by joshft · Claude Skill · ★ 61
Correctless Composable Claude Code skills that enforce a correctness-oriented development workflow. Spec before you code. Test before you implement. Never let an agent grade its own work. The Problem AI coding assistants are fast but sloppy. They write code that works for the happy path, skip edge cases, and silently introduce bugs that don't surface until production. The same model that wrote the code will review it and say "looks good" — because it's confirming its own decisions.
| Stars | 61 |
| Forks | 2 |
| Language | Shell |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 53.338/100 |
| Last Updated | 2026-05-20 |
| Created | 2026-03-27 |
| Platforms | claude-code, cli |
| Est. Tokens | ~195k |
Explore other popular claude skill tools:
correctless is The agent that writes the code never reviews it. Spec-driven TDD with agent separation, adversarial QA, and dynamic rigor for Claude Code.. It is categorized as a Claude Skill with 61 GitHub stars.
correctless is primarily written in Shell. It covers topics such as ai-development, ai-workflow, claude.
You can find installation instructions and usage details in the correctless GitHub repository at github.com/joshft/correctless. The project has 61 stars and 2 forks, indicating an active community.
correctless is released under the MIT license, making it free to use and modify according to the license terms.