell commands in SKILL.md call:
npmnpx
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
github.comnpmjs.com
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
Multi AI Research loads about 2k tokens when it runs. Until then it costs about 146 tokens; SKILL.md has 605 words of instructions outside code blocks.
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 majiayu000/spellbook at commit ed52af7, republished under its MIT licence (© majiayu000). 605 words, ~2,039 tokens.
Download SKILL.mdSave it as
.claude/skills/multi-ai-research/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- multi-ai-research
- description
- Parallel multi-AI cross-validation research workflow (大版本). Dispatch N internal sub-agents + grok + gemini in parallel, automatically cross-validate findings, tier by confidence (strong consensus / partial / conflict / insufficient), generate tiered action items with arbitration. Use when user says "多 AI 调研", "交叉验证", "独立共识", "三脑调研", "multi-ai research", "parallel research", "cross-validate", or needs deep research that benefits from internal data + external 2026 consensus. NOT for quick factual Q&A, pure code reasoning, or tasks needing deep project context.
<!-- v1 | 2026-04-09 | 从 2026-04-08 X reply deboost 调研实战沉淀；集成自动置信度分级 + 仲裁 + 改动清单 -->Multi-AI Research（并行多 AI 交叉验证）
核心价值：能力乘法，不是加法。Claude（主脑）+ grok（X 社区/实时）+ gemini（Google 生态/结构化）+ N 个内部 sub-agent = N+3 个 agent 并行处理同一个研究问题。
关键洞察（2026-04-08 实战验证）：两个独立外部 AI 的共识信号 强于 任何单个 AI 的深度。"更深度" < "更少错"。
和 ask-opencli 的关系：
ask-opencli= 单次 grok 或 gemini 调用（日常 second opinion）multi-ai-research= 完整调研工作流，并行多 AI + 内部数据 + 交叉验证 + 自动仲裁
如果用户只是想"问 grok 一个问题"，用 ask-opencli。如果用户要做"深度调研"或"交叉验证多个维度"，用这个 skill。
何时触发
✅ 适合
- 深度研究任务（手动做 >30 分钟）
- 行业机制问题（算法规则、产品决策、社区共识）
- 需要外部共识加权的内部数据推断
- 时效性问题（grok 有实时 X 数据，gemini 有最新 web 索引）
- 反转既有假设（数据 vs 理论冲突时仲裁）
- 新工具/新做法的可行性调研
❌ 不适合
- 纯代码推理（单个 Claude 足够）
- 需要深度项目 context 的任务（外部 AI 不了解你的代码库）
- 快速事实问答（<30 秒能解决，并行开销不值）
- 创意生成（单家强模型即可）
工作流（7 Phase）
Phase 1：问题分解（Claude 自动 + 用户可覆盖）
从用户的一个研究问题，自动拆分成：
内部数据查询（1-5 个 sub-agent 并行）
- 数据分布/量化分析
- 内容对比/质性分析
- 多维度切分
- 时序/趋势分析
- （按需增加）
外部理论查询（2 个 Bash 并行）
- grok：侧重实时/社区/X 信号
- gemini：侧重结构化/框架/长推理
默认分解策略：
- 3 个内部 agent + 2 个外部 AI = 5 个并行任务
- 如果用户问题偏理论 → 减少内部 agent 到 1-2 个，加大外部 AI 权重
- 如果用户问题偏数据 → 加到 4-5 个内部 agent，只跑 2 个外部 AI 做交叉
用户可覆盖：用户明确说"只问 grok 和 gemini"或"只派内部 agent"时按用户指令。
Phase 2：Prompt 自动生成
对每个并行任务，自动生成具体 prompt：
内部 agent prompt 模板
你的任务是**只读数据分析**，不要修改任何文件。
## 背景
{{研究问题的 2-3 句背景描述}}
## 数据源
{{数据库路径或文件列表}}
## 任务
{{具体要查的维度，1-5 个 task}}
## 输出格式
- 结构化 markdown 报告
- 每个结论标注 n（样本数）和 置信度
- 3 屏幕内
- 纯文本返回，不要尝试写文件grok / gemini prompt 模板
{{研究问题的精简描述，≤300 字}}
具体问：
(1) {{子问题 1}}
(2) {{子问题 2}}
...
