@zenku/agent-kit 0.1.4 → 0.1.6

package/README.md

@@ -0,0 +1,138 @@
+# @zenku/agent-kit
+
+Skills, agents, and personas for the Zenku ecosystem. Works with Claude Code, OpenCode, and Codex CLI.
+
+## Contents
+
+### Skills
+
+| Name              | Description                                                                       |
+| ----------------- | --------------------------------------------------------------------------------- |
+| `frontend-design` | Create distinctive, production-grade frontend interfaces with high design quality |
+| `skill-creator`   | Guide for creating effective skills that extend agent capabilities                |
+| `zenku-kanban`    | Manage kanban projects, issues, labels, and comments via the zenku CLI            |
+
+### Agents
+
+| Name                    | Description                                                                           |
+| ----------------------- | ------------------------------------------------------------------------------------- |
+| `code-architect`        | Designs feature architectures by analyzing codebase patterns and conventions          |
+| `code-explorer`         | Deeply analyzes codebase features by tracing execution paths and mapping architecture |
+| `code-reviewer`         | Reviews code for bugs, security vulnerabilities, and quality issues                   |
+| `code-simplifier`       | Simplifies code for clarity and maintainability while preserving functionality        |
+| `silent-failure-hunter` | Identifies silent failures, inadequate error handling, and suppressed errors          |
+| `skill-reviewer`        | Reviews skill quality and ensures skills follow best practices                        |
+
+### Personas
+
+| Name    | Description                                                       |
+| ------- | ----------------------------------------------------------------- |
+| `zenku` | A focused, minimal coding assistant with a Japanese zen aesthetic |
+
+## Installation
+
+Install the package globally:
+
+```bash
+npm install -g @zenku/agent-kit
+```
+
+Then copy the artifacts you want into your project.
+
+### Claude Code
+
+```bash
+KIT=$(npm root -g)/@zenku/agent-kit
+
+# Skills → .claude/skills/
+mkdir -p .claude/skills
+unzip -o "$KIT/skills/frontend-design.skill" -d .claude/skills/frontend-design/
+
+# Agents → .claude/agents/
+mkdir -p .claude/agents
+unzip -o "$KIT/agents/code-reviewer.agent" -d .claude/agents/
+
+# Personas → .claude/agents/ (personas are used as main thread agents)
+unzip -o "$KIT/personas/zenku.persona" -d .claude/agents/
+```
+
+To use a persona as your default agent:
+
+```bash
+# Via CLI flag
+claude --agent zenku
+
+# Or set in .claude/settings.json
+{
+  "agent": "zenku"
+}
+```
+
+### OpenCode
+
+```bash
+KIT=$(npm root -g)/@zenku/agent-kit
+
+# Skills → .opencode/skills/
+mkdir -p .opencode/skills
+unzip -o "$KIT/skills/frontend-design.skill" -d .opencode/skills/frontend-design/
+
+# Agents → .opencode/agents/
+mkdir -p .opencode/agents
+unzip -o "$KIT/agents/code-reviewer.agent" -d .opencode/agents/
+unzip -o "$KIT/personas/zenku.persona" -d .opencode/agents/
+```
+
+### Manual
+
+Each `.skill`, `.agent`, and `.persona` file is a standard zip archive. You can unzip them with any tool:
+
+```bash
+unzip frontend-design.skill -d frontend-design/
+unzip code-reviewer.agent
+unzip zenku.persona
+```
+
+Inside each archive is one or more `.md` files with YAML frontmatter and a markdown body.
+
+## Usage
+
+**Skills** are invoked with slash commands (e.g., `/frontend-design`) or triggered automatically when the agent detects a matching task.
+
+**Agents** are specialized sub-agents spawned for specific tasks. They appear in agent selection when placed in the agents directory.
+
+**Personas** replace the default AI identity for the entire session. Set one as your main thread agent to change the assistant's personality, tone, and behavior.
+
+## Uninstall
+
+Remove the files you copied:
+
+```bash
+# Claude Code
+rm -rf .claude/skills/frontend-design/
+rm -f .claude/agents/code-reviewer.md
+rm -f .claude/agents/zenku.md
+
+# OpenCode
+rm -rf .opencode/skills/frontend-design/
+rm -f .opencode/agents/code-reviewer.md
+rm -f .opencode/agents/zenku.md
+```
+
+## Update
+
+When a new version is published:
+
+```bash
+npm update -g @zenku/agent-kit
+```
+
+Then re-copy the artifacts you use (see Installation above). New versions may add, update, or remove artifacts — check the manifest for changes:
+
+```bash
+cat $(npm root -g)/@zenku/agent-kit/manifest.json
+```
+
+## Manifest
+
+The `manifest.json` file at the package root lists all included artifacts with their frontmatter metadata. Use it to programmatically discover available skills, agents, and personas.

