prompt-management

Consolidate LLM prompts into a centralized library with named exports and builder utilities.

7|Updated Dec 4, 2025
One-click install
npx skills add https://github.com/planetaryescape/blah.chat --skill prompt-management
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: prompt-management
Source: https://github.com/planetaryescape/blah.chat/tree/main/.claude/skills/prompt-management
Command: npx skills add https://github.com/planetaryescape/blah.chat --skill prompt-management

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill consolidates LLM prompts into a single, auditable library to prevent ad-hoc prompt usage and ensure consistent behavior across models and projects.

Core Features & Use Cases

  • Centralized Prompt Library: All prompts are exported as named exports from lib/prompts, avoiding hardcoded strings in actions or routes.
  • Dynamic Prompt Building: Builder functions enable parameterized prompts and context-aware injections for flexible workflows.
  • System Prompt Composition: Multi-source system prompts are composed with clear priority, ensuring predictable LLM behavior.
  • Use Case: Standardize prompts across AI models in a team, enabling reuse, versioning, and easier maintenance.

Quick Start

Import the central prompts index and start using the named exports in your model calls, e.g.:

  • Import { CONVERSATION_TITLE_PROMPT } from "../lib/prompts";

Frequently Asked Questions about prompt-management

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I centralize LLM prompts to stop hardcoding strings in model workflows?

Centralizing LLM prompts involves exporting them as named exports from a dedicated library, preventing hardcoded strings. This creates an auditable index, ensuring consistent model behavior and enabling easier maintenance across projects.

What is the best way to build parameterized system prompts for AI models?

Building parameterized system prompts uses builder functions for context-aware injections. Multi-source system prompts are composed with clear priority, ensuring predictable LLM behavior across different dynamic workflows.

Can I compose multi-source system prompts with clear priority for deterministic LLM behavior?

Yes, multi-source system prompts are composed with explicit priority levels. This composition ensures deterministic LLM behavior by standardizing how context and instructions are assembled before model execution.

How do I inject parameters dynamically into a centralized prompt library?

Dynamic parameter injection uses builder utility functions within the prompt library. These functions accept parameters and context, constructing prompts on the fly for flexible and standardized model workflows.

Does prompt-management work without external dependencies for prompt governance?

Yes, this prompt governance operates without external dependencies. It uses internal builder utilities and a central index to standardize prompts, requiring only a compatible LLM workflow environment to function.

Why should I use a centralized prompt library instead of ad-hoc prompt strings?

A centralized prompt library prevents ad-hoc prompt usage, ensuring consistent behavior across models. It enables team reuse, versioning, and easier maintenance by consolidating prompts into an auditable index.