请基于 2026 年上半年真实情况/最新数据回答，要具体可引用。关键要求：问 grok 和 gemini 的 prompt 必须一致（独立对比的前提）。
Phase 3：并行派发（一条消息多个工具调用）
Tool 1: Agent (general-purpose) run_in_background=true [内部数据 agent A]
Tool 2: Agent (general-purpose) run_in_background=true [内部数据 agent B]
Tool 3: Agent (general-purpose) run_in_background=true [内部数据 agent C]
Tool 4: Bash run_in_background=true [OPENCLI_BROWSER_COMMAND_TIMEOUT=300 opencli grok ask "..." --timeout 300 -f json]
Tool 5: Bash run_in_background=true [opencli gemini ask "..." --format plain]必须在 Claude 的同一条 assistant 消息里一次性调用多个工具，才能真正并行。
Phase 4：等待（不要 poll）
Background agent / Bash 任务完成会自动通知。在等的时候，Claude 可以：
- 读现有 docs / memory 获取更多 context
- 准备输出结构
- 做初步的 Phase 5/6 分析框架
明确禁止：
- 不要 sleep + 轮询任务状态
- 不要主动 Read output 文件（除非收到完成通知）
- 不要抢跑做结论
Phase 5：交叉验证 + 自动置信度分级（大版本核心）
所有结果回来后，按 4 层分类规则自动仲裁每个发现：
分类规则矩阵
| Tier | 判定条件 | 置信度 | 处理 |
|---|---|---|---|
| 🟢 Strong consensus | 内部数据(n≥20) + grok + gemini 全部支持 | 高 | 可直接写进最终结论，作为硬依据 |
| 🟡 Partial consensus | 内部数据 + 1 家外部 AI 支持 | 中 | 小幅建议，保留怀疑 |
| 🔴 Conflict | 内部数据 vs 外部 AI 矛盾 | 需仲裁 | 按仲裁原则决定 |
| ⚪ Insufficient data | 内部数据 n<10 且没有强外部支持 | 低 | 标为假设，需 A/B 测试 |
仲裁原则（自动执行）
原则 1：样本量门槛
- n ≥ 20：可作为高置信度依据
- 10 ≤ n < 20：中置信度，小幅改动
- n < 10：仅观察，不作为结论
- n < 5：完全忽略
原则 2：数据 vs 理论冲突时
- 内部数据 n ≥ 20 → 优先内部数据（除非外部 AI 双方都独立反对）
- 内部数据 n < 10 → 优先外部 AI 共识（双方一致时）
- 内部数据 n < 5 → 结论待定，标为 open question
原则 3：外部 AI 可疑概念识别
- gemini 有时会给出疑似幻觉的概念（如"Phoenix 架构"等具体命名）
- 规则：概念名只在 gemini 单家出现且无 grok 交叉 → 标为 "potential hallucination"，不采纳
- grok 引用的社区数据（"用户反馈说..."）→ 中等可信度
原则 4：反直觉发现的特别处理
- 如果 n ≥ 20 数据和常识/理论相反（如"小帖 > 大爆款"）
- 且外部 AI 共识支持
- 标注 "⚠️ 反直觉但强共识"，需要在后续跟进验证
Phase 5.5：外部 AI 案例二次验证（大版本新增）
外部 AI 有时会给出具体的"案例"（如 @morsyxbt 100→1600/月），这类"单家独有案例"需要二次验证：
验证方式（按优先级）：
- 用户工具直接验证：如果是 X 账号 → 用
twitter -c user <handle>查是否真实存在 - 反向问另一家 AI：问 gemini "你听说过 @morsyxbt 吗？" 看是否有交叉记忆
- Web search 验证：让用户手动搜或用额外 web 工具
2026-04-09 实战案例：
- Grok 独家提到
@morsyxbt100→1600/月 - Gemini 没提
- 用
twitter -c user morsyxbt验证：真实账号，10.2k followers, verified - 结论：账号真实，但"100→1600/月"的具体数字仍需 morsyxbt 本人 tweet 确认
- Tier：从 "单家可疑" 升级到 "单家可信案例"
潜在幻觉的识别：
- 如果验证失败（账号不存在/数字对不上）→ 标记为
hallucination，从 report 删除 - 如果部分验证（账号存在但数字未证）→ 标记为
partial verified，保留但降低权重
Show full SKILL.md (240 more words)Show less
Phase 6：自动生成改动清单（tiered action items）
输出结构：
## Action Items (auto-generated, tiered)
### 🔴 极高置信度必做（Strong consensus，可直接落地）
1. [action] — 依据：{数据来源 + AI 共识} — 预期效果：{具体可衡量}
- Rollback：{怎么撤销}
- Verify：{24-48h 后如何验证}
2. ...
### 🟡 高置信度建议做（Partial consensus）
1. [action] — 依据：{单侧支持} — 前提假设：{什么条件下才成立}
2. ...
### ⚪ 待验证假设（Insufficient data）
1. [hypothesis] — 需要：{什么数据才能确认} — 建议：{A/B 测试设计}
2. ...
