Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add majiayu000/spellbook --skill multi-ai-researchgit clone --depth 1 https://github.com/majiayu000/spellbookWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/majiayu000/spellbook/multi-ai-research)<a href="https://agentmods.dev/skills/majiayu000/spellbook/multi-ai-research"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/multi-ai-research/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/majiayu000/spellbook/multi-ai-research"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/multi-ai-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 317 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00134 | $0.03681 |
| Opus 5 | $0.00067 | $0.01840 |
| Sonnet 5 | $0.00027 | $0.00736 |
| Haiku 4.5 | $0.00013 | $0.00368 |
Grade A, and why
multi-ai-research scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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]
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 337 lines · 134 tokens per session scan A 506476bf538d
multi-ai-research is a skill published in the GitHub repository majiayu000/spellbook (278 stars, last pushed today), licensed MIT. It adds 134 tokens to every session and 3,681 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
pneuma-session
Instructions for renaming an active Pneuma session and replacing its default preview with a useful title and summary. A Pneuma session is one work area inside a larger project.
session-handoff
Use when the user wants to hand off, transfer, pause, or continue the current session in a new session or with another agent — asks for a "session handoff", a "prompt para a próxima sessão", to "continuar de onde paramos", or invokes /session-handoff; also when context is running low and in-flight work must survive a…
aenv
Use when the user wants to set up, switch between, or manage aenv namespaces — named bundles of CLAUDE.md, skills, MCP entries, and other AI-coding-harness config — in a project OR globally across $HOME. Triggers include aenv … mentioned directly, "switch namespace/profile", "activate/deactivate", "create/snapshot a…
cao-session-management
Interact with CAO (CLI Agent Orchestrator) — launch multi-agent sessions, check status, send follow-up instructions, unblock stuck terminals, or shut down sessions. Use when working with CAO sessions in any capacity.
mulmoterminal-keys
Bind keyboard shortcuts and fix keyboard/clipboard behaviour in MulmoTerminal. Writes keymap, which Settings cannot set at all — its Keyboard shortcuts section is read-only, listing every action bound or not plus a send row. Explains copyOnSelect, questionPaneEnabled and terminalSubmit, which have their own Settings…
tokf-discover
Find missed token savings by scanning AI coding session files for commands that ran without tokf filtering.