Spec-driven SDLC skills for AI coding agents — Claude Code, Cursor, Windsurf, Gemini CLI
Project description
ai-sdlc-kit
Spec-driven SDLC skills that make AI coding agents work like real engineers.
What is it?
ai-sdlc-kit installs a set of skills for Claude Code, Cursor, Windsurf, and Gemini CLI that take an agent through a real engineering workflow instead of one-shot code generation:
understand → decide → plan in verifiable steps → build with checks after every step → gate → ship
| Skill | Does |
|---|---|
sdlc-init |
One-time project setup: stack, layout, commands, conventions |
roadmap |
Splits a PRD into ordered, shippable features |
spec |
Plans one feature: decisions, tasks with contracts + verify commands |
build |
Executes the spec task-by-task, verifying after every step |
qa |
Re-runs verifies + acceptance checks; failures become fix-tasks |
ship |
Branch guard, staged commit built from the spec — never pushes |
architecture-diagram |
Renders a self-contained HTML/SVG architecture diagram |
Install
pip install ai-sdlc-kit
# or: uv tool install ai-sdlc-kit
Use
ai-sdlc install --agent claude # or cursor / windsurf / gemini / all
This copies the skills into your agent's skills directory. They then appear as slash commands: /sdlc-init, /roadmap, /spec, /build, /qa, /ship.
| Flag | Effect |
|---|---|
--agent all |
install for every supported agent at once |
--target PATH |
install into a specific project directory (default: .) |
--global |
install into your home directory instead of a project |
--force |
overwrite existing skill folders |
ai-sdlc list # see bundled skills
ai-sdlc --version # print the installed version
Changelog
-
0.1.1— cleaner README, professional package presentation -
0.1.0— initial release: 6 core skills + architecture-diagram, pip-installable CLI
Related prior art: github/spec-kit.
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file ai_sdlc_kit-0.1.1.tar.gz.
File metadata
- Download URL: ai_sdlc_kit-0.1.1.tar.gz
- Upload date:
- Size: 18.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.10.7 {"installer":{"name":"uv","version":"0.10.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
22b00ad8c96c93ac45a87566481a5567630d7d26ec21ceb50fd635808261cbba
|
|
| MD5 |
fe5b501bc750c7070f07725585c6a395
|
|
| BLAKE2b-256 |
09abb9e07303d25a314dfbb78b1b803c26504c5529d7ca00c9ae0527f8d1c07a
|
File details
Details for the file ai_sdlc_kit-0.1.1-py3-none-any.whl.
File metadata
- Download URL: ai_sdlc_kit-0.1.1-py3-none-any.whl
- Upload date:
- Size: 23.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.10.7 {"installer":{"name":"uv","version":"0.10.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
63fc7d29634086f30d962707dba68b3b5c401b6a681f13a24aa2df04923d9089
|
|
| MD5 |
ef433032bc569a358026df4621e74b05
|
|
| BLAKE2b-256 |
65109be75c68a3f73e519f9d16f2e1fb38700a30f905eb8ce34f0d639e3d298a
|
