Speclint

Score and fix your specs before AI agents build from them

4 followers

Score and fix your specs before AI agents build from them

4 followers

Visit website

Command line tools

Clean spec in. Clean code out. FIX THE SPEC! AI agents build what the spec says, not what you meant. Speclint scores specs 0-100 across 5 dimensions (measurable outcome, testable criteria, constraints, vague verbs, verification steps). Below 70? It rewrites the failing parts automatically. CLI: npx speclint lint "your spec" GitHub Action: scores on issue open MCP Server: inline in Claude/Cursor REST API: for pipelines Open source scoring engine (MIT). Free tier, no signup.

Free Options

Launch tags:Open Source•Developer Tools•Artificial Intelligence

Launch Team / Built With

Framer AI AgentsDesign and publish professional sites with AI

Promoted

Maker

📌

I built Speclint because I kept watching AI agents confidently build the wrong thing. The problem was never the agent — it was the spec I gave it. Speclint scores your specs 0-100 across 5 dimensions before any code gets written. Below 70? It rewrites the failing parts automatically. Think of it as a linter for requirements, not code. It's open source (MIT), works as a CLI, GitHub Action, MCP server, or REST API. Free tier, no signup. > Would love feedback — especially from anyone using AI coding agents daily. What makes a spec "good enough" for your workflow?

Report

6mo ago

Maker

speclint.ai

Report

6mo ago

Reviews