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.

agent-foreman

New

248Community RegistryGeneralby Lukin · MIT

Long Task Harness providing external memory, feature-driven workflow, and clean agent handoffs

Community PluginView Source

Overview

⚠️ DEPRECATED: This project is no longer maintained. Please migrate to ralph-dev - a simplified and improved version.

🚨 Migration Notice

This project has been deprecated due to its complexity. A new, simplified version is now available:

👉 [https://github.com/mylukin/ralph-dev](https://github.com/mylukin/ralph-dev)

Please migrate to ralph-dev for continued support and updates.

<details> <summary>Legacy Documentation (archived)</summary>

Stop AI agents from half-building features. Ship complete code in one session.

![npm version](https://www.npmjs.com/package/agent-foreman) ![License: MIT](https://opensource.org/licenses/MIT)

Problem

AI coding agents face three common failure modes:

Doing too much at once - Trying to complete everything in one session
Premature completion - Declaring victory before features actually work
Superficial testing - Not thoroughly validating implementations

Solution

agent-foreman provides a structured harness that enables AI agents to:

•Maintain external memory via structured files
•Work on one feature at a time with clear acceptance criteria
•Hand off cleanly between sessions via progress logs
•Track impact of changes on other features

Quick Start

bash

/plugin install agent-foreman        # 1. Install
/agent-foreman:init Build auth API   # 2. Initialize
/agent-foreman:run                   # 3. Let AI work

Installation

bash

# Quick install (binary)
curl -fsSL https://raw.githubusercontent.com/mylukin/agent-foreman/main/scripts/install.sh | bash

# Via npm
npm install -g agent-foreman

# Or use npx directly
npx agent-foreman --help

Manual download: GitHub Releases

Usage

Plugin Commands (Recommended)

code

/plugin marketplace add mylukin/agent-foreman
/plugin install agent-foreman

Command	Description
`/agent-foreman:status`	View project status and progress
`/agent-foreman:init`	Initialize harness with project goal
`/agent-foreman:analyze`	Analyze existing project structure
`/agent-foreman:spec`	Transform requirements into tasks
`/agent-foreman:next`	Get next priority task
`/agent-foreman:run`	Auto-complete all pending tasks

Transform requirements into tasks:

code

/agent-foreman:spec Build a user authentication system

code

Requirement → [PM→UX→Tech→QA] → Spec Files → BREAKDOWN Tasks → /run → Implementation

<details> <summary>CLI Commands (standalone)</summary>

For standalone CLI usage without Claude Code:

Command	Description
`init [goal]`	Initialize or upgrade the harness
`next [feature_id]`	Show next feature to work on
`status`	Show current project status
`check [feature_id]`	Verify code changes or task completion
`done <feature_id>`	Verify, mark complete, and auto-commit
`fail <feature_id>`	Mark a task as failed
`impact <feature_id>`	Analyze impact of changes
`tdd [mode]`	View or set TDD mode
`agents`	Show available AI agents
`install`	Install Claude Code plugin
`uninstall`	Uninstall Claude Code plugin

</details>

Workflow

code

next → implement → check → done → repeat

Step	Command	What Happens
1	`next`	Get task with acceptance criteria
2	implement	Write code to satisfy criteria
3	`check`	Verify implementation
4	`done`	Mark complete, auto-commit

Best Practices

One feature at a time - Complete before switching
Update status promptly - Mark passing when criteria met
Review impact - Run impact analysis after changes
Clean commits - One feature = one atomic commit
Read first - Always check feature list and progress log

Reference

<details> <summary>Core Files</summary>

File	Purpose
`ai/tasks/index.json`	Task index with status summary
`ai/tasks/{module}/{id}.md`	Individual task definitions
`ai/progress.log`	Session handoff audit log
`ai/init.sh`	Environment bootstrap script
`CLAUDE.md`	AI agent instructions

</details>

<details> <summary>Status Values</summary>

Status	Meaning
`failing`	Not yet implemented
`passing`	Acceptance criteria met
`blocked`	External dependency blocking
`needs_review`	May be affected by changes
`failed`	Verification failed
`deprecated`	No longer needed

</details>

<details> <summary>Why It Works</summary>

AI agents need the same tooling that makes human teams effective:

Human Practice	AI Equivalent
Scrum board	`ai/tasks/index.json`
Sprint notes	`progress.log`
CI/CD pipeline	`init.sh check`
Code review	Acceptance criteria

</details>

License

MIT

Author

Lukin (@mylukin)

Inspired by Anthropic's blog post: Effective harnesses for long-running agents

</details>

Install & Usage

Create the skills directory

mkdir -p .claude/skills

Download the skill file

mkdir -p .claude/skills && curl -o .claude/skills/agent-foreman.md https://raw.githubusercontent.com/mylukin/agent-foreman/main/SKILL.md

Invoke in Claude Code

/agent-foreman

View source on GitHub

agentlong-taskharnessfeature-drivenagent-memoryhandoffai-agentclaude-code

Frequently Asked Questions

What is agent-foreman?

Long Task Harness providing external memory, feature-driven workflow, and clean agent handoffs

How to install agent-foreman?

To install agent-foreman, 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 /agent-foreman.

What is agent-foreman best for?

agent-foreman is a community categorized under General. It is designed for: agent, long-task, harness, feature-driven, agent-memory, handoff, ai-agent, claude-code. Created by Lukin.