Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →机构调研Skill - 提供调研记录、调研热度排行、调研问答分析 via AkShare
.claude/skills/aifinlab-akshare-survey/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -17% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -19% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -29% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -35% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -38% | 0% |
| 属性 | 内容 | |:---|:---| | 名称 | akshare-survey | | 版本 | 1.1.0 | | 分类 | 机构调研 | | 状态 | ✅ 已上线 | | 维护者 | FinClaw Core Team | | 最后更新 | 2026-03-19 |
机构调研Skill，提供A股市场机构调研记录查询、调研热度排行、调研问答分析等功能。追踪机构关注的热点公司和行业。
| 用户输入 | 识别意图 | 调用函数 | |:---|:---|:---| | 最新机构调研 | survey_latest | survey_latest.py --limit 30 | | 茅台调研记录 | survey_stock | survey_stock.py --code 600519 | | 调研热度排行 | survey_rank | survey_rank.py |
| 数据类型 | 主要来源 | 备用来源 | 认证要求 | |:---|:---|:---|:---:| | 调研数据 | AkShare-交易所 | - | 无需 |
bash python scripts/survey_latest.py --limit 30
bash python scripts/survey_stock.py --code 600519
bash python scripts/survey_rank.py
| 脚本名 | 功能 | 入口点 | |:---|:---|:---:| | survey_latest.py | 最新调研 | ✅ | | survey_stock.py | 个股调研 | ✅ | | survey_rank.py | 调研排行 | ✅ |
| 情形 | 信号 | |:---|:---| | 近期被多家机构密集调研 | 机构关注度高，可能有催化剂 | | 知名机构（公募基金）调研 | 潜在配置意向 | | 调研后股价异动 | 调研内容可能有重大信息 | | 冷门股突然被调研 | 可能存在预期差 |
markdown--- 📊 **数据来源**: AkShare-交易所 ⏱️ **数据时间**: 2026-03-19 📌 **调研日期**: 2026-03-15 📌 **接待机构**: xx基金、xx证券 🔗 **原始来源**: 上市公司投资者关系活动记录 🔧 **分析工具**: FinClaw v1.0
akshare>=1.10.0
pandas>=1.3.0
pyyaml>=5.4.0| 版本 | 日期 | 变更内容 | |:---|:---:|:---| | 1.1.0 | 2026-03-19 | 符合FinClaw数据规范v1.0 | | 1.0.0 | 2026-03-13 | 初始版本 |
本Skill遵循 FinClaw 数据规范 v1.0 | 数据来源强制标注 | 禁止训练数据编造
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 24,886 | 30,389 | +22% | 1 | 1 | 0% | 3,532 | 5,700 | +61% | 0 | 0 | — |
case-02 | fail→fail | 22,203 | 16,881 | -24% | 1 | 1 | 0% | 2,998 | 3,339 | +11% | 0 | 0 | — |
case-03 | fail→fail | 21,529 | 15,237 | -29% | 1 | 1 | 0% | 2,708 | 3,373 | +25% | 0 | 0 | — |
case-04 | fail→pass | 16,575 | 6,982 | -58% | 1 | 1 | 0% | 2,188 | 1,818 | -17% | 0 | 0 | — |
case-05 | fail→pass | 11,266 | 3,494 | -69% | 1 | 1 | 0% | 1,947 | 1,576 | -19% | 0 | 0 | — |
case-06 | fail→pass | 12,695 | 4,003 | -68% | 1 | 1 | 0% | 2,052 | 1,457 | -29% | 0 | 0 | — |
case-07 | fail→pass | 22,204 | 6,614 | -70% | 1 | 1 | 0% | 3,153 | 2,062 | -35% | 0 | 0 | — |
case-08 | fail→pass | 16,463 | 3,799 | -77% | 1 | 1 | 0% | 2,618 | 1,615 | -38% | 0 | 0 | — |
case-09 | pass→pass | 22,552 | 19,026 | -16% | 1 | 1 | 0% | 2,861 | 3,398 | +19% | 0 | 0 | — |
case-10 | pass→pass | 22,257 | 16,533 | -26% | 1 | 1 | 0% | 2,591 | 3,266 | +26% | 0 | 0 | — |
case-11 | pass→pass | 17,654 | 10,484 | -41% | 1 | 1 | 0% | 2,075 | 2,582 | +24% | 0 | 0 | — |
case-12 | pass→pass | 18,588 | 30,667 | +65% | 1 | 1 | 0% | 2,670 | 4,338 | +62% | 0 | 0 | — |
case-13 | fail→pass | 21,320 | 3,645 | -83% | 1 | 1 | 0% | 2,857 | 1,483 | -48% | 0 | 0 | — |
case-14 | fail→pass | 16,994 | 2,768 | -84% | 1 | 1 | 0% | 2,616 | 1,399 | -47% | 0 | 0 | — |
case-15 | fail→pass | 10,308 | 2,987 | -71% | 1 | 1 | 0% | 1,651 | 1,508 | -9% | 0 | 0 | — |
case-16 | fail→pass | 11,056 | 2,884 | -74% | 1 | 1 | 0% | 1,901 | 1,378 | -28% | 0 | 0 | — |
case-17 | pass→pass | 8,628 | 2,683 | -69% | 1 | 1 | 0% | 1,448 | 1,350 | -7% | 0 | 0 | — |
case-18 | fail→pass | 7,429 | 4,308 | -42% | 1 | 1 | 0% | 1,311 | 1,533 | +17% | 0 | 0 | — |
case-19 | pass→pass | 8,660 | 6,155 | -29% | 1 | 1 | 0% | 1,272 | 1,935 | +52% | 0 | 0 | — |
case-20 | fail→fail | 17,538 | 23,640 | +35% | 1 | 1 | 0% | 2,167 | 4,829 | +123% | 0 | 0 | — |
case-21 | fail→fail | 15,640 | 15,464 | -1% | 1 | 1 | 0% | 2,064 | 3,438 | +67% | 0 | 0 | — |
case-22 | fail→fail | 14,429 | 14,019 | -3% | 1 | 1 | 0% | 2,400 | 2,808 | +17% | 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.
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.