### 🚫 不做（Conflict / 反对证据强）
1. [originally planned action] — 反对依据：{为什么不做}Phase 7：Artifact 保存
保存到 .omx/artifacts/multi-ai-research-<slug>-<YYYYMMDD-HHMMSS>.md
必须包含：
- 原始研究问题（用户的一句话）
- Phase 1 问题分解（每个任务的具体 prompt）
- Phase 3 并行任务列表（task id + 命令）
- 每个 agent 的 raw response（N 个内部 + 2 个外部）
- Phase 5 交叉验证矩阵（每个发现的置信度判定）
- Phase 6 改动清单（tiered action items）
- 用时 + 任务数（metadata）
⚠️ 命令速查（防呆，最先看这个）
grok 和 gemini 的有效子命令只有这些，其他都是错的：
# ✅ Grok —— 只有一个子命令 ask
OPENCLI_BROWSER_COMMAND_TIMEOUT=300 opencli grok ask "问题" --timeout 300 -f json
# ✅ Gemini —— 5 个子命令，最常用是 ask
opencli gemini ask "问题" --format plain # 最常用（单次问答）
opencli gemini new # 开新对话
opencli gemini deep-research "问题" # Deep Research
opencli gemini deep-research-result # 取 Deep Research 结果
opencli gemini image "画一个..." # 生图❌ 常见错误命令（运行会直接报 unknown command）：
| ❌ 错误 | ✅ 正确 | 备注 |
|---|---|---|
opencli gemini chat "..." | opencli gemini ask "..." | 没有 chat 子命令（常见错误，别习惯性用） |
opencli gemini query "..." | opencli gemini ask "..." | 没有 query |
opencli grok chat "..." | opencli grok ask "..." | grok 只有 ask |
opencli grok new | opencli grok ask "..." --new true | grok 的"新对话"是 ask 的参数 |
记忆锚点：ask 是两家唯一的"问一次"命令。不是 chat，不是 query，不是 prompt。
如果不确定，跑 opencli grok --help 或 opencli gemini --help 看完整子命令列表。
首次使用：安装 opencli（5 分钟一次性）
官方仓库：https://github.com/jackwener/opencli npm 包：
@jackwener/opencli(npmjs) 作者：jackwener License：Apache-2.0
环境要求
- Node.js ≥ 20.0.0
- Chrome 或 Chromium 浏览器
- macOS / Linux / Windows 均支持
一、安装 opencli CLI
npm install -g @jackwener/opencli验证：
opencli --version二、安装 Browser Bridge 扩展
opencli 通过一个轻量的 Chrome 扩展 + 本地 daemon 复用你浏览器已登录的 session。首次运行会自动引导安装：
opencli doctor按提示把扩展加载到 Chrome（通常是 chrome://extensions → 开发者模式 → 加载已解压的扩展，路径 doctor 会告诉你）。
三、登录目标 AI 网站
用装了扩展的那个 Chrome profile 打开并登录：
登录一次就行，session 会被 opencli 长期复用。
四、设置环境变量（必须）
# 加到 ~/.zshrc 或 ~/.bashrc
export OPENCLI_BROWSER_COMMAND_TIMEOUT=300为什么必须：opencli 的默认 browser command timeout 是 60 秒（runtime.js:25），对 grok 复杂问题不够。不设这个 grok 会报 timed out after 60s。这是血泪教训。
五、可选：安装 opencli 的 AI skills
opencli 自己提供了几个 AI skill，也可以装：
npx skills add jackwener/opencli（这些 skill 和 multi-ai-research 不冲突，是互补的。）
六、验证全链路
OPENCLI_BROWSER_COMMAND_TIMEOUT=300 opencli grok ask "请只回复：OK" --timeout 300 -f json
opencli gemini ask "请只回复：OK" --format plain两个都返回 OK 就代表全链路通了。
Extended Reference
Detailed material starting at ## Phase 0: Pre-flight Prerequisites（强制检查） has been moved to reference/extended.md to keep this skill concise. Load that reference when the task requires the moved examples, command catalogs, checklists, platform details, or implementation templates.
© majiayu000, MIT. 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 1 other file in skills/multi-ai-research of majiayu000/spellbook.
- SKILL.md
- reference/extended.md
Open the folder on GitHubat commit ed52af7
Compare with similar skills
Multi AI Research 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Multi AI Research this skillmajiayu000/spellbook | 287 | — | ~2k | Automated safety check: Pass | MIT | |
| Web ResearchJuncai22/spring-ai-agent-learning | 124 | 2 repos | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Deep Researchasgeirtj/system_prompts_leaks | 69k | — | ~3.3k | Automated safety check: Pass | CC0-1.0 | |
| Deep Research312362115/claude | 107 | — | ~6.6k | Automated safety check: Pass | MIT | |
| ULW Deep Researchcode-yeongyu/oh-my-openagent | 70k | — | ~14k | Automated safety check: Pass | Custom licence | |
| Deep ResearchXiaomiMiMo/MiMo-Code | 14k | — | ~1.2k | Automated safety check: Pass | MIT |
Similar skills
Deep Research
asgeirtj/system_prompts_leaks
A skill your agent uses when the user's prompt requires (1) researching a topic across multiple sources, comparing options or alternatives, analyzing trends or history, understanding markets or…
Deep Research
312362115/claude
深度调研技能：对任意命题进行系统性调研并输出专业研究报告. An agent skill from 312362115/claude.
