prompt-management
Centralized prompt management for LLM operations. All prompts in lib/prompts/ as named exports. Multi-level extraction, system builder, parameter injection. Triggers on "prompt", "LLM", "system prompt", "extraction", "operational prompt".
npx skills add majiayu000/claude-skill-registry --skill prompt-management --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Prompt Management All LLM prompts centralized in `packages/backend/convex/lib/prompts/`. Never hardcode prompts in actions/routes. Always import from this directory. ## Directory Structure ``` convex/lib/prompts/ ├── index.ts # Central export point ├── base.ts # Base system prompt ├── systemBuilder.ts # Builds system message array ├── formatting.ts # Memory formatting utilities ├── operational/ # Task-specific prompts │ ├── memoryExtraction.ts # Extract facts from conversations │ ├── titleGeneration.ts # Generate titles │ ├── summarization.ts # Summarize text │ ├── tagExtraction.ts # Auto-tag notes/tasks │ ├── documentMode.ts # Canvas mode prompt │ └── ... └── templates/ # User-facing templates └── builtIn.ts ``` ## Named Export Pattern Every prompt MUST be a named export. Never inline strings. ```typescript // From operational/titleGeneration.ts export const CONVERSATION_TITLE_PROMPT = `Generate a 3-6 word title capturing the main topic of this conversation. Rules: - Focus on the core subject, not the request type - Use natural language, avoid technical jargon unless central to the topic - No quotes, periods, or special punctuation - Title case (capitalize first letter of major
- Directory Structure
- Named Export Pattern
- Builder Functions for Dynamic Prompts
- Memory Extraction Levels
- System Prompt Building
- Base System Prompt Pattern
- Prompt Categories
- Central Export Pattern
- Parameter Injection Patterns
- Simple Constant Injection
- Dynamic List Injection
- Threshold Injection
- Conditional Sections
- Key Files
What does the prompt-management skill do?
Centralized prompt management for LLM operations. All prompts in lib/prompts/ as named exports. Multi-level extraction, system builder, parameter injection. Triggers on "prompt", "LLM", "system prompt", "extraction", "operational prompt".
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill prompt-management --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.