agents-templated 1.2.3 → 1.2.5

package/README.md

@@ -122,7 +122,6 @@ your-project/
 ├── agent-docs/                      # 📚 Comprehensive documentation
 │   ├── AGENTS.md                   # AI assistant guide
 │   ├── ARCHITECTURE.md             # Project architecture & tech stack
-│   ├── AGENTS.MD                   # Agent delegation patterns
 │   └── README.md                   # Human-readable setup guide
 │
 ├── agents/                          # 🤖 AI Agent rules and skills
@@ -134,8 +133,9 @@ your-project/
 │   │   ├── database.mdc           # Database patterns
 │   │   └── style.mdc              # Code style guidelines
 │   └── skills/
-│       ├── web-design-guidelines/ # UI/UX patterns
-│       └── find-skills/           # Skill discovery
+│       ├── find-skills/           # Skill discovery helper
+│       ├── README.md              # Guide for creating custom skills
+│       └── [your-custom-skills]/  # Your project-specific skills
 │
 ├── .github/
 │   └── copilot-instructions.md    # GitHub Copilot config
@@ -224,15 +224,49 @@ Open your AI assistant and it will automatically load the appropriate config:
 - **Claude**: Reads `CLAUDE.md`
 - **Gemini**: Reads `GEMINI.md`
 
-### 3. Read the Documentation
+### 3. Create Custom Skills (Optional)
+
+Extend your AI agents with domain-specific skills for your project:
+
+```bash
+# View the skills guide
+cat agents/skills/README.md
+```
+
+Create a new skill folder in `agents/skills/`:
+
+```markdown
+agents/skills/my-custom-skill/SKILL.md
+---
+name: my-custom-skill
+description: Custom patterns for my project domain
+---
+
+# My Custom Skill
+
+Use this skill when working with [your domain].
+
+## Recommended Patterns
+
+- Pattern 1: Description
+- Pattern 2: Description
+
+## Example
+
+Code and examples...
+```
+
+Skills define *how to execute specific tasks*, complementing rules that define *how to behave*. See [agents/skills/README.md](agents/skills/README.md) for detailed guidance.
+
+### 4. Read the Documentation
 
 - **[AGENTS.md](AGENTS.md)** – AI assistant guide
 - **[agent-docs/ARCHITECTURE.md](agent-docs/ARCHITECTURE.md)** – Project architecture & tech stack guidance
-- **[AGENTS.md](AGENTS.md)** – AI assistant guide
+- **[agents/skills/README.md](agents/skills/README.md)** – Custom skills guide
 - **[agents/rules/security.mdc](agents/rules/security.mdc)** – Security patterns (CRITICAL)
 - **[agents/rules/testing.mdc](agents/rules/testing.mdc)** – Testing strategy
 
-### 4. Start Building
+### 5. Start Building
 
 Tell your AI assistant what to build:
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agents-templated",
-  "version": "1.2.3",
+  "version": "1.2.5",
   "description": "Technology-agnostic development template with multi-AI agent support (Cursor, Copilot, VSCode, Gemini), security-first patterns, and comprehensive testing guidelines",
   "main": "index.js",
   "bin": {

package/templates/.github/copilot-instructions.md

@@ -4,9 +4,9 @@ This project follows enterprise-grade, technology-agnostic development patterns.
 
 ## Quick Start
 
-- **AI Guide**: See `agent-docs/AI_INSTRUCTIONS.md` for comprehensive instructions
+- **AI Guide**: See `AGENTS.md` for comprehensive instructions
 - **Architecture**: See `agent-docs/ARCHITECTURE.md` for project guidelines
-- **Agent Patterns**: See `agent-docs/AGENTS.md` for delegation patterns
+- **Custom Skills**: See `agents/skills/` directory for domain-specific extensions
 - **Detailed Rules**: See `agents/rules/*.mdc` files
 
 ## Always Apply

package/templates/AGENTS.MD

@@ -6,6 +6,7 @@ This project follows enterprise-grade, technology-agnostic development patterns.
 
