What are Claude Code Skills?

Claude Code Skills are reusable prompt templates stored as markdown files in your project's .claude/skills/ directory. They let you codify best practices and common workflows into slash commands that Claude follows consistently.

How do I create a Claude Code Skill?

Create a markdown file in .claude/skills/ with instructions for Claude. The filename becomes the command name — for example, .claude/skills/code-review.md can be invoked with /code-review during a Claude Code session.

Can I share skills with my team?

Yes. Skills stored in .claude/skills/ can be committed to version control so every team member has access to the same standardized workflows. You can also organize skills into subdirectories by category.

What is the difference between project and global skills?

Project skills (.claude/skills/) are specific to the current project and are committed to git. Global skills (~/.claude/skills/) are personal skills available across all your projects.

am2rican5

New

Community RegistryGeneralby am2rican5 · MIT

Personal Claude Code extensions â workflow automation, self-improvement, and session management

Community PluginView Source

Overview

Personal Claude Code extensions for workflow automation, spec-driven development, and session management.

![License: MIT](LICENSE)

About

A Claude Code plugin that adds skills and agents for automating development workflows. Skills provide structured guidance for tasks like writing specs, building other skills, and orchestrating parallel agents. Agents handle delegated work like code quality sweeps, performance optimization, and spec validation.

Installation

Option 1: Clone and load locally

bash

git clone https://github.com/am2rican5/cc-plugin.git
claude --plugin-dir ./cc-plugin

Option 2: Load from existing directory

bash

claude --plugin-dir /path/to/cc-plugin

Option 3: Marketplace (when published)

code

/plugin marketplace add am2rican5/cc-plugin

Skills

Skills are invoked with the /am2rican5:<skill-name> namespace.

Skill	Command	Description
sdd-workflow	`/am2rican5:sdd-workflow`	Orchestrates the full spec-driven development lifecycle: Specify, Plan, Implement, Validate
spec-writer	`/am2rican5:spec-writer`	Guides creation of functional specifications with Given/When/Then acceptance criteria
skill-builder	`/am2rican5:skill-builder`	Creates or updates skills following Anthropic's guide best practices with automated validation
self-improve	`/am2rican5:self-improve`	Analyzes usage reports and proposes targeted improvements to CLAUDE.md, hooks, and skills
parallel-agent-orchestration	`/am2rican5:parallel-agent-orchestration`	Teaches patterns for running multiple Claude agents in parallel on a shared codebase
test-driven-autonomous-dev	`/am2rican5:test-driven-autonomous-dev`	Guides design of test suites and feedback loops for autonomous agent workflows

Agents

Agents are auto-invoked by Claude based on task context, or manually via /agents.

Agent	Description
spec-planner	Translates functional specs into codebase-aware implementation plans with architecture decisions and task decomposition
spec-validator	Validates implementation against specs: checks acceptance criteria coverage, edge case handling, and spec drift
code-quality	Deduplication sweeps, naming consistency checks, dead code detection
perf-optimizer	Profile-change-benchmark optimization cycle (runs on Sonnet)
task-runner	Autonomous task execution with lock-file coordination

Usage Examples

Spec-driven development workflow

code

/am2rican5:sdd-workflow

Walks through four phases — Specify, Plan, Implement, Validate — with three rigor levels: spec-first (default), spec-anchored, and spec-as-source.

Write a functional specification

code

/am2rican5:spec-writer

Progressive detail elicitation that produces Given/When/Then acceptance criteria, edge case suggestions, and rigor level annotations.

Self-improve after running /insights

code

/am2rican5:self-improve

Reads your latest usage report, audits current CLAUDE.md/hooks/skills, and proposes grouped improvements.

Create a new skill

code

/am2rican5:skill-builder my-new-skill

Walks through frontmatter, instructions, examples, and troubleshooting, then validates with validate-skill.sh.

Design tests for autonomous agents

code

/am2rican5:test-driven-autonomous-dev

Helps you pick an oracle, design test tiers, create a fast subset, and structure error output for agent consumption.

Parallelize work across agents

code

/am2rican5:parallel-agent-orchestration

Assesses task decomposability, sets up locking, configures conflict avoidance strategy, and launches parallel agents.

Development

Skills follow Anthropic's skill-building guide best practices.

Validate a skill

bash

bash skills/skill-builder/scripts/validate-skill.sh skills/<skill-name>/SKILL.md

Structure

code

.claude-plugin/plugin.json          # Plugin manifest
skills/<name>/SKILL.md              # Skills (with optional references/ and scripts/)
agents/<name>.md                    # Agents

License

MIT

Install & Usage

Create the skills directory

mkdir -p .claude/skills

Download the skill file

mkdir -p .claude/skills && curl -o .claude/skills/am2rican5.md https://raw.githubusercontent.com/am2rican5/cc-plugin/main/SKILL.md

Invoke in Claude Code

/am2rican5

View source on GitHub

workflow-automationself-improvementparallel-agentstest-driven-developmentskill-builderclaude-code-plugin

Frequently Asked Questions

What is am2rican5?

Personal Claude Code extensions â workflow automation, self-improvement, and session management

How to install am2rican5?

To install am2rican5, create the .claude/skills directory in your project, then run the curl command to download the skill file. Once installed, invoke it in Claude Code with /am2rican5.

What is am2rican5 best for?

am2rican5 is a community categorized under General. It is designed for: workflow-automation, self-improvement, parallel-agents, test-driven-development, skill-builder, claude-code-plugin. Created by am2rican5.