Ready to supercharge your AI agents?

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

千帆深度研究 Agent — measured AI agent skill | DecimalAI

openakita/skills@baidu-deep-research

NewSkillScoreMaintained

Qianfan Deep Research Agent for complex research tasks. Combines information retrieval, multi-source analysis, content synthesis, and report generation. Use when user needs in-depth research, analysis reports, or comprehensive investigation on complex topics.

researchby openakita

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Research pack

decimalai skills pull openakita-skills-baidu-deep-research

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/openakita-skills-baidu-deep-research/SKILL.md

Raw file: /s/openakita-skills-baidu-deep-research/SKILL.md ↗ · machine-readable summary at /s/openakita-skills-baidu-deep-research.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 2h ago

—-43% tokens0% turns86% of whole cases pass with skill (19/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-04	✗→✓	▲ Improved	-43%	0%
case-05	✗→✓	▲ Improved	-58%	0%
case-19	✗→✓	▲ Improved	-67%	0%
case-06	✗→✓	▲ Improved	-35%	0%
case-08	✗→✓	▲ Improved	-60%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

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

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

openakita / openakita

skills/baidu-deep-research/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1Bundled 1 file · scripts

Skill contents

scripts/

SKILL.md

千帆深度研究 Agent

百度千帆官方构建的复杂智能体应用范例，深度融合信息检索、多源分析、内容综合、报告生成。DeepResearch 排行榜第一。

配置

export BAIDU_API_KEY="your_key"

功能

信息检索：全网多源信息采集
多源分析：交叉验证与深度分析
内容综合：结构化内容整合
报告生成：专业研究报告输出

预置脚本

scripts/deep_research.py

深度研究报告生成（百度千帆 AppBuilder），需设置 APPBUILDER_TOKEN。

bash
python3 scripts/deep_research.py research "人工智能在医疗领域的应用"
python3 scripts/deep_research.py report "大模型技术趋势分析"

Want to see if openakita/skills@baidu-deep-research would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.