clavix 6.2.0 → 7.1.0

package/README.md

@@ -1,170 +1,83 @@
 # Clavix
 
-> 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, GitHub Copilot, and many AI coding tools.
+> Agentic prompt workflows as skills. Works with any [agentskills.io](https://agentskills.io) compatible AI tool.
 
-## Quick Links
-
-| I want to... | Go to |
-|--------------|-------|
-| Get started | [Quickstart](#quickstart) |
-| See all commands | [docs/commands.md](docs/commands.md) |
-| Understand the architecture | [docs/architecture.md](docs/architecture.md) |
-| Check integrations | [docs/integrations.md](docs/integrations.md) |
-| Contribute | [CONTRIBUTING.md](CONTRIBUTING.md) |
-
-## Command Format
-
-**Your command format depends on your AI tool:**
-
-| Tool Type | Format | Example |
-|-----------|--------|---------|
-| **CLI tools** (Claude Code, Gemini, Qwen) | Colon (`:`) | `/clavix:improve` |
-| **IDEs & extensions** (Cursor, Windsurf, Cline, GitHub Copilot) | Hyphen (`-`) | `/clavix-improve` |
-
-**Rule of thumb:** CLI tools use colon, IDE extensions use hyphen.
-
-## Quickstart
-
-### 1. Install and Initialize
+## Install
 
 ```bash
 npm install -g clavix
 clavix init
 ```
 
-During `clavix init`, pick your AI tools (Cursor, Claude Code, GitHub Copilot, etc.). Clavix installs slash command templates into those integrations.
-
-### 2. Use Slash Commands
+Select **Agent Skills** during setup. Choose global (`~/.config/agents/skills/`) or project (`.skills/`) scope.
 
-```text
-# CLI-style tools (Claude Code, Gemini, Qwen)
-/clavix:improve "Create a secure login page with JWT"
-
-# IDE-style tools (Cursor, Windsurf, GitHub Copilot, etc.)
-/clavix-improve "Create a secure login page with JWT"
-```
-
-The AI agent reads the Clavix template and optimizes your prompt.
-
-### 3. Choose Your Workflow
-
-```mermaid
-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
-```
-
-#### Quick Path (Simple Tasks)
-```
-/clavix:improve → /clavix:implement
-```
-Optimize a prompt and implement it directly.
+## Skills
 
-#### Full Planning (Complex Features)
-```
-/clavix:prd → /clavix:plan → /clavix:implement → /clavix:verify → /clavix:archive
-```
-Structured planning with PRD, task breakdown, implementation, verification, and archival.
+| Skill | Purpose |
+|-------|---------|
+| `clavix-improve` | Optimize prompts with 6-dimension quality assessment |
+| `clavix-prd` | Generate PRD through strategic questions |
+| `clavix-plan` | Create task breakdown from PRD |
+| `clavix-implement` | Execute tasks with progress tracking |
+| `clavix-start` | Begin conversational exploration |
+| `clavix-summarize` | Extract requirements from conversation |
+| `clavix-refine` | Update existing PRD or prompt |
+| `clavix-verify` | Verify implementation against requirements |
+| `clavix-review` | Review PRs with criteria presets |
+| `clavix-archive` | Archive completed projects |
 
-#### Exploratory (Discovery Mode)
-```
-/clavix:start → [conversation] → /clavix:summarize → /clavix:plan
-```
-Have a conversation to explore requirements, then extract and plan.
+## Workflows
 
-#### Refinement (Iteration)
 ```
-/clavix:refine → (updated PRD or prompt) → continue workflow
+Quick:      clavix-improve → clavix-implement
+Full:       clavix-prd → clavix-plan → clavix-implement → clavix-verify
+Exploratory: clavix-start → clavix-summarize → clavix-plan
 ```
-Refine existing PRDs or prompts based on feedback.
-
-### All 10 Slash Commands
-
-| 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:review` | Review teammate PRs using criteria presets |
-| `/clavix:archive` | Archive completed projects |
-
-`/clavix:review` is for reviewing teammates' PRs (criteria-driven, severity levels, saved reports), while `/clavix:verify` checks your implementation against your own PRD.
-
-For a full walkthrough, see [Getting Started](docs/getting-started.md).
 
