Ready to supercharge your AI agents?

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

Get Started Free →

Nexu IO/Card Xiaohongshu — measured AI agent skill | DecimalAI

nexu-io/card-xiaohongshu

NewSkillScoreMaintained

小红书风格知识卡片, 多张联排可滑动浏览

design-mediaby nexu-io

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

Automatic

Marketing & Content pack

decimalai skills pull nexu-io-card-xiaohongshu

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/nexu-io-card-xiaohongshu/SKILL.md

Raw file: /s/nexu-io-card-xiaohongshu/SKILL.md ↗ · machine-readable summary at /s/nexu-io-card-xiaohongshu.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

Yes — +5% lift · at higher cost+96% tokens0% turns23% of whole cases pass with skill (5/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-07	✗→✓	▲ Improved	124%	0%
case-08	✗→✓	▲ Improved	140%	0%
case-16	✗→✓	▲ Improved	40%	0%
case-02	✓→✗	▼ Worse	134%	0%
case-03	✓→✗	▼ Worse	137%	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

nexu-io / html-anything

next/src/lib/templates/skills/card-xiaohongshu/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1

Skill contents

SKILL.md

【模板: 小红书图文卡片】

输出 N 张连续卡片, 每张 w-[1080px] h-[1440px], 用 flex 纵向排列方便整体截图也方便单张截图。N 由【用户内容】信息量决定: 短内容 3-6 张起步, 长内容应更多 (小红书平台单帖最多 18 图, 通常 9 张以内最佳); 一张卡只承载一个核心观点。
第一张是封面: 巨大的标题 + 1 行副标题 + 一个吸引人的标签 (类似 "干货预警" / "建议收藏")。
中间几张展开正文, 每张一个核心观点, 配 emoji + 短句 + 1-2 个例子。
最后一张是总结 + 行动号召 (关注 / 收藏 / 评论)。
配色: 选择柔和的莫兰迪色或粉色系; 元素圆润, 大量留白。
字号大、行距宽、对比强（小红书在手机上看, 小字根本看不清）。
每张卡片右下角小水印 (作者名 / 日期)。

Want to see if nexu-io/card-xiaohongshu 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.