policy-qa
Automated assistant for fund compliance, regulatory disclosure, and policy QA.
Install
mkdir -p .claude/skills/policy-qa && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16163" && unzip -o skill.zip -d .claude/skills/policy-qa && rm skill.zipInstalls to .claude/skills/policy-qa
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
面向基金合规与信息披露领域的制度问答任务Skill,围绕「制度问答助手」场景提供信息抽取、结构化分析与结果输出。Key capabilities
- →Identify sensitive or non-compliant expressions
- →Provide compliance rewriting suggestions
- →Suggest risk levels for identified issues
- →Organize question lists and standard answers based on input
- →Provide citation sources and consistency explanations
How it works
The skill processes fund-related documents to extract information, identify compliance issues, and structure Q&A tasks. It provides suggestions for rewriting and risk levels.
Inputs & outputs
When to use policy-qa
- →Analyze fund announcements for compliance
- →Extract data from prospectuses
- →Check consistency of disclosure documents
- →Flag sensitive expressions in marketing content
About this skill
制度问答助手 Skill
数据来源
1. 输入类型
- 基金公告/定期报告/招募说明书/产品说明材料
- 净值与收益时间序列、持仓与资产配置披露
- 销售/服务记录、客户反馈与问答素材(如适用)
- 合规口径与品牌内容规范(如适用)
2. 主要数据要素
- 监管法规条款与公司内控口径
- 披露模板、历史公告与对外口径
- 营销文案/素材与合规审查记录
- 披露时点、频率与留痕要求
- 敏感词与禁止性表述清单
3. 质量要求
- 输入信息尽量完整,包含时间区间、基金代码与核心指标
- 若来自 OCR/截图,请尽量校对错字与断行
- 对于未披露的数据需明确标注“缺失/待补充”
核心能力
- 识别敏感/违规表述与披露缺口
- 给出合规改写建议与风险等级提示
- 基于输入资料组织问题清单与标准回答
- 提供引用来源与口径一致性说明
输出结构
1. 基础字段
- skill
- domain
- scene
- input_summary
- key_findings
- data_quality
- limitations
2. 场景扩展模块(按需输出)
- compliance
- flags
- revision_suggestions
- risk_level
- qa
- questions
- answers
- citations
使用示例
1. 安装依赖
pip install -r requirements.txt
2. 运行脚本
python scripts/main.py --input sample.txt --output-json result.json --output-md report.md
3. 输出示例
{
"skill": "制度问答助手",
"domain": "合规与信息披露",
"scene": "制度问答",
"input_summary": {
"fund_code": "000000",
"fund_name": "示例基金",
"period": "2024Q4",
"data_coverage": "净值/持仓/披露/市场"
},
"key_findings": [
"关键结论1",
"关键结论2"
],
"data_quality": {
"has_text": true,
"text_length": 1200
},
"limitations": [
"仅基于输入信息形成初步判断"
]
}
注意事项与限制
- 仅对输入文本进行结构化与初步判断,不替代人工投研或合规结论
- 若缺少关键数据(持仓、基准、时间区间),结果需明确提示不完整
- 输出建议应结合实际业务口径与监管要求复核
适用场景
- 业务条线: 合规与信息披露
- 场景/能力: 制度问答
- 典型用户: 研究员、产品经理、渠道与客服、合规审查或内容运营人员
License
- 代码部分遵循 MIT License
- 数据来源与披露口径需遵循对应数据供应商与监管要求
When not to use it
- →When the task requires manual investment research
- →When the task requires compliance conclusions without review
Limitations
- →The skill is for fund compliance and information disclosure.
- →The skill is for Q&A tasks related to institutional policies.
How it compares
This skill automates the analysis of fund documents for compliance and information extraction, providing structured outputs and suggestions, which is more efficient than manual review processes.
Compared to similar skills
policy-qa side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| policy-qa (this skill) | 0 | 5mo | Review | Intermediate |
| market-research-reports | 38 | 7mo | Review | Advanced |
| executing-marketing-campaigns | 11 | 8mo | Review | Intermediate |
| competitive-intelligence | 15 | 6mo | No flags | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by aifinlab
View all by aifinlab →You might also like
market-research-reports
davila7
Generate comprehensive market research reports (50+ pages) in the style of top consulting firms (McKinsey, BCG, Gartner). Features professional LaTeX formatting, extensive visual generation with scientific-schematics and generate-image, deep integration with research-lookup for data gathering, and multi-framework strategic analysis including Porter's Five Forces, PESTLE, SWOT, TAM/SAM/SOM, and BCG Matrix.
executing-marketing-campaigns
davila7
Plans, creates, and optimizes marketing campaigns including content strategy, social media, email, and analytics. Helps develop go-to-market strategies, campaign messaging, and performance measurement.
competitive-intelligence
anthropics
Research your competitors and build an interactive battlecard. Outputs an HTML artifact with clickable competitor cards and a comparison matrix. Trigger with "competitive intel", "research competitors", "how do we compare to [competitor]", "battlecard for [competitor]", or "what's new with [competitor]".
employment-contract-templates
wshobson
Create employment contracts, offer letters, and HR policy documents following legal best practices. Use when drafting employment agreements, creating HR policies, or standardizing employment documentation.
clinical-decision-support
K-Dense-AI
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
marketing-ops
alirezarezvani
Central router for the marketing skill ecosystem. Use when unsure which marketing skill to use, when orchestrating a multi-skill campaign, or when coordinating across content, SEO, CRO, channels, and analytics. Also use when the user mentions 'marketing help,' 'campaign plan,' 'what should I do next,' 'marketing priorities,' or 'coordinate marketing.'