
Spec Driven Development
Keeps your specs and code from drifting apart by enforcing a tight loop: read the spec in .claude/specs/, implement, verify alignment, update whichever side changed. It'll check off TODOs as you go, flag when you diverge from architectural decisions, and run verification passes to catch drift in API contracts, config values, or module structure. Useful on any project where you're tired of docs rotting the moment implementation starts. The discipline feels heavy at first but pays off when you're three weeks in and the spec still matches reality. Works best when specs are concise and treated as living documents, not write once artifacts.
- skills.sh installs
- 141
- GitHub stars
- 210K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add n8n-io/n8n --skill spec-driven-development --agent claude-codeInstalls into .claude/skills of the current project.
Files
Spec-Driven Development
Specs live in .agents/specs/. They are the source of truth for architectural
decisions, API contracts, and implementation scope. Implementation and specs
must stay in sync — neither leads exclusively.
Core Loop
Read spec → Implement → Verify alignment → Update spec or code → Repeat
Before Starting Work
- Find the spec. Search
.agents/specs/for files matching the feature:
ls .agents/specs/
-
Read the full spec. Understand scope, decisions, API contracts, and open questions before writing code.
-
If no spec exists and the task is non-trivial (new module, new API, architectural change), ask the user whether to create one first.
During Implementation
Sponsors
Details
- Repository
- github.com/n8n-io/n8n
- Category
- Automation & Workflows
- First seen
- Jun 3, 2026