AML.T0056: Extract LLM System Prompt
generic skill
Explore
1,488 skills indexed with the new KISS metadata standard.
generic skill
- Compare outputs objectively based on quality, accuracy, and adherence to requirements
{% hint style="info" %}
Detects and corrects Korean AI writing patterns to transform text into natural human writing. Based on scientific linguistic research (KatFishNet paper with 94.88% AUC accuracy). Analyzes 19 patterns including comma overuse, spacing rigidity, POS diversity, AI vocabulary overuse, and structural monotony. Use when humanizing Korean text from ChatGPT/Claude/Gemini or removing AI traces from Korean LLM output.
Detects and corrects Korean AI writing patterns to transform text into natural human writing. Based on scientific linguistic research (KatFishNet paper with 94.88% AUC accuracy). Analyzes 19 patterns including comma overuse, spacing rigidity, POS diversity, AI vocabulary overuse, and structural monotony. Use when humanizing Korean text from ChatGPT/Claude/Gemini or removing AI traces from Korean LLM output.
Detects and corrects Korean AI writing patterns to transform text into natural human writing. Based on scientific linguistic research (KatFishNet paper with 94.88% AUC accuracy). Analyzes 19 patterns including comma overuse, spacing rigidity, POS diversity, AI vocabulary overuse, and structural monotony. Use when humanizing Korean text from ChatGPT/Claude/Gemini or removing AI traces from Korean LLM output.
Detects and corrects Korean AI writing patterns to transform text into natural human writing. Based on scientific linguistic research (KatFishNet paper with 94.88% AUC accuracy). Analyzes 19 patterns including comma overuse, spacing rigidity, POS diversity, AI vocabulary overuse, and structural monotony. Use when humanizing Korean text from ChatGPT/Claude/Gemini or removing AI traces from Korean LLM output.
> These rules define best practices for implementing and using memory systems
Use these as starting points. Keep user-provided requirements and constraints; do not invent new creative elements.
You generate alt text for HTML `img` tags.
Tools prefixed with `A2A_` are autonomous remote agents.
- Compare outputs objectively based on quality, accuracy, and adherence to requirements
Use npm for this project.
<!-- This section is auto-generated by claude-mem. Edit content outside the tags. -->
领域层是 Clean Architecture 的核心层,定义业务实体、业务规则和数据访问接口。该模块保持纯 Kotlin 实现,不依赖任何 Android 框架。
> **Parent Context**: See `../../CLAUDE.md` for repository-wide guidelines
generic skill
{{systemPromptCustomization}}
Select and apply the correct SQL connector implementation pattern (SDK-default minimal or source-specific custom). Use when building or extending SQL metadata/query extraction connectors.
generic skill
Documentation for the `Mastra.listStoredAgents()` method in Mastra, which retrieves a paginated list of agents from storage.
Shared Drizzle ORM schema for the 15 core Datagrok tables that grok-smith apps reference
Salience Delegation & Latent Horizon Preservation
Develop a memory profiling tool in C for analyzing process memory usage. Implement process attachment with minimal performance impact. Add heap analysis with allocation tracking. Include memory leak d...