Speclint

Speclint is an open-source spec linter that scores user stories and requirements on a 0-100 scale across 5 dimensions: Measurable Outcomes (20pts), Testable Criteria (25pts), Constraints (20pts), No Vague Verbs (20pts), and Verification Steps (15pts).

The scoring is fully deterministic — pure regex pattern matching, no LLM involved. AI is only used for the optional rewrite feature, which rewrites failing specs to pass all checks. Available as: CLI (npx speclint lint), GitHub Action, MCP Server (3 tools), and REST API.

Free tier: 5 lints/day. Paid plans start at $9/mo for unlimited linting and rewrites. Open source (MIT).

Built for teams shipping to AI coding agents — if your spec scores below 70, the agent will hallucinate. Fix the spec first.

## How to Use

Run npx speclint lint in your terminal, paste a user story, and get a 0-100 score instantly. Or add the GitHub Action to score specs on every PR. Or connect the MCP Server to Claude, Cursor, or any AI coding agent — it auto-lints specs before the agent writes code.

## Key Features

- Deterministic 0-100 scoring across 5 dimensions - CLI, GitHub Action, and MCP Server - AI-powered spec rewrite to fix failing specs - Agent-ready threshold scoring (70+) - Open source (MIT) with paid tiers

## Use Cases

- Score user stories before handing them to AI coding agents - Add spec quality gates to CI/CD pipelines - Rewrite vague requirements into agent-ready specs - Audit backlog quality across a sprint