Promptlint Spec v2
# Technical Specification: promptlint v2
## 1. Project Overview
`promptlint` is a static analysis tool (linter) for Large Language Model (LLM) prompts. It treats prompts as code artifacts, analyzing them for token bloat, missing context, security vulnerabilities (prompt injection vectors), hallucination risk, structural inconsistencies, and cross-prompt pipeline integrity.
- **Target Environment:** Python 3.9+
- **Primary Interface:** CLI
- **Core Dependencies:** `typer` (CLI), `pydantic` (Data Models), `pyyaml` (Config/Parsing), `tiktoken` (Token estimation), `rich` (Console output), `watchfiles` (Watch mode)
---
## 2. Architecture & Directory Structurewhen to use it
Community prompt sourced from the open-source GitHub repo scottconverse/promptlint (MIT). A "Promptlint Spec v2" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.
tags
roleplaycommunitygeneral
source
scottconverse/promptlint · MIT