 - **`AGENTS.md`** - This file! AI instructions for working with AI assistants
 - **`agent-docs/ARCHITECTURE.md`** - Overall project guidelines, architecture principles, and technology stack selection
+- **`agents/skills/`** - Custom skills for domain-specific tasks in your project
 
 ## Detailed Rules (Reference When Relevant)
 
@@ -23,10 +24,11 @@ When implementing features, always check the relevant rule file:
 
 When implementing any feature:
 
-1. **Reference `agent-docs/ARCHITECTURE.md`** for overall architecture and technology stack guidance
-2. **Apply relevant rules** from `agents/rules/*.mdc` files based on the task
-3. **Always apply security patterns** from `agents/rules/security.mdc`
-4. **Always apply testing patterns** from `agents/rules/testing.mdc`
+1. **Check for custom skills**: Review `agents/skills/` for domain-specific guidance
+2. **Reference `agent-docs/ARCHITECTURE.md`** for overall architecture and technology stack guidance
+3. **Apply relevant rules** from `agents/rules/*.mdc` files based on the task
+4. **Always apply security patterns** from `agents/rules/security.mdc`
+5. **Always apply testing patterns** from `agents/rules/testing.mdc`
 
 ## Critical Rules (Always Apply)
 

package/templates/CLAUDE.md

@@ -6,7 +6,7 @@ This project uses enterprise-grade, technology-agnostic development patterns for
 
 - **AI Guide**: See `AGENTS.md` for comprehensive instructions
 - **Architecture**: See `agent-docs/ARCHITECTURE.md` for project guidelines
-- **AI Guide**: See `AGENTS.md` for AI assistant patterns
+- **Custom Skills**: See `agents/skills/` directory for domain-specific extensions
 - **Detailed Rules**: See `agents/rules/*.mdc` files
 
 ## Always Apply

package/templates/GEMINI.md

@@ -10,9 +10,9 @@ This project uses enterprise-grade, technology-agnostic development patterns for
 
 - **AI Guide**: See `AGENTS.md` for comprehensive instructions
 - **Architecture**: See `agent-docs/ARCHITECTURE.md` for project guidelines
-- **AI Guide**: See `AGENTS.md` for AI assistant patterns
+- **Custom Skills**: See `agents/skills/` directory for domain-specific extensions
 - **Detailed Rules**: See `agents/rules/*.mdc` files
-- **Available Skills**: See `agents/skills/` directory
+- **Available Skills**: Check `agents/skills/` for project-specific skills
 
 ## Core Development Patterns
 

package/templates/README.md

@@ -118,7 +118,6 @@ your-project/
 ├── agent-docs/                      # 📚 Comprehensive documentation
 │   ├── AGENTS.md                   # AI assistant guide
 │   ├── ARCHITECTURE.md             # Project architecture & tech stack
-│   ├── AGENTS.MD                   # Agent delegation patterns
 │   └── README.md                   # Human-readable setup guide
 │
 ├── agents/                          # 🤖 AI Agent rules and skills
@@ -130,8 +129,9 @@ your-project/
 │   │   ├── database.mdc           # Database patterns
 │   │   └── style.mdc              # Code style guidelines
 │   └── skills/
-│       ├── web-design-guidelines/ # UI/UX patterns
-│       └── find-skills/           # Skill discovery
+│       ├── find-skills/           # Skill discovery helper
+│       ├── README.md              # Guide for creating custom skills
+│       └── [your-custom-skills]/  # Your project-specific skills
 │
 ├── .github/
 │   └── copilot-instructions.md    # GitHub Copilot config
@@ -220,15 +220,49 @@ Open your AI assistant and it will automatically load the appropriate config:
 - **Claude**: Reads `CLAUDE.md`
 - **Gemini**: Reads `GEMINI.md`
 
-### 3. Read the Documentation
+### 3. Create Custom Skills (Optional)
+
+Extend your AI agents with domain-specific skills for your project:
+
+```bash
+# View the skills guide
+cat agents/skills/README.md
+```
+
+Create a new skill folder in `agents/skills/`:
+
+```markdown
+agents/skills/my-custom-skill/SKILL.md
+---
+name: my-custom-skill
+description: Custom patterns for my project domain
+---
+
+# My Custom Skill
+
+Use this skill when working with [your domain].
+
+## Recommended Patterns
+
+- Pattern 1: Description
+- Pattern 2: Description
+
+## Example
+
+Code and examples...
+```
+
+Skills define *how to execute specific tasks*, complementing rules that define *how to behave*. See [agents/skills/README.md](agents/skills/README.md) for detailed guidance.
+
+### 4. Read the Documentation
 
 - **[AGENTS.md](AGENTS.md)** – AI assistant guide
 - **[agent-docs/ARCHITECTURE.md](agent-docs/ARCHITECTURE.md)** – Project architecture & tech stack guidance
-- **[AGENTS.md](AGENTS.md)** – Working with AI assistants guide
+- **[agents/skills/README.md](agents/skills/README.md)** – Custom skills guide
 - **[agents/rules/security.mdc](agents/rules/security.mdc)** – Security patterns (CRITICAL)
 - **[agents/rules/testing.mdc](agents/rules/testing.mdc)** – Testing strategy
 
-### 4. Start Building
+### 5. Start Building
 
 Tell your AI assistant what to build:
 

package/templates/agent-docs/README.md

@@ -36,16 +36,43 @@ agents-templated list
 
 ## Rules and Skills
 
-- **Rules** (`agents/rules/*.mdc`): Markdown files with YAML frontmatter (`description`, `globs`, `alwaysApply`). AI agents use them to know when to apply each rule. Adapt the content to your stack.
-- **Skills** (`agents/skills/*/SKILL.md`): Extend agent capabilities (e.g. find-skills, web-design-guidelines). Each has a name, description, and when to use.
+- **Rules** (`agents/rules/*.mdc`): Define *how to behave* - patterns, principles, and standards for your team
+- **Skills** (`agents/skills/*/SKILL.md`): Define *how to execute specific tasks* - domain-specific workflows and specialized knowledge
+
+### Using Skills in Your AI Assistants
+
+Skills can be referenced in all AI configuration files:
+
+**In `.cursorrules` (Cursor IDE):**
+```
+When the user asks about [domain], use the [skill-name] skill from agents/skills/
+```
+
+**In `CLAUDE.md` (Claude):**
+```
+
+When working on [domain-specific task], reference the [skill-name] skill in agents/skills/[skill-name]/SKILL.md
+```
+
+**In `GEMINI.md` (Google Gemini):**
+```
+When working on [domain-specific task], reference the [skill-name] skill in agents/skills/[skill-name]/SKILL.md
+```
+
+**In `.github/copilot-instructions.md` (GitHub Copilot):**
+```
+When helping with [domain-specific task], reference the [skill-name] skill from agents/skills/[skill-name]/SKILL.md
+```
+
+All AI assistants support skill references. Create custom skills in `agents/skills/` to extend capabilities across your entire team.
 
 ## Getting Started
 
 1. Review AGENTS.md for AI assistance guidance
 2. Review ARCHITECTURE.md for overall project guidelines
-3. Review AGENTS.MD for agent patterns
-4. Adapt the rules to your specific technology stack
-5. Configure your AI assistant (Cursor, Copilot, Claude, Gemini)
+3. Adapt the rules to your specific technology stack
+4. Create custom skills in `agents/skills/` for your domain
+5. Configure your AI assistants (Cursor, Copilot, Claude, Gemini) to reference your skills
 
 ## Documentation
 

package/templates/agents/skills/README.md

@@ -0,0 +1,172 @@
+# Agent Skills
+
+This directory contains custom skills for your AI agents. Skills extend agent capabilities with specialized knowledge, workflows, and tools for specific domains.
+
+## What is a Skill?
+
+A **skill** is a reusable module that:
+- Defines domain-specific knowledge or workflows
+- Extends agent capabilities for specialized tasks
+- Can be shared across your project or published for others
+
+**Rules** define *how to behave*; **Skills** define *how to execute specific tasks*.
+
+## Getting Started
+
+### Finding Existing Skills
+
+Use the built-in `find-skills` skill to discover skills from the open ecosystem:
+
+```bash
+npx skills find [query]
+```
+
+Examples:
+- `npx skills find react testing`
+- `npx skills find deployment`
+- `npx skills find accessibility`
+
+Browse more at: https://skills.sh/
+
+### Creating a Custom Skill
+
+To create a new skill for your specific domain:
+
+1. **Create a new folder** in this directory:
+   ```
+   agents/skills/my-custom-skill/
+   ```
+
+2. **Create a SKILL.md file** with metadata and instructions:
+   ```markdown
+   ---
+   name: my-custom-skill
+   description: Brief description of what this skill does
+   ---
+
+   # My Custom Skill
+
+   Instructions and examples for using this skill...
+   ```
+
+3. **Reference it** in your agent documentation or `.cursorrules`
+
+### Skill Structure
+
+```
+agents/skills/
+├── find-skills/
+│   └── SKILL.md              # Meta-skill for discovering skills
+├── my-custom-skill/
+│   └── SKILL.md              # Your custom skill
+└── README.md                 # This file
+```
+
+## Best Practices
+
+1. **Keep skills focused** - Each skill should handle one domain or workflow
+2. **Document clearly** - Include examples and use cases in SKILL.md
+3. **Name descriptively** - Use kebab-case names that reflect the skill's purpose
+4. **Version your skills** - Include version info in the metadata
+5. **Test before sharing** - Ensure skills work as documented
+
+## Common Skill Categories
+
+Consider creating skills for:
+
+| Category        | Use Case                                 |
+| --------------- | ---------------------------------------- |
+| Web Development | Framework-specific patterns and guidelines |
+| Testing         | Testing strategies and examples          |
+| DevOps          | Deployment, CI/CD, infrastructure        |
+| Documentation   | Doc generation, README templates         |
+| Code Quality    | Code review, refactoring patterns        |
+| Design          | UI/UX, accessibility, design systems    |
+| Productivity    | Workflows, automation, git patterns      |
+
+## Using Skills in Your Project
+
+Skills can be referenced in all your AI assistant configuration files:
+
+### Cursor IDE (`.cursorrules`)
+```
+When the user asks about [domain], use the [skill-name] skill from agents/skills/[skill-name]/SKILL.md
+```
+
+### Claude (`CLAUDE.md`)
+```markdown
+## When Working on [Domain]
+
+Reference the [skill-name] skill in `agents/skills/[skill-name]/SKILL.md` for patterns and guidance.
+```
+
+### Google Gemini (`GEMINI.md`)
+```markdown
+## When Working on [Domain]
+
+Reference the [skill-name] skill in `agents/skills/[skill-name]/SKILL.md` for patterns and guidance.
+```
+
+### GitHub Copilot (`.github/copilot-instructions.md`)
+```markdown
+When helping with [domain-specific task], reference the [skill-name] skill from `agents/skills/[skill-name]/SKILL.md`
+```
+
+### Documentation (`AGENTS.md`)
+```markdown
+- When working with [domain], see the [skill-name] skill in `agents/skills/[skill-name]/SKILL.md`
+```
+
+**All AI assistants support skill references.** Keep your team aligned by linking to skill files across your configuration files.
+
+3. **Share with your team**:
+   - Commit to version control
+   - Document installation in your README
+
+## Example: Creating a Fastapi Skill
+
+```markdown
+---
+name: fastapi-patterns
+description: FastAPI development patterns and best practices for your projects
+---
+
+# FastAPI Patterns
+
+Use this skill when working with FastAPI projects.
+
+## Recommended Patterns
+
+### Request Validation
+- Use Pydantic models for all request bodies
+- Validate query parameters with proper typing
+
+### Error Handling
+- Return meaningful HTTP status codes
+- Document error responses in OpenAPI
+
+### Testing
+- Use TestClient for API testing
+- Mock external dependencies
+
+## Project Structure
+
+```
+src/
+├── api/
+│   ├── v1/
+│   │   ├── users/
+│   │   └── posts/
+│   └── dependencies.py
+├── models/
+├── schemas/
+├── database/
+└── main.py
+```
+```
+
+## Resources
+
+- [Skills Documentation](https://skills.sh/)
+- [Creating Skills Guide](https://skills.sh/docs/creating-skills)
+- [Browse Popular Skills](https://skills.sh/explore)

package/templates/agents/skills/web-design-guidelines/SKILL.md

@@ -1,39 +0,0 @@
----
-name: web-design-guidelines
-description: Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
-metadata:
-  author: vercel
-  version: "1.0.0"
-  argument-hint: <file-or-pattern>
----
-
-# Web Interface Guidelines
-
-Review files for compliance with Web Interface Guidelines.
-
-## How It Works
-
-1. Fetch the latest guidelines from the source URL below
-2. Read the specified files (or prompt user for files/pattern)
-3. Check against all rules in the fetched guidelines
-4. Output findings in the terse `file:line` format
-
-## Guidelines Source
-
-Fetch fresh guidelines before each review:
-
-```
-https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md
-```
-
-Use WebFetch to retrieve the latest rules. The fetched content contains all the rules and output format instructions.
-
-## Usage
-
-When a user provides a file or pattern argument:
-1. Fetch guidelines from the source URL above
-2. Read the specified files
-3. Apply all rules from the fetched guidelines
-4. Output findings using the format specified in the guidelines
-
-If no files specified, ask the user which files to review.