Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →ESG数据Skill - 提供A股ESG评级、碳中和数据、可持续发展分析 via AkShare
.claude/skills/aifinlab-akshare-esg/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | 51% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 90% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 113% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 45% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 27% | 0% |
| 属性 | 内容 | |:---|:---| | 名称 | akshare-esg | | 版本 | 1.1.0 | | 分类 | ESG数据 | | 状态 | ✅ 已上线 | | 维护者 | FinClaw Core Team | | 最后更新 | 2026-03-19 |
ESG数据Skill，提供A股上市公司ESG评级、碳中和相关数据、可持续发展分析。覆盖环境(Environmental)、社会(Social)、治理(Governance)三个维度。
| 用户输入 | 识别意图 | 调用函数 | |:---|:---|:---| | 茅台ESG评级 | esg_rating | esg_rating.py --code 600519 | | ESG排名 | esg_rank | esg_rank.py | | 碳中和概念股 | esg_carbon | esg_carbon.py | | ESG行业排行 | esg_industry | esg_rank.py --by industry |
| 数据类型 | 主要来源 | 备用来源 | 认证要求 | |:---|:---|:---|:---:| | ESG评级 | AkShare-华证/商道融绿 | - | 无需 | | 碳中和数据 | AkShare | - | 无需 | | 可持续发展报告 | 上市公司公告 | - | 无需 |
| 评级机构 | 评级范围 | 最高评级 | |:---|:---|:---:| | 华证指数 | A股全市场 | AAA | | 商道融绿 | A股重点公司 | A+ | | 盟浪 | A股全市场 | AAA | | 润灵环球 | A股重点公司 | AAA |
| 等级 | 含义 | 投资参考 | |:---:|:---|:---| | AAA | 卓越 | 优先投资 | | AA | 优秀 | 积极投资 | | A | 良好 | 正常投资 | | BBB | 中等 | 谨慎投资 | | BB | 一般 | 需关注 | | B | 较弱 | 规避风险 | | CCC | 弱 | 高风险 |
bash python scripts/esg_rating.py --code 600519 python scripts/esg_rating.py --code 000001
bash python scripts/esg_rank.py python scripts/esg_rank.py --industry 银行
bash python scripts/esg_carbon.py python scripts/esg_carbon.py --sector 光伏
| 脚本名 | 功能 | 入口点 | |:---|:---|:---:| | esg_rating.py | ESG评级查询 | ✅ | | esg_rank.py | ESG行业排行 | ✅ | | esg_carbon.py | 碳中和股票 | ✅ |
| 维度 | 关注点 | 投资风险 | |:---|:---|:---| | 环境(E) | 碳排放、污染、资源利用 | 环保处罚、碳税 | | 社会(S) | 员工权益、供应链、社区 | 舆情风险、罢工 | | 治理(G) | 董事会、信息披露、反腐败 | 治理丑闻、财务造假 |
| 板块 | 代表公司 | 投资逻辑 | |:---|:---|:---| | 光伏 | 隆基绿能、通威股份 | 清洁能源替代 | | 锂电 | 宁德时代、比亚迪 | 新能源车普及 | | 风电 | 金风科技、明阳智能 | 可再生能源 | | 储能 | 派能科技、阳光电源 | 能源存储需求 | | 氢能 | 亿华通、美锦能源 | 未来清洁能源 | | 碳交易 | 岳阳林纸、福建金森 | 碳汇资产 |
markdown--- 📊 **数据来源**: AkShare-华证指数/商道融绿 ⏱️ **数据时间**: 2026-03-19 📌 **评级机构**: 华证指数 📌 **评级周期**: 2025Q4 🔗 **原始来源**: 华证ESG评级 🔧 **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，新增ESG评级体系 | | 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-09 | fail→pass | 9,552 | 4,923 | -48% | 1 | 1 | 0% | 1,497 | 2,257 | +51% | 0 | 0 | — |
case-01 | fail→pass | 20,185 | 25,780 | +28% | 1 | 1 | 0% | 3,154 | 5,988 | +90% | 0 | 0 | — |
case-02 | fail→pass | 19,221 | 27,095 | +41% | 1 | 1 | 0% | 3,115 | 6,626 | +113% | 0 | 0 | — |
case-03 | fail→pass | 18,232 | 15,404 | -16% | 1 | 1 | 0% | 3,036 | 4,412 | +45% | 0 | 0 | — |
case-04 | fail→pass | 21,055 | 3,858 | -82% | 1 | 1 | 0% | 1,671 | 2,118 | +27% | 0 | 0 | — |
case-05 | fail→pass | 17,375 | 5,336 | -69% | 1 | 1 | 0% | 2,668 | 2,410 | -10% | 0 | 0 | — |
case-06 | fail→pass | 14,337 | 5,407 | -62% | 1 | 1 | 0% | 2,159 | 2,414 | +12% | 0 | 0 | — |
case-07 | pass→pass | 20,314 | 11,123 | -45% | 1 | 1 | 0% | 2,571 | 3,341 | +30% | 0 | 0 | — |
case-08 | fail→pass | 16,587 | 6,295 | -62% | 1 | 1 | 0% | 2,066 | 2,634 | +27% | 0 | 0 | — |
case-10 | fail→pass | 16,912 | 4,606 | -73% | 1 | 1 | 0% | 2,794 | 2,462 | -12% | 0 | 0 | — |
case-11 | pass→pass | 7,637 | 5,489 | -28% | 1 | 1 | 0% | 1,205 | 2,459 | +104% | 0 | 0 | — |
case-12 | pass→pass | 8,998 | 6,810 | -24% | 1 | 1 | 0% | 1,223 | 2,599 | +113% | 0 | 0 | — |
case-13 | pass→pass | 8,440 | 7,905 | -6% | 1 | 1 | 0% | 1,220 | 2,747 | +125% | 0 | 0 | — |
case-14 | pass→pass | 8,521 | 8,113 | -5% | 1 | 1 | 0% | 912 | 2,632 | +189% | 0 | 0 | — |
case-15 | pass→pass | 10,273 | 6,027 | -41% | 1 | 1 | 0% | 1,322 | 2,526 | +91% | 0 | 0 | — |
case-16 | pass→pass | 19,266 | 15,506 | -20% | 1 | 1 | 0% | 2,888 | 3,535 | +22% | 0 | 0 | — |
case-17 | pass→pass | 19,396 | 13,414 | -31% | 1 | 1 | 0% | 2,804 | 3,601 | +28% | 0 | 0 | — |
case-18 | pass→pass | 6,072 | 2,002 | -67% | 1 | 1 | 0% | 750 | 1,867 | +149% | 0 | 0 | — |
case-19 | fail→pass | 16,916 | 4,163 | -75% | 1 | 1 | 0% | 2,637 | 2,275 | -14% | 0 | 0 | — |
case-20 | fail→pass | 18,420 | 15,868 | -14% | 1 | 1 | 0% | 2,367 | 3,554 | +50% | 0 | 0 | — |
case-21 | fail→fail | 22,331 | 15,829 | -29% | 1 | 1 | 0% | 3,230 | 4,241 | +31% | 0 | 0 | — |
case-22 | pass→pass | 12,012 | 10,413 | -13% | 1 | 1 | 0% | 1,931 | 3,202 | +66% | 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 +50 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.