ULW Deep Research
code-yeongyu/oh-my-openagent
Runs an exhaustive, team-based research session that stands up cooperating agents, debates findings and delivers a report where every claim has a citation or proof.
Deep Research
XiaomiMiMo/MiMo-Code
Runs a multi-source investigation with parallel sub-agents and built-in web tools, then writes one cited report. Meant for open-ended topics, not quick lookups.
Deep Dive
rohitg00/awesome-claude-code-toolkit
Claude-native deep research using DAG-based query planning, parallel subagent execution, and gap-driven iteration.
More from majiayu000/spellbook
All 97 skills in this repoSkill Ecosystem Doctor
majiayu000/spellbook
Audits and repairs how coding-agent Skills are owned, copied and exposed across runtimes, from canonical sources to quarantine and retirement.
AGENTS.md Scaffold
majiayu000/spellbook
Scans a repository for real evidence and proposes, or on request writes, a small stack of root and scoped AGENTS.md files with validation commands and generated-file boundaries.
Product Demo Builder
majiayu000/spellbook
Plans, produces or diagnoses evidence-backed product demo videos: script, capture plan, pacing checks and verified final media built on real product behavior.
Flowguard Task Guard
majiayu000/spellbook
Single entry point that routes long or ambiguous agent tasks, checks live state, bounds autonomous loops and leaves a resumable handoff.
npm Supply Chain Check
majiayu000/spellbook
Scans a repository, its lockfiles and node_modules for known malicious npm package versions and install-time indicators, using a read-only Python scanner.
Product Manager Toolkit
majiayu000/spellbook
Product management helpers: a RICE scoring script, an interview transcript analyzer and PRD templates for prioritizing features, synthesizing research and writing requirements.
Related
Questions about Multi AI Research
What does Multi AI Research do?
Parallel multi-AI cross-validation research workflow (大版本). An agent skill from majiayu000/spellbook. Multi AI Research is an agent skill from majiayu000/spellbook. Parallel multi-AI cross-validation research workflow (大版本).
When should I use Multi AI Research?
Multi AI Research fits situations like: user says 多 AI 调研; multi-ai research; parallel research; needs deep research that benefits from internal data + external 2026 consensus.
How do I install Multi AI Research in Claude Code?
Run `npx skills add majiayu000/spellbook --skill multi-ai-research -a claude-code`. Or copy the skill folder (skills/multi-ai-research in majiayu000/spellbook) into .claude/skills/multi-ai-research in your project. Claude Code loads it when a task matches its description.
How do I install Multi AI Research in Codex?
Run `npx skills add majiayu000/spellbook --skill multi-ai-research -a codex`. Or copy the skill folder (skills/multi-ai-research in majiayu000/spellbook) into .agents/skills/multi-ai-research in your project. Codex loads it when a task matches its description.
Can I use Multi AI Research 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 majiayu000/spellbook --skill multi-ai-research -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/multi-ai-research, .gemini/skills/multi-ai-research, .github/skills/multi-ai-research and .opencode/skills/multi-ai-research in your project.
What does Multi AI Research need to run?
Going by SKILL.md and its folder, Multi AI Research needs the command-line tools its instructions call (npm and npx). Our summary lists: Node.js.
Does Multi AI Research access the network?
SKILL.md names 2 domains. As links in the text: github.com and npmjs.com. This is read from the text; nothing was executed.
Is Multi AI Research 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 Multi AI Research use?
Multi AI Research is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Multi AI Research use?
About 2k tokens (SKILL.md is roughly 8.2k 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 Multi AI Research?
Skills that share tags, products or a category with Multi AI Research: Web Research (Juncai22/spring-ai-agent-learning, 124 stars), Deep Research (asgeirtj/system_prompts_leaks, 69k stars), Deep Research (312362115/claude, 107 stars) and ULW Deep Research (code-yeongyu/oh-my-openagent, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Multi AI Research?
majiayu000 (a GitHub user) maintains it in majiayu000/spellbook, which has 287 GitHub stars. The repository holds 97 skills in this directory. The repository was last updated on October 8, 2026.
Source: majiayu000/spellbook on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.