Agentic-first prompt workflows. Markdown templates that teach AI agents how to optimize prompts, create PRDs, and manage implementation. Works with Claude Code, Cursor, Windsurf, and 20 AI coding tools.
| I want to... | Go to |
|---|---|
| Get started | Quickstart |
| See all commands | docs/commands.md |
| Understand the architecture | docs/architecture.md |
| Check integrations | docs/integrations.md |
| Contribute | CONTRIBUTING.md |
Your command format depends on your AI tool:
| Tool Type | Format | Example |
|---|---|---|
| CLI tools (Claude Code, Gemini, Qwen) | Colon (:) |
/clavix:improve |
| IDE extensions (Cursor, Windsurf, Cline) | Hyphen (-) |
/clavix-improve |
Rule of thumb: CLI tools use colon, IDE extensions use hyphen.
npm install -g clavix
clavix init/clavix:improve "Create a secure login page with JWT"
The AI agent reads the template and optimizes your prompt.
graph TD
A["/clavix:improve"] --> B["/clavix:implement"]
C["/clavix:prd"] --> D["/clavix:plan"]
D --> E["/clavix:implement"]
E --> F["/clavix:verify"]
F --> G["/clavix:archive"]
H["/clavix:start"] --> I["/clavix:summarize"]
I --> D
J["/clavix:refine"] --> D
J --> B
/clavix:improve → /clavix:implement
Optimize a prompt and implement it directly.
/clavix:prd → /clavix:plan → /clavix:implement → /clavix:verify → /clavix:archive
Structured planning with PRD, task breakdown, implementation, verification, and archival.
/clavix:start → [conversation] → /clavix:summarize → /clavix:plan
Have a conversation to explore requirements, then extract and plan.
/clavix:refine → (updated PRD or prompt) → continue workflow
Refine existing PRDs or prompts based on feedback.
| Command | Purpose |
|---|---|
/clavix:improve |
Optimize prompts (auto-selects depth) |
/clavix:prd |
Generate PRD through guided questions |
/clavix:plan |
Create task breakdown from PRD |
/clavix:implement |
Execute tasks or prompts |
/clavix:start |
Begin conversational session |
/clavix:summarize |
Extract requirements from conversation |
/clavix:refine |
Refine existing PRD or prompt |
/clavix:verify |
Verify implementation against requirements |
/clavix:archive |
Archive completed projects |
See Getting Started for the full guide.
Clavix is agentic-first:
- You run
clavix init- Sets up slash command templates - You invoke a slash command - Like
/clavix:improve - AI agent reads the template - Markdown instructions
- Agent follows instructions - Using its native tools
- Output is saved - To
.clavix/outputs/
No TypeScript executes during slash commands. The markdown templates ARE the product.
See Architecture for details.
| Category | Tools |
|---|---|
| IDE extensions | Cursor, Windsurf, Kilocode, Roocode, Cline |
| CLI agents | Claude Code, Gemini CLI, Qwen Code, Droid CLI, CodeBuddy, OpenCode, LLXPRT, Amp, Crush CLI, Codex CLI, Augment CLI |
| Universal | AGENTS.md, GitHub Copilot, OCTO.md, WARP.md |
Full list: docs/integrations.md
| Command | Purpose |
|---|---|
clavix init |
Initialize Clavix in a project |
clavix update |
Regenerate templates |
clavix diagnose |
Check installation |
clavix version |
Show version |
All workflows (/clavix:improve, etc.) are slash commands that AI agents execute.
- Getting Started - Installation and first workflow
- Commands Reference - All commands in one place
- Architecture - How Clavix works
- Integrations - Full tool matrix
- CONTRIBUTING.md - Contribute to Clavix
- Node.js >= 18.0.0
- npm or yarn
- An AI coding tool (Claude Code, Cursor, etc.)
Apache-2.0