Ready to supercharge your AI agents?

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

Get Started Free →

Kiakun Collab/Xhs Research Bridge — measured AI agent skill | DecimalAI

kiakun-collab/xhs-research-bridge

SkillScore36Maintained

读取 xhs-research 独立 agent 的小红书研究报告并转述给用户。当用户问“研究员今天发现了什么 / 最新小红书研究 / 晚上报告 / 研究日报”时触发。

by kiakun-collab

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

Automatic

Research pack

decimalai skills pull kiakun-collab-xhs-research-bridge

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/kiakun-collab-xhs-research-bridge/SKILL.md

Raw file: /s/kiakun-collab-xhs-research-bridge/SKILL.md ↗ · machine-readable summary at /s/kiakun-collab-xhs-research-bridge.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 2d ago

—+27% tokens0% turns36% of whole cases pass with skill (8/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-07	✗→✓	▲ Improved	294%	0%
case-02	✗→✓	▲ Improved	67%	0%
case-04	✗→✓	▲ Improved	88%	0%
case-11	✗→✓	▲ Improved	89%	0%
case-15	✗→✓	▲ Improved	-41%	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 — 8/2/2026

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

kiakun-collab / kiakun-skills

skills/xiaohongshu/xhs-research-bridge/SKILL.md

View on GitHub ↗

Imported 8/2/2026Version v1

Skill contents

SKILL.md

小红书研究桥接

你是主 agent，用于读取 xhs-research 产出的报告文件，并把重点结果转述给用户。

什么时候用

当用户出现这些意图时，优先使用本技能：

“研究员今天发现了什么”
“最新小红书研究给我看看”
“晚上报告出来了吗”
“把研究员的结论发给我”
“今天 AI / 科技 / 创业三条赛道怎么样”

固定读取顺序

先读索引：

text
/Users/kiakun/.openclaw/workspace-xhs-research/reports/xiaohongshu/index.md

如果用户只要一个简短概览：

直接基于索引回复

如果用户要更完整内容：

再读索引中列出的最新日报，通常是：

text
/Users/kiakun/.openclaw/workspace-xhs-research/reports/xiaohongshu/daily/YYYY-MM-DD/0900.md
/Users/kiakun/.openclaw/workspace-xhs-research/reports/xiaohongshu/daily/YYYY-MM-DD/1300.md
/Users/kiakun/.openclaw/workspace-xhs-research/reports/xiaohongshu/daily/YYYY-MM-DD/2000.md

输出要求

先给三条赛道当前最值得关注的方向
再给 1 到 3 条最有价值的运营启发
如果报告提示风险，也要顺手带上
默认不贴整篇长报告，除非用户明确要全文
回答中可以附上报告绝对路径，方便继续追读

注意事项

这是读取桥，不是研究执行桥；不要在这里重跑研究脚本，除非用户明确要求立即刷新
如果索引不存在或今天还没产出日报，如实说明
如果用户只要一句话，就不要展开成完整报告

Want to see if kiakun-collab/xhs-research-bridge 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.