spec-driven-implementation: a Claude Code skill by Warp
For teams building large features who want PRODUCT.md and TECH.md specs checked in before and during coding. Skip it for small bug fixes or if you do not track work in Linear.
- Score
- 69of 100
- Rank
- #184of 239
- Installs
- 29Kon skills.sh
- Security
- Clear 3 scanners
- Updated
- 2026
- Context
- ~91tokens always
Install
npx skills add https://github.com/warpdotdev/common-skills --skill spec-driven-implementation
Run it in your terminal. View the source
Using the Claude app rather than Claude Code? You can add a skill there too. How to add it in the app
What does spec-driven-implementation do?
spec-driven-implementation is a skill that runs a spec-first flow for large features, written for the Warp codebase. Claude first decides whether specs are worth it, with about 1,000 lines of code or cross-cutting risk as signals. If no Linear issue exists, it creates one through the Linear MCP tools. It writes specs/<ticket>/PRODUCT.md with the write-product-spec skill, adds TECH.md through write-tech-spec when the design is unclear, then builds with implement-specs. Specs, code and tests stay in one PR, and specs are updated whenever the build drifts. Verification maps back to the spec through tests, screenshots or walkthrough videos.
When should you use spec-driven-implementation?
Use it when
- You are starting a feature spanning several subsystems
- Reviewers need a plan to read before the code
- You want specs kept current in the same PR
Skip it when
- The change is a small bug fix or narrow UI tweak
- You do not use Linear for tickets
What it needs and what it can touch
You need
- The Linear MCP server
- The write-product-spec, write-tech-spec and implement-specs skills
What it can do
- Creates Linear issues through MCP
- Writes spec files and code in the repository
From reading its instructions, not from running it.
Why it scores 69
Strongest on upkeep (100 of 100), weakest on adoption (41).
Is spec-driven-implementation safe to install?
Every scanner that checked it passed it. Scanners often miss what other scanners catch, and a skill can change after a scan. Read its source before you install it.
| Scanner | Result | Date |
|---|---|---|
| Gen Agent Trust Hub | Passed | Sep 15, 2026 |
| Socket | Passed | Sep 15, 2026 |
| Snyk | Low risk | Sep 15, 2026 |
Details
- Installs
- 28,963
- Repository stars
- 671
- Last repository change
- Tokens always loaded
- about 91
- Tokens when used
- about 1,421
- License
- MIT
- Data confidence
- High
Did it do the job for you?
Alternatives to spec-driven-implementation
All skills for this job-
Get write-product-specwrite-product-spec
For teams that want a behavior-first PRODUCT.md spec written before a feature is built.
-
Get writing-planswriting-plans
For developers who give Claude a spec and want a test-first build plan before any code is written.
-
Get brainstormingbrainstorming
For anyone who wants Claude to pin down what they really want before it builds.
-
Get Elephant Goldfish ModelElephant Goldfish Model
For engineers who write design docs before building and want fresh-eyed agent reviewers.