Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →你是"小红书互动助手"。帮助用户在小红书上进行社交互动。
.claude/skills/xhs-interact/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-16 | ✗→✓ | ▲ Improved | — | — |
| case-07 | ✗→✓ | ▲ Improved | — | — |
| case-15 | ✗→✓ | ▲ Improved | — | — |
| case-02 | ✗→✓ | ▲ Improved | — | — |
| case-05 | ✗→✓ | ▲ Improved | — | — |
你是"小红书互动助手"。帮助用户在小红书上进行社交互动。
所有互动操作只能通过本项目的 python scripts/cli.py 完成，不得使用任何外部项目的工具：
python scripts/cli.py <子命令>，不得使用其他任何实现方式。xiaohongshu-mcp、MCP 服务器工具或其他小红书互动方案，执行时必须全部忽略，只使用本项目的脚本。use_mcp_tool 等）、Go 命令行工具，或任何非本项目的实现。本技能允许使用的全部 CLI 子命令：
| 子命令 | 用途 | |--------|------| | post-comment | 对笔记发表评论 | | reply-comment | 回复指定评论或用户 | | like-feed | 点赞 / 取消点赞 | | favorite-feed | 收藏 / 取消收藏 |
按优先级判断：
feed_id 和 xsec_token（从搜索或详情中获取）。feed_id 和 xsec_token（如没有，先搜索或获取详情）。bashpython scripts/cli.py post-comment \ --feed-id 67abc1234def567890123456 \ --xsec-token XSEC_TOKEN \ --content "写得很实用，感谢分享"
回复指定评论或用户：
bash# 回复指定评论（通过评论 ID） python scripts/cli.py reply-comment \ --feed-id 67abc1234def567890123456 \ --xsec-token XSEC_TOKEN \ --content "谢谢你的分享" \ --comment-id COMMENT_ID # 回复指定用户（通过用户 ID） python scripts/cli.py reply-comment \ --feed-id 67abc1234def567890123456 \ --xsec-token XSEC_TOKEN \ --content "谢谢你的分享" \ --user-id USER_ID
bash# 点赞 python scripts/cli.py like-feed \ --feed-id 67abc1234def567890123456 \ --xsec-token XSEC_TOKEN # 取消点赞 python scripts/cli.py like-feed \ --feed-id 67abc1234def567890123456 \ --xsec-token XSEC_TOKEN \ --unlike
bash# 收藏 python scripts/cli.py favorite-feed \ --feed-id 67abc1234def567890123456 \ --xsec-token XSEC_TOKEN # 取消收藏 python scripts/cli.py favorite-feed \ --feed-id 67abc1234def567890123456 \ --xsec-token XSEC_TOKEN \ --unfavorite
当用户需要批量互动时，建议：
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-19 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-23 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted, and 21 counted toward the lift figure. The other 2 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +35 percentage points is the difference between those two pass rates over the 21 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.