package/manifest.json

@@ -0,0 +1,63 @@
+{
+  "skills": {
+    "frontend-design": {
+      "name": "frontend-design",
+      "description": "Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics."
+    },
+    "skill-creator": {
+      "name": "skill-creator",
+      "description": "Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends the agent's capabilities with specialized knowledge, workflows, or tool integrations."
+    },
+    "zenku-kanban": {
+      "name": "zenku-kanban",
+      "description": "Manage kanban projects, issues, labels, comments, and links via the zenku CLI. Use when the user wants to create/update/list kanban issues, manage projects, track work items, add comments, link issues, or manage labels. Also covers CLI installation and authentication (login/logout/whoami/profiles) as prerequisites. Trigger when user mentions zenku, kanban, issues, sprints, project boards, or task tracking via CLI."
+    }
+  },
+  "agents": {
+    "code-architect": {
+      "name": "code-architect",
+      "description": "Designs feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create/modify, component designs, data flows, and build sequences",
+      "model": "inherit",
+      "color": "green"
+    },
+    "code-explorer": {
+      "name": "code-explorer",
+      "description": "Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, understanding patterns and abstractions, and documenting dependencies to inform new development",
+      "model": "inherit",
+      "color": "yellow"
+    },
+    "code-reviewer": {
+      "name": "code-reviewer",
+      "description": "Reviews code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions, using confidence-based filtering to report only high-priority issues that truly matter",
+      "model": "inherit",
+      "color": "red"
+    },
+    "code-simplifier": {
+      "name": "code-simplifier",
+      "description": "Use this agent when code has been written or modified and needs to be simplified for clarity, consistency, and maintainability while preserving all functionality. This agent should be triggered automatically after completing a coding task or writing a logical chunk of code. It simplifies code by following project best practices while retaining all functionality. The agent focuses only on recently modified code unless instructed otherwise.\n\nExamples:\n\n<example>\nContext: The assistant has just implemented a new feature that adds user authentication to an API endpoint.\nuser: \"Please add authentication to the /api/users endpoint\"\nassistant: \"I've implemented the authentication for the /api/users endpoint. Here's the code:\"\n<commentary>\nSince a logical chunk of code has been written (authentication feature), use the code-simplifier agent to improve the code's clarity and maintainability while preserving functionality.\n</commentary>\nassistant: \"Now let me use the code-simplifier agent to refine this implementation for better clarity and maintainability\"\n</example>\n\n<example>\nContext: The assistant has just fixed a bug by adding several conditional checks.\nuser: \"Fix the null pointer exception in the data processor\"\nassistant: \"I've added the necessary null checks to prevent the exception:\"\n<commentary>\nAfter modifying code to fix a bug, use the code-simplifier agent to ensure the fix follows best practices and maintains code quality.\n</commentary>\nassistant: \"Let me refine this bug fix using the code-simplifier agent to ensure it follows our best practices\"\n</example>\n\n<example>\nContext: The assistant has just refactored a function to improve performance.\nuser: \"Optimize the data sorting algorithm for better performance\"\nassistant: \"I've optimized the sorting algorithm. Here's the updated implementation:\"\n<commentary>\nAfter completing a performance optimization task, use the code-simplifier agent to ensure the optimized code is also clear and maintainable.\n</commentary>\nassistant: \"Now I'll use the code-simplifier agent to ensure the optimized code is also clear and follows our coding standards\"\n</example>",
