提示词
提示词工程与模板
quant-factor-screener
Geeksfino
使用正式因子模型进行系统化多因子A股筛选，识别具有有利因子暴露的个股。当用户询问因子投资、多因子筛选、价值/动量/质量因子分析、因子打分、因子择时、Smart Beta策略、量化选股或基于学术因子的系统化选股时使用此技能。
suitability-report-generator
Geeksfino
生成机构级投资适当性报告，包括投资理由、风险披露和客户适当性评估。当用户要求记录投资决策、创建合规报告、生成风险披露文件、准备面向客户的投资理由说明、撰写适当性评估报告，或为投资建议或组合出具信义义务文档时使用此技能。
insider-trading-analyzer
Geeksfino
分析A股市场董监高及重要股东增减持行为，识别具有显著管理层信心信号的公司。当用户询问董监高增持、大股东买入、内部人交易分析、管理层增持信号、股东增减持动态时使用此技能。
topic-generator
zephyrwang6
AI选题生成工具。从采集的热点中筛选TOP10，生成完整选题方案。当用户说"生成选题"、"筛选热点"、"哪些值得写"时触发。输出包含：事件描述、核心角度、标题、写作方式。
topic-agent
zephyrwang6
选题系统主控Agent。协调热点采集、选题生成、选题审核三个环节，支持迭代直到产出合格选题。触发方式：(1)"开始今日选题"启动完整流程 (2)"今日AI热点"只采集热点不生成选题 (3)"我有一个选题"进入单个选题分析 (4)"推荐一些好的选题"直接输出推荐。输出保存到Obsidian选题库。
total-recall
gavdalf
"The only memory skill that watches on its own. No database. No vectors. No manual saves. Just an LLM observer that compresses your conversations into prioritised notes, consolidates when they grow, and recovers anything missed. Five layers of redundancy, zero maintenance. ~$0.00/month (using free-tier models). While other memory skills ask you to remember to remember, this one just pays attention."
agenta-langchain-integration
vamseeachanta
'Sub-skill of agenta: Langchain Integration.'
prompt-engineering-4-system-prompt-design
vamseeachanta
'Sub-skill of prompt-engineering: 4. System Prompt Design.'
prompt-engineering-example-1-multi-stage-document-processor
vamseeachanta
'Sub-skill of prompt-engineering: Example 1: Multi-Stage Document Processor
ai-prompting-available-skills
vamseeachanta
'Sub-skill of ai-prompting: Available Skills.'
prompt-engineering-constraints
vamseeachanta
'Sub-skill of prompt-engineering: Constraints.'
agenta-2-ab-testing-prompts
vamseeachanta
'Sub-skill of agenta: 2. A/B Testing Prompts.'
prompt-engineering-background
vamseeachanta
'Sub-skill of prompt-engineering: Background.'
prompt-engineering-1-zero-shot-prompting
vamseeachanta
'Sub-skill of prompt-engineering: 1. Zero-Shot Prompting (+1).'
agenta-1-prompt-versioning-and-management
vamseeachanta
'Sub-skill of agenta: 1. Prompt Versioning and Management.'
agent-usage-optimizer-baseline-route-defaults
vamseeachanta
'Sub-skill of agent-usage-optimizer: Baseline Route Mapping (quota-agnostic
agenta-3-evaluation-metrics-and-testing
vamseeachanta
'Sub-skill of agenta: 3. Evaluation Metrics and Testing.'
template-validator
armanzeroeight
Validates CloudFormation templates for syntax, security, and best practices. Use when validating CloudFormation templates, checking for security issues, or ensuring compliance with best practices.
langchain-3-conversation-memory
vamseeachanta
'Sub-skill of langchain: 3. Conversation Memory.'
ai-prompting-choose-langchain-when
vamseeachanta
'Sub-skill of ai-prompting: Choose langchain when: (+4).'
dspy-dspy-philosophy
vamseeachanta
'Sub-skill of dspy: DSPy Philosophy.'
prompt-engineering-3-provide-context
vamseeachanta
'Sub-skill of prompt-engineering: 3. Provide Context (+1).'
lsp-manager
bahayonghang
Automatically detect programming languages, configure Language Server Protocol (LSP) servers, and troubleshoot LSP integration issues for Claude Code. Use when users request to set up LSP, configure code intelligence, add language support, troubleshoot LSP errors, or when working with projects that need real-time code diagnostics and navigation.
prompt-engineering
vamseeachanta
Comprehensive prompting techniques including chain-of-thought, few-shot, zero-shot, system prompts, persona design, and evaluation patterns