 ## How It Works
 
-Clavix is **agentic-first**:
+1. **You run `clavix init`** – Skills are installed as directories with `SKILL.md` files
+2. **You invoke a skill** – Your AI tool loads the skill instructions
+3. **The agent follows the workflow** – Using its native tools
+4. **Outputs saved locally** – Under `.clavix/outputs/`
 
-1. **You run `clavix init`** – Select integrations (Cursor, Claude Code, GitHub Copilot, etc.). Clavix installs markdown templates into each tool (e.g. `.cursor/commands/`, `.github/prompts/clavix-*.prompt.md`).
-2. **You invoke a slash command** – Like `/clavix:improve`, `/clavix:plan`, or `/clavix:review` in your AI tool.
-3. **The AI agent reads the template** – Structured markdown instructions with frontmatter.
-4. **The agent follows the instructions** – Using its native tools (edit files, run tests, summarize, review PRs, etc.).
-5. **Outputs are saved locally** – Under `.clavix/outputs/` (including `.clavix/outputs/reviews/` for PR review reports).
+No code executes during skill invocation. The markdown templates ARE the product.
 
-**No TypeScript executes during slash commands.** The markdown templates ARE the product; Clavix only installs and updates them.
+## Other Integrations
 
-See [Architecture](docs/architecture.md) for details.
-
-## Supported AI Tools
+Clavix also supports tool-specific integrations for tools that don't yet support Agent Skills:
 
 | Category | Tools |
 |----------|-------|
-| IDEs & extensions | Cursor, Windsurf, Kilocode, Roocode, Cline, GitHub Copilot (VS Code) |
-| CLI agents | Claude Code, Gemini CLI, Qwen Code, Droid CLI, CodeBuddy, OpenCode, LLXPRT, Amp, Crush CLI, Codex CLI, Augment CLI, Vibe CLI |
-| Universal formats | AGENTS.md, OCTO.md, WARP.md |
-
-In GitHub Copilot Chat, Clavix commands appear as `/clavix-improve`, `/clavix-prd`, `/clavix-review`, etc.
+| IDEs | Cursor, Windsurf, Kilocode, Roocode, Cline, GitHub Copilot |
+| CLI agents | Claude Code, Gemini CLI, Qwen, Droid, CodeBuddy, OpenCode, LLXPRT, Amp, Crush, Codex, Augment, Vibe |
+| Universal | AGENTS.md, OCTO.md, WARP.md |
 
-Full list: [docs/integrations.md](docs/integrations.md)
+Run `clavix init` and select your tools. Command format varies by tool:
+- **CLI tools** (Claude Code, Gemini): `/clavix:improve`
+- **IDE extensions** (Cursor, Copilot): `/clavix-improve`
 
 ## CLI Commands
 
 | Command | Purpose |
 |---------|---------|
-| `clavix init` | Initialize or reconfigure Clavix integrations in a project |
-| `clavix update` | Regenerate templates for selected integrations |
-| `clavix diagnose` | Check installation and integration health |
+| `clavix init` | Initialize or reconfigure integrations |
+| `clavix update` | Regenerate templates |
+| `clavix diagnose` | Check installation health |
 | `clavix version` | Show version |
 
-All workflows (`/clavix:improve`, `/clavix:plan`, `/clavix:review`, etc.) are **slash commands** that your AI tools execute using Clavix templates.
+## Docs
 
-## Documentation
-
-- [Getting Started](docs/getting-started.md) - Installation and first workflow
-- [Commands Reference](docs/commands.md) - All commands in one place
-- [Architecture](docs/architecture.md) - How Clavix works
-- [Integrations](docs/integrations.md) - Full tool matrix
-- [CONTRIBUTING.md](CONTRIBUTING.md) - Contribute to Clavix
+- [Commands Reference](docs/commands.md)
+- [Integrations](docs/integrations.md)
+- [Architecture](docs/architecture.md)
+- [Getting Started](docs/getting-started.md)
 
 ## Requirements
 
-- **Node.js >= 18.0.0**
-- npm or yarn
-- An AI coding tool (Claude Code, Cursor, GitHub Copilot, etc.)
+- Node.js >= 18.0.0
+- An AI coding tool
 
 ## License
 
 Apache-2.0
-
-## Star History
-
-<a href="https://www.star-history.com/#ClavixDev/Clavix&type=date&legend=top-left">
- <picture>
-   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=ClavixDev/Clavix&type=date&theme=dark&legend=top-left" />
-   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=ClavixDev/Clavix&type=date&legend=top-left" />
-   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=ClavixDev/Clavix&type=date&legend=top-left" />
- </picture>
-</a>

package/dist/cli/commands/init.js

@@ -261,12 +261,71 @@ export default class Init extends Command {
                     }
                 }
             }
+            // Prompt for custom Agent Skills path if selected
+            if (selectedIntegrations.includes('agent-skills-custom')) {
+                this.log(chalk.cyan('\n🔧 Agent Skills Custom Path Configuration'));
+                const { pathType } = await inquirer.prompt([
+                    {
+                        type: 'list',
+                        name: 'pathType',
+                        message: 'What type of path do you want to use?',
+                        choices: [
+                            {
+                                name: 'Relative - resolved from current folder (e.g., .aider-desk/skills)',
+                                value: 'relative',
+                            },
+                            {
+                                name: 'Absolute - starts from root or home (e.g., ~/.config/my-skills or /opt/skills)',
+                                value: 'absolute',
+                            },
+                        ],
+                    },
+                ]);
+                const existingCustomPath = existingConfig?.experimental?.integrationPaths?.['agent-skills-custom'];
+                const { customSkillsPath } = await inquirer.prompt([
+                    {
+                        type: 'input',
+                        name: 'customSkillsPath',
+                        message: 'Enter path to skills directory:',
+                        default: existingCustomPath ||
+                            (pathType === 'relative' ? '.skills' : '~/.config/agents/skills'),
+                        validate: (input) => {
+                            const trimmed = input.trim();
+                            if (!trimmed) {
+                                return 'Path cannot be empty';
+                            }
+                            if (pathType === 'relative') {
+                                if (path.isAbsolute(trimmed) || trimmed.startsWith('~/')) {
+                                    return 'Relative path should not start with / or ~/. Example: .aider-desk/skills';
+                                }
+                            }
+                            else {
+                                if (!path.isAbsolute(trimmed) && !trimmed.startsWith('~/')) {
+                                    return 'Absolute path should start with / or ~/. Example: ~/.config/my-skills';
+                                }
+                            }
+                            return true;
+                        },
+                    },
+                ]);
+                integrationPaths['agent-skills-custom'] = customSkillsPath.trim();
+                this.log(chalk.gray(`  ✓ Using custom skills path: ${customSkillsPath.trim()}`));
+            }
             // Create .clavix directory structure
             this.log(chalk.cyan('\n📁 Creating directory structure...'));
             await this.createDirectoryStructure();
             // Generate config
             this.log(chalk.cyan('⚙️  Generating configuration...'));
             await this.generateConfig(selectedIntegrations, integrationPaths);
+            // Re-create AgentManager with updated config (includes custom integration paths)
+            const updatedConfig = {
+                ...DEFAULT_CONFIG,
+                integrations: selectedIntegrations,
+                ...(Object.keys(integrationPaths).length > 0 && {
+                    experimental: { integrationPaths },
+                }),
+            };
+            const updatedAgentManager = new AgentManager(updatedConfig);
             // Generate INSTRUCTIONS.md and QUICKSTART.md
             await this.generateInstructions();
             await this.generateQuickstart();
@@ -292,9 +351,17 @@ export default class Init extends Command {
                 }
                 // Handle Agent Skills integrations
                 if (isAgentSkillsIntegration(integrationName)) {
-                    const adapter = agentManager.requireAdapter(integrationName);
-                    const scope = integrationName === 'agent-skills-global' ? 'global' : 'project';
-                    const location = scope === 'global' ? '~/.config/agents/skills/' : '.skills/';
+                    const adapter = updatedAgentManager.requireAdapter(integrationName);
+                    let location;
+                    if (integrationName === 'agent-skills-global') {
+                        location = '~/.config/agents/skills/';
+                    }
+                    else if (integrationName === 'agent-skills-project') {
+                        location = '.skills/';
+                    }
+                    else {
+                        location = integrationPaths['agent-skills-custom'] || 'custom path';
+                    }
                     this.log(chalk.gray(`  ✓ Generating ${adapter.displayName}...`));
                     // Validate before generating
                     if (adapter.validate) {

package/dist/core/adapters/agent-skills-adapter.d.ts

@@ -27,8 +27,13 @@ export declare class AgentSkillsAdapter extends BaseAdapter {
     get installScope(): SkillScope;
     /**
      * Get the directory path based on scope
+     * For custom scope without a configured path, returns a placeholder
      */
     get directory(): string;
+    /**
+     * Check if the adapter is properly configured
+     */
+    isConfigured(): boolean;
     /**
      * Expand tilde in path to home directory
      */

package/dist/core/adapters/agent-skills-adapter.js

@@ -31,12 +31,21 @@ export class AgentSkillsAdapter extends BaseAdapter {
         this.scope = scope;
         this.userConfig = userConfig;
         // Set name and displayName based on scope
-        this.name = scope === 'global' ? 'agent-skills-global' : 'agent-skills-project';
-        this.displayName = scope === 'global' ? 'Agent Skills (Global)' : 'Agent Skills (Project)';
+        if (scope === 'global') {
+            this.name = 'agent-skills-global';
+            this.displayName = 'Agent Skills (Global)';
+        }
+        else if (scope === 'project') {
+            this.name = 'agent-skills-project';
+            this.displayName = 'Agent Skills (Project)';
+        }
+        else {
+            this.name = 'agent-skills-custom';
+            this.displayName = 'Agent Skills (Custom Path)';
+        }
         // Check for custom path in user config
-        const configKey = scope === 'global' ? 'agent-skills-global' : 'agent-skills-project';
-        if (userConfig?.experimental?.integrationPaths?.[configKey]) {
-            this.customPath = userConfig.experimental.integrationPaths[configKey];
+        if (userConfig?.experimental?.integrationPaths?.[this.name]) {
+            this.customPath = userConfig.experimental.integrationPaths[this.name];
         }
     }
     /**
@@ -47,13 +56,26 @@ export class AgentSkillsAdapter extends BaseAdapter {
     }
     /**
      * Get the directory path based on scope
+     * For custom scope without a configured path, returns a placeholder
      */
     get directory() {
         if (this.customPath) {
             return this.customPath;
         }
+        if (this.scope === 'custom') {
+            return '<custom-path-not-configured>';
+        }
         return this.scope === 'global' ? SKILL_PATHS.global : SKILL_PATHS.project;
     }
+    /**
+     * Check if the adapter is properly configured
+     */
+    isConfigured() {
+        if (this.scope === 'custom') {
+            return !!this.customPath;
+        }
+        return true;
+    }
     /**
      * Expand tilde in path to home directory
      */
@@ -68,9 +90,15 @@ export class AgentSkillsAdapter extends BaseAdapter {
      */
     getCommandPath() {
         const dir = this.directory;
-        if (dir.startsWith('~/') || this.scope === 'global') {
+        // Expand ~ paths
+        if (dir.startsWith('~/')) {
             return this.expandPath(dir);
         }
+        // Absolute paths (global scope default or user-provided absolute)
+        if (this.scope === 'global' || path.isAbsolute(dir)) {
+            return dir;
+        }
+        // Relative paths (project scope or custom relative)
         return path.join(process.cwd(), dir);
     }
     /**
@@ -99,6 +127,9 @@ export class AgentSkillsAdapter extends BaseAdapter {
      *       └── <reference-files>.md
      */
     async generateCommands(templates) {
+        if (!this.isConfigured()) {
+            throw new IntegrationError('Custom scope requires a custom path to be set', 'Ensure agent-skills-custom has a path configured in experimental.integrationPaths');
+        }
         const skillsPath = this.getCommandPath();
         try {
             // Ensure base directory exists

package/dist/core/agent-manager.js

@@ -28,9 +28,10 @@ export class AgentManager {
         this.registerAdapter(new QwenAdapter(userConfig)); // TOML format
         this.registerAdapter(new LlxprtAdapter(userConfig)); // TOML format
         this.registerAdapter(new VibeAdapter(userConfig)); // Vibe CLI skills
-        // Register Agent Skills adapters (both global and project scope)
+        // Register Agent Skills adapters (global, project, and custom scope)
         this.registerAdapter(new AgentSkillsAdapter('global', userConfig));
         this.registerAdapter(new AgentSkillsAdapter('project', userConfig));
+        this.registerAdapter(new AgentSkillsAdapter('custom', userConfig));
         // Register simple adapters from config (using UniversalAdapter factory)
         for (const config of getSimpleAdapters()) {
             // Skip adapters that have special handlers registered above

package/dist/templates/slash-commands/_canonical/archive.md

@@ -274,7 +274,7 @@ Result: Project permanently deleted
 
 ---
 
-## Agent Transparency (v6.2.0)
+## Agent Transparency (v7.1.0)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

package/dist/templates/slash-commands/_canonical/implement.md

@@ -615,7 +615,7 @@ I'll explain what's wrong and what you might need to do:
 
 ---
 
-## Agent Transparency (v6.2.0)
+## Agent Transparency (v7.1.0)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

package/dist/templates/slash-commands/_canonical/improve.md

@@ -524,7 +524,7 @@ Wait for the user to decide what to do next.
 
 ---
 
-## Agent Transparency (v6.2.0)
+## Agent Transparency (v7.1.0)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

package/dist/templates/slash-commands/_canonical/plan.md

@@ -229,7 +229,7 @@ Present the plan and ask:
 
 ---
 
-## Agent Transparency (v6.2.0)
+## Agent Transparency (v7.1.0)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

package/dist/templates/slash-commands/_canonical/prd.md

@@ -354,7 +354,7 @@ The validation ensures generated PRDs are immediately usable for AI consumption
 
 ---
 
-## Agent Transparency (v6.2.0)
+## Agent Transparency (v7.1.0)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

package/dist/templates/slash-commands/_canonical/refine.md

@@ -415,7 +415,7 @@ I'll update the PRD and add this to the refinement history. Confirm?
 
 ---
 
-## Agent Transparency (v6.2.0)
+## Agent Transparency (v7.1.0)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

package/dist/templates/slash-commands/_canonical/review.md

@@ -447,7 +447,7 @@ consistent with the project's conventions.
 
 ---
 
-## Agent Transparency (v6.2.0)
+## Agent Transparency (v7.1.0)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

package/dist/templates/slash-commands/_canonical/start.md

@@ -230,7 +230,7 @@ The goal is natural exploration of requirements, not a rigid questionnaire. Foll
 
 ---
 
-## Agent Transparency (v6.2.0)
+## Agent Transparency (v7.1.0)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

package/dist/templates/slash-commands/_canonical/summarize.md

@@ -409,7 +409,7 @@ The `/clavix:summarize` command extracts requirements from exploratory conversat
 
