Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Multi-AI Research（并行多 AI 交叉验证） · majiayu000 | DecimalAI

researchby majiayu000

Multi-AI Research（并行多 AI 交叉验证）

majiayu000/multi-ai-research

Source majiayu000/spellbook ↗License MIT

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.

SkillScore80Maintained

Automatic

Research pack

Last verified 8/24/2026

What it changes

Passed 18 of 22 test cases with the skill, and 6 of 22 without it.

Without skill28%

With skill80%

Checks it passed that the model alone missed

The command uses opencli gemini ask.
The report is saved into .omx/artifacts/.
The finding is assigned to the Strong Consensus tier.

and 11 more in the full report

13 fixed7 passed either way5 still failing0 broke

Pass-rate lift: +52 pp
Tokens: +175%
Agent turns: 0%
Response time: -53%

Model gemini-3.6-flashMeasured 8/24/2026v120 of 25 cases passed with skill · 22 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/majiayu000-multi-ai-research/SKILL.md https://app.decimal.ai/s/majiayu000-multi-ai-research/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add majiayu000-multi-ai-research, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/majiayu000-multi-ai-research/ and pins it in .decimal/skills.lock

decimalai skills add majiayu000-multi-ai-research

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/majiayu000-multi-ai-research/SKILL.md https://app.decimal.ai/s/majiayu000-multi-ai-research/SKILL.md

Raw file: /s/majiayu000-multi-ai-research/SKILL.md ↗ · machine-readable summary at /s/majiayu000-multi-ai-research.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 13

Prompt

Our Grok queries keep timing out after 60 seconds when running complex browser-based questions via opencli. What environment variable and value must be set to extend browser command timeout to 300 seconds?

What was checked, without and with the skill
Checked	Without skill	With skill
The solution specifies setting OPENCLI_BROWSER_COMMAND_TIMEOUT to 300.	Missed	Passed

case-09 · gemini-3.6-flash · 8/24/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md331 linessingle file

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）

Track record

Benchmark

18 / 22

test cases passed, vs 6 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

majiayu000 / spellbook

skills/multi-ai-research/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Multi-AI Research（并行多 AI 交叉验证）

何时触发

✅ 适合

❌ 不适合

工作流（7 Phase）

Phase 1：问题分解（Claude 自动 + 用户可覆盖）

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills