Skip to content

basic readme and fixed some markdown linting errors #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
rhwas wants to merge 1 commit into
base: main
Choose a base branch
from
Open

basic readme and fixed some markdown linting errors #1

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 9 additions & 5 deletions CLAUDE.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@ A reusable library of DevOps agents and skills for Claude Code. Drop the `.claud
Agents are autonomous workers that handle complex, multi-step tasks. They run in isolated contexts and can use multiple skills.

| Agent | Purpose |
|-------|---------|
| ----- | ------- |
| `test-runner` | Runs tests, analyzes failures, suggests fixes |
| `pr-reviewer` | Reviews code changes, checks quality and security |
| `ci-cd-helper` | Debugs CI/CD pipeline issues |
Expand All @@ -32,6 +32,7 @@ Agents are autonomous workers that handle complex, multi-step tasks. They run in
### Using Agents

Agents are invoked via the Task tool with the agent name:

- "Run the test-runner agent to check all tests"
- "Use pr-reviewer to review my changes"
- "Use code-simplifier to simplify my recent changes"
Expand All @@ -51,7 +52,7 @@ Skills are inline capabilities that can be invoked directly or used by agents.
### Development Skills

| Skill | Purpose |
|-------|---------|
| ----- | ------- |
| `/run-tests` | Execute tests based on project type |
| `/analyze-coverage` | Analyze test coverage reports |
| `/lint-code` | Run linters based on project config |
Expand All @@ -68,7 +69,7 @@ Skills are inline capabilities that can be invoked directly or used by agents.
### Git/Release Skills

| Skill | Purpose |
|-------|---------|
| ----- | ------- |
| `/commit` | Create well-formatted commits |
| `/commit-push` | Commit and push to remote |
| `/review-changes` | Review staged/unstaged git changes |
Expand All @@ -95,7 +96,7 @@ When skills and agents need context, they use the **Explore** agent with a topic

Place CLAUDE.md files anywhere in your project to provide instructions:

```
```txt
project/
CLAUDE.md # Root - always read
src/
Expand All @@ -106,6 +107,7 @@ project/
```

CLAUDE.md files can contain:

- Coding conventions and patterns
- Testing requirements
- Security guidelines
Expand Down Expand Up @@ -137,6 +139,7 @@ CLAUDE.md files can contain:
## Language Support

All components are language-agnostic. They detect project type from:

- `package.json` (Node.js/JavaScript/TypeScript)
- `pyproject.toml`, `setup.py`, `requirements.txt` (Python)
- `go.mod` (Go)
Expand All @@ -148,7 +151,7 @@ All components are language-agnostic. They detect project type from:

## Directory Structure

```
```txt
.claude/
agents/
test-runner.md
Expand Down Expand Up @@ -194,6 +197,7 @@ All components are language-agnostic. They detect project type from:
**Plans and temporary files must NOT be saved in the project directory.**

When creating plans, improvement documents, or any temporary working files:

- Save to the user's `.claude` folder: `~/.claude/plans/` or `~/.claude/temp/`
- On Windows: `C:\Users\<username>\.claude\plans\`
- Never create a `.claude/plans/` folder in the project
Expand Down
81 changes: 81 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,81 @@
# Agent Library

A collection of reusable agents and skills for Claude Code and VSCode Copilot. Provides autonomous workers for complex tasks like testing, code review, CI/CD debugging, refactoring, and more.
Copy link

Copilot AI Feb 16, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The README refers to "VSCode Copilot", but the product name is typically "GitHub Copilot" (often used within "VS Code"). Consider rephrasing to avoid implying a separate product and to make the requirement unambiguous for readers.

Copilot uses AI. Check for mistakes.

## Quick Start

Symlink the folders to your project:

```bash
ln -s ~/AgentLibrary/.claude/agents ~/yourproject/.claude/agents
ln -s ~/AgentLibrary/.claude/skills ~/yourproject/.claude/skills
ln -s ~/AgentLibrary/.claude/rules ~/yourproject/.claude/rules
```
Comment on lines +7 to +13
Copy link

Copilot AI Feb 16, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The symlink commands will fail if the destination .claude/ directory doesn't already exist (e.g., ~/yourproject/.claude). Consider adding a preceding step/command to create the destination directory (or clarify that it must exist) so the Quick Start works when followed verbatim.

Copilot uses AI. Check for mistakes.

Or for a single folder:

```bash
ln -s ~/AgentLibrary/.claude ~/yourproject/.claude
```

Then in Claude Code or VSCode Copilot:

- Agents appear in the `/agents` menu
- Skills appear in the `/skills` menu
- Rules auto-load into context

## What's Included

**14 Agents** for autonomous multi-step work:

- `test-runner`, `pr-reviewer`, `code-architect`, `bug-fixer`, `feature-implementer`
- `release-manager`, `dependency-manager`, `project-setup`
- Plus specialized agents for CI/CD, code simplification, pattern evaluation, and more

**20+ Skills** for targeted capabilities:

- Development: test execution, linting, code analysis, test generation
- Git/Release: commit management, PR creation, release notes, advanced workflows
- Context: dependency management, environment validation, API documentation

## Usage

### Agents (Complex Multi-Step Tasks)

```text
"Use code-architect to review the architecture"
"Use bug-fixer to diagnose and fix [bug description]"
"Use feature-implementer to implement [feature description]"
```

### Skills (Quick Capabilities)

```text
/run-tests
/lint-code
/commit-push
/create-pr
```

## Context System

Add `CLAUDE.md` files to your project to provide instructions:

```text
yourproject/
CLAUDE.md # Root instructions (always read)
src/
CLAUDE.md # Feature-specific instructions
```

Instructions are discovered and applied automatically based on task context.

## Documentation

See [CLAUDE.md](./CLAUDE.md) for detailed agent/skill documentation, capabilities, and context system details.

## Requirements

- Claude Code or VSCode Copilot with Claude model
- Git repository in your project
Comment on lines +79 to +80
Copy link

Copilot AI Feb 16, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Same naming issue as earlier: "VSCode Copilot" is ambiguous/misleading compared to "GitHub Copilot" (in VS Code). Updating this phrasing would make the requirements clearer.

Copilot uses AI. Check for mistakes.
- Symlinks must point to the correct paths