Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →小红书复合内容运营技能。组合搜索、详情、发布、互动等能力完成运营工作流。 当用户要求竞品分析、热点追踪、内容创作、互动管理等复合任务时触发。
.claude/skills/kiakun-collab-xhs-content-ops/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 41% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -10% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 18% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -25% | 0% |
你是"小红书内容运营助手"。帮助用户完成需要多步骤组合的运营任务。
按优先级判断：
目标：搜索竞品笔记 → 获取详情 → 整理分析报告。
步骤：
bashpython scripts/cli.py search-feeds \ --keyword "目标关键词" --sort-by 最多点赞
bashpython scripts/cli.py get-feed-detail \ --feed-id FEED_ID --xsec-token XSEC_TOKEN
输出格式：
使用 markdown 表格对比各笔记的关键指标，并总结共性特征和差异化策略。
目标：搜索热门关键词 → 分析趋势 → 提供选题建议。
步骤：
bash# 按最新排序，观察近期热度 python scripts/cli.py search-feeds \ --keyword "关键词" --sort-by 最新 --publish-time 一周内 # 按最多点赞排序，找爆款 python scripts/cli.py search-feeds \ --keyword "关键词" --sort-by 最多点赞
目标：研究话题 → 辅助生成草稿 → 用户确认 → 发布。
步骤：
bashpython scripts/cli.py search-feeds \ --keyword "主题关键词" --sort-by 最多点赞
AskUserQuestion 让用户确认最终内容。bashpython scripts/cli.py publish \ --title-file /tmp/xhs_title.txt \ --content-file /tmp/xhs_content.txt \ --images "/abs/path/pic1.jpg" "/abs/path/pic2.jpg" \ --tags "标签1" "标签2"
目标：浏览目标笔记 → 有策略地评论/点赞/收藏。
步骤：
bashpython scripts/cli.py search-feeds \ --keyword "目标关键词" --sort-by 最新
bashpython scripts/cli.py get-feed-detail \ --feed-id FEED_ID --xsec-token XSEC_TOKEN
bashpython scripts/cli.py post-comment \ --feed-id FEED_ID \ --xsec-token XSEC_TOKEN \ --content "评论内容"
bashpython scripts/cli.py like-feed \ --feed-id FEED_ID --xsec-token XSEC_TOKEN python scripts/cli.py favorite-feed \ --feed-id FEED_ID --xsec-token XSEC_TOKEN
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 20,668 | 2,218 | -89% | 1 | 1 | 0% | 3,801 | 1,755 | -54% | 0 | 0 | — |
case-02 | fail→fail | 15,750 | 2,921 | -81% | 1 | 1 | 0% | 2,459 | 1,937 | -21% | 0 | 0 | — |
case-03 | fail→fail | 13,411 | 2,082 | -84% | 1 | 1 | 0% | 2,162 | 1,804 | -17% | 0 | 0 | — |
case-04 | pass→pass | 10,358 | 7,826 | -24% | 1 | 1 | 0% | 2,172 | 2,963 | +36% | 0 | 0 | — |
case-05 | pass→pass | 11,777 | 12,320 | +5% | 1 | 1 | 0% | 2,905 | 4,133 | +42% | 0 | 0 | — |
case-06 | pass→pass | 11,669 | 11,294 | -3% | 1 | 1 | 0% | 1,851 | 3,137 | +69% | 0 | 0 | — |
case-07 | fail→pass | 7,283 | 3,046 | -58% | 1 | 1 | 0% | 1,392 | 1,964 | +41% | 0 | 0 | — |
case-08 | fail→pass | 12,797 | 4,374 | -66% | 1 | 1 | 0% | 2,180 | 2,123 | -3% | 0 | 0 | — |
case-09 | pass→fail | 11,859 | 3,037 | -74% | 1 | 1 | 0% | 2,272 | 1,966 | -13% | 0 | 0 | — |
case-10 | fail→pass | 11,810 | 2,886 | -76% | 1 | 1 | 0% | 2,129 | 1,909 | -10% | 0 | 0 | — |
case-11 | fail→pass | 12,422 | 4,466 | -64% | 1 | 1 | 0% | 1,899 | 2,250 | +18% | 0 | 0 | — |
case-12 | fail→pass | 12,698 | 2,304 | -82% | 1 | 1 | 0% | 2,336 | 1,761 | -25% | 0 | 0 | — |
case-13 | pass→pass | 16,429 | 8,160 | -50% | 1 | 1 | 0% | 2,444 | 2,910 | +19% | 0 | 0 | — |
case-14 | fail→pass | 12,948 | 4,119 | -68% | 1 | 1 | 0% | 2,544 | 2,208 | -13% | 0 | 0 | — |
case-15 | fail→pass | 15,730 | 5,973 | -62% | 1 | 1 | 0% | 2,373 | 2,335 | -2% | 0 | 0 | — |
case-16 | fail→pass | 11,684 | 4,697 | -60% | 1 | 1 | 0% | 2,103 | 2,109 | +0% | 0 | 0 | — |
case-17 | fail→pass | 14,183 | 6,343 | -55% | 1 | 1 | 0% | 2,583 | 2,460 | -5% | 0 | 0 | — |
case-18 | fail→pass | 6,324 | 1,972 | -69% | 1 | 1 | 0% | 1,340 | 1,780 | +33% | 0 | 0 | — |
case-19 | fail→fail | 14,826 | 3,027 | -80% | 1 | 1 | 0% | 2,675 | 1,954 | -27% | 0 | 0 | — |
case-20 | fail→pass | 10,946 | 3,024 | -72% | 1 | 1 | 0% | 1,862 | 1,877 | +1% | 0 | 0 | — |
case-21 | pass→pass | 16,360 | 11,431 | -30% | 1 | 1 | 0% | 2,654 | 3,349 | +26% | 0 | 0 | — |
case-22 | pass→pass | 10,596 | 3,523 | -67% | 1 | 1 | 0% | 2,031 | 1,985 | -2% | 0 | 0 | — |
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. 22 cases were attempted. The headline lift of +45 percentage points is the difference between those two pass rates over the 22 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.