+      "model": "inherit",
+      "color": "magenta"
+    },
+    "silent-failure-hunter": {
+      "name": "silent-failure-hunter",
+      "description": "Use this agent when reviewing code changes to identify silent failures, inadequate error handling, and inappropriate fallback behavior. This agent should be invoked proactively after completing a logical chunk of work that involves error handling, catch blocks, fallback logic, or any code that could potentially suppress errors.\n\n<example>\nContext: The user has just finished implementing a new feature that fetches data from an API with fallback behavior.\nuser: \"I've added error handling to the API client. Can you review it?\"\nassistant: \"Let me use the silent-failure-hunter agent to thoroughly examine the error handling in your changes.\"\n</example>\n\n<example>\nContext: The user has created a PR with changes that include try-catch blocks.\nuser: \"Please review PR #1234\"\nassistant: \"I'll use the silent-failure-hunter agent to check for any silent failures or inadequate error handling in this PR.\"\n</example>\n\n<example>\nContext: The user has just refactored error handling code.\nuser: \"I've updated the error handling in the authentication module\"\nassistant: \"Let me proactively use the silent-failure-hunter agent to ensure the error handling changes don't introduce silent failures.\"\n</example>",
+      "model": "inherit",
+      "color": "yellow"
+    },
+    "skill-reviewer": {
+      "name": "skill-reviewer",
+      "description": "Use this agent when the user has created or modified a skill and needs quality review, asks to \"review my skill\", \"check skill quality\", \"improve skill description\", or wants to ensure skill follows best practices. Trigger proactively after skill creation. Examples:\n\n<example>\nContext: User just created a new skill\nuser: \"I've created a PDF processing skill\"\nassistant: \"Great! Let me review the skill quality.\"\n<commentary>\nSkill created, proactively trigger skill-reviewer to ensure it follows best practices.\n</commentary>\nassistant: \"I'll use the skill-reviewer agent to review the skill.\"\n</example>\n\n<example>\nContext: User requests skill review\nuser: \"Review my skill and tell me how to improve it\"\nassistant: \"I'll use the skill-reviewer agent to analyze the skill quality.\"\n<commentary>\nExplicit skill review request triggers the agent.\n</commentary>\n</example>\n\n<example>\nContext: User modified skill description\nuser: \"I updated the skill description, does it look good?\"\nassistant: \"I'll use the skill-reviewer agent to review the changes.\"\n<commentary>\nSkill description modified, review for triggering effectiveness.\n</commentary>\n</example>",
+      "model": "inherit",
+      "color": "cyan",
+      "tools": "[\"Read\", \"Grep\", \"Glob\"]"
+    }
+  },
+  "personas": {
+    "zenku": {
+      "name": "zenku",
+      "description": "A focused, minimal coding assistant with a Japanese zen aesthetic",
+      "model": "inherit",
+      "color": "cyan"
+    }
+  }
+}

package/package.json

@@ -1,10 +1,12 @@
 {
   "name": "@zenku/agent-kit",
-  "version": "0.1.4",
-  "description": "Agent kit (skills, agents, commands) for the Zenku ecosystem — works with Claude Code, OpenCode, and Codex CLI.",
+  "version": "0.1.6",
+  "description": "Agent kit (skills, agents, personas) for the Zenku ecosystem — works with Claude Code, OpenCode, and Codex CLI.",
   "files": [
     "skills",
-    "agents"
+    "agents",
+    "personas",
+    "manifest.json"
   ],
   "license": "SEE LICENSE IN LICENSE"
 }