 ---
 
-## Agent Transparency (v6.2.0)
+## Agent Transparency (v7.1.0)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

package/dist/templates/slash-commands/_canonical/verify.md

@@ -123,7 +123,7 @@ Implementation: BLOCKED - I'll analyze and report, not modify or fix
 
 ----
 
-## Agent Transparency (v6.2.0)
+## Agent Transparency (v7.1.0)
 
 ### Agent Manual (Universal Protocols)
 {{INCLUDE:agent-protocols/AGENT_MANUAL.md}}

package/dist/types/skill.d.ts

@@ -9,7 +9,7 @@
 /**
  * Skill installation scope
  */
-export type SkillScope = 'global' | 'project';
+export type SkillScope = 'global' | 'project' | 'custom';
 /**
  * Skill template with optional references
  * Used during skill generation
@@ -71,7 +71,7 @@ export interface SkillDirectory {
  * Skills configuration options
  */
 export interface SkillsConfig {
-    /** Installation scope: 'global' or 'project' */
+    /** Installation scope: 'global', 'project', or 'custom' */
     scope: SkillScope;
     /** Custom directory path (overrides default based on scope) */
     customPath?: string;

package/dist/utils/integration-selector.js

@@ -21,6 +21,7 @@ export async function selectIntegrations(agentManager, preSelected = []) {
                 new inquirer.Separator('=== Agent Skills (agentskills.io) ==='),
                 { name: 'Agent Skills - Global (~/.config/agents/skills/)', value: 'agent-skills-global' },
                 { name: 'Agent Skills - Project (.skills/)', value: 'agent-skills-project' },
+                { name: 'Agent Skills - Custom Path', value: 'agent-skills-custom' },
                 new inquirer.Separator(),
                 new inquirer.Separator('=== CLI Tools ==='),
                 { name: 'Amp (.agents/commands/)', value: 'amp' },
@@ -83,7 +84,9 @@ export function ensureMandatoryIntegrations(integrations) {
  * Check if agent skills integration is selected
  */
 export function hasAgentSkillsSelected(integrations) {
-    return integrations.includes('agent-skills-global') || integrations.includes('agent-skills-project');
+    return (integrations.includes('agent-skills-global') ||
+        integrations.includes('agent-skills-project') ||
+        integrations.includes('agent-skills-custom'));
 }
 /**
  * Get the skill scope from integration name
@@ -93,12 +96,16 @@ export function getSkillScope(integrationName) {
         return 'global';
     if (integrationName === 'agent-skills-project')
         return 'project';
+    if (integrationName === 'agent-skills-custom')
+        return 'custom';
     return null;
 }
 /**
  * Check if integration name is an agent skills integration
  */
 export function isAgentSkillsIntegration(name) {
-    return name === 'agent-skills-global' || name === 'agent-skills-project';
+    return (name === 'agent-skills-global' ||
+        name === 'agent-skills-project' ||
+        name === 'agent-skills-custom');
 }
 //# sourceMappingURL=integration-selector.js.map

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "clavix",
-  "version": "6.2.0",
+  "version": "7.1.0",
   "description": "Agentic-first prompt workflows. Markdown templates that teach AI agents how to optimize prompts, create PRDs, and manage implementation.\n\nSLASH COMMANDS (in your AI assistant):\n  /clavix:improve    Optimize prompts with auto-depth\n  /clavix:prd        Generate PRD through questions\n  /clavix:plan       Create task breakdown from PRD\n  /clavix:implement  Execute tasks with progress tracking\n  /clavix:start      Begin conversational session\n  /clavix:summarize  Extract requirements from conversation\n  /clavix:refine     Refine existing PRD or prompt\n  /clavix:verify     Verify implementation against requirements\n  /clavix:review     Review teammate PRs with criteria\n  /clavix:archive    Archive completed projects\n\nWorks with Claude Code, Cursor, Windsurf, and 20 AI coding tools.",
   "type": "module",
   "main": "dist/index.js",