Claude Skills Marketplace
A curated marketplace of Claude Code plugins for software engineering workflows.
Repository Structure
claude-skills-marketplace/
├── .claude-plugin/
│ └── marketplace.json # Marketplace manifest
├── execution-runtime/ # 🚀 Code execution environment (NEW!)
│ ├── api/ # Importable API library
│ ├── mcp-server/ # FastMCP server
│ ├── setup.sh # One-command installation
│ └── README.md
├── engineering-workflow-plugin/ # Engineering workflow plugin
│ ├── .claude-plugin/
│ │ └── plugin.json # Plugin manifest
│ ├── agents/
│ │ └── plan-implementer.md # Plan implementation agent
│ ├── skills/
│ │ ├── feature-planning/ # Feature planning skill
│ │ ├── git-pushing/ # Git automation skill
│ │ ├── review-implementing/ # Code review skill
│ │ └── test-fixing/ # Test fixing skill
│ └── README.md
├── visual-documentation-plugin/ # Visual documentation plugin
│ ├── .claude-plugin/
│ │ └── plugin.json # Plugin manifest
│ ├── skills/
│ │ ├── architecture-diagram-creator/ # Architecture diagram skill
│ │ ├── dashboard-creator/ # Dashboard creation skill
│ │ ├── flowchart-creator/ # Flowchart creation skill
│ │ ├── technical-doc-creator/ # Technical documentation skill
│ │ └── timeline-creator/ # Timeline creation skill
│ ├── EXAMPLES.md
│ └── README.md
├── productivity-skills-plugin/ # Productivity & optimization plugin
│ ├── .claude-plugin/
│ │ └── plugin.json # Plugin manifest
│ ├── skills/
│ │ ├── code-auditor/ # Code auditing skill
│ │ ├── codebase-documenter/ # Codebase documentation skill
│ │ ├── conversation-analyzer/ # Usage analysis skill
│ │ └── project-bootstrapper/ # Project setup skill
│ └── README.md
├── code-operations-plugin/ # Code manipulation plugin
│ ├── .claude-plugin/
│ │ └── plugin.json # Plugin manifest
│ ├── skills/
│ │ ├── code-execution/ # 🚀 Python execution skill (NEW!)
│ │ │ └── examples/ # Example scripts
│ │ ├── code-transfer/ # Code transfer skill
│ │ │ └── scripts/
│ │ │ └── line_insert.py # Line-based insertion script
│ │ ├── code-refactor/ # Bulk refactoring skill
│ │ └── file-operations/ # File analysis skill
│ └── README.md
├── LICENSE
└── README.md
What are Skills and Agents?
Skills are model-invoked capabilities that extend Claude Code's functionality. Unlike slash commands that require explicit user activation, Skills are automatically triggered by Claude based on context and the Skill's description.
Each Skill consists of a SKILL.md file with:
- YAML frontmatter (name, description, metadata)
- Detailed instructions for Claude
- Optional supporting files (scripts, templates, references)
Agents are specialized Claude instances that can be invoked by Claude to handle specific types of work. They run independently with their own context and can use different models optimized for their task.
Each Agent consists of an AGENT.md file with:
- YAML frontmatter (name, description, model selection)
- Specialized instructions and constraints
- Decision-making frameworks for their domain
Skills and Agents work together: Skills can orchestrate when to invoke Agents, and Agents can use Skills while executing their tasks.
🚀 NEW: Execution Runtime (90%+ Token Savings)
The marketplace now includes a code execution environment implementing the Anthropic code execution pattern. Instead of loading code through context, Claude executes Python locally with API access—achieving 90-99% token reduction for bulk operations.
Quick Benefits
✅ Massive token savings: Process 100 files with 1K tokens instead of 100K ✅ Faster operations: Local execution vs multiple API round-trips ✅ Stateful workflows: Resume multi-step refactoring across sessions ✅ Auto-secure: PII/secret masking, sandboxed execution
Setup (2 minutes)
# After installing marketplace plugin
~/.claude/plugins/marketplaces/mhattingpete-claude-skills/execution-runtime/setup.sh
When It Activates
Skills automatically use execution mode for:
- Bulk operations (10+ files)
- Complex multi-step workflows
- Iterative processing
- Codebase-wide analysis
Example: "Rename getUserData to fetchUserData in all Python files"
- Without execution: ~25,000 tokens (read/edit 50 files)
- With execution: ~600 tokens (script + summary) - 97.6% savings
Installation
Install from Marketplace
# In Claude Code - installs the entire plugin with all skills and agents
/plugin marketplace add mhattingpete/claude-skills-marketplace
This installs the engineering-workflow-plugin which includes all skills and the plan-implementer agent.
To install individual plugins:
# Install only engineering workflows
/plugin marketplace add mhattingpete/claude-skills-marketplace/engineering-workflow-plugin
# Install only visual documentation
/plugin marketplace add mhattingpete/claude-skills-marketplace/visual-documentation-plugin
# Install only productivity skills
/plugin marketplace add mhattingpete/claude-skills-marketplace/productivity-skills-plugin
# Install only code operations
/plugin marketplace add mhattingpete/claude-skills-marketplace/code-operations-plugin
Available Plugins
Engineering Workflow Plugin
Skills for common software engineering workflows including git operations, test fixing, code review implementation, and feature planning.
Visual Documentation Plugin
Skills for creating stunning visual HTML documentation with modern UI design, SVG diagrams, flowcharts, dashboards, timelines, and comprehensive project architecture diagrams.
Productivity Skills Plugin
Productivity and workflow optimization skills for analyzing usage patterns, auditing code quality, bootstrapping projects, and generating comprehensive documentation.
Code Operations Plugin
High-precision code manipulation operations including line-based insertion, bulk refactoring, and file analysis. Converted from code-copy-mcp to native Claude Code skills.
Available Skills
Feature Development
feature-planning
Break down feature requests into detailed, implementable plans with clear tasks that can be executed by the plan-implementer agent.
Activates when: User requests a new feature, enhancement, or complex change requiring planning.
Example usage:
- "Add user authentication"
- "Build a dashboard for analytics"
- "Plan how to implement export functionality"
Works with: plan-implementer agent for execution
Git & Version Control
git-pushing
Automatically stage, commit with conventional commit messages, and push changes to remote.
Activates when: User mentions pushing changes, committing work, or saving to remote.
Example usage:
- "Push these changes"
- "Commit and push to github"
- "Let's save this work"
Testing & Quality
test-fixing
Systematically identify and fix failing tests using smart error grouping strategies.
Activates when: User reports test failures, asks to fix tests, or wants test suite passing.
Example usage:
- "Fix the failing tests"
- "Make the test suite green"
- "Tests are broken after my refactor"
Code Review
review-implementing
Process and implement code review feedback systematically with todo tracking.
Activates when: User provides reviewer comments, PR feedback, or asks to address review notes.
Example usage:
- "Implement this review feedback: [paste comments]"
- "Address these PR comments"
- "The reviewer suggested these changes"
Code Operations
code-execution 🆕
Execute Python code locally with marketplace API access for 90%+ token savings on bulk operations.
Activates when: Bulk operations (10+ files), complex workflows, codebase-wide transformations, performance needs.
Example usage:
- "Refactor 50 files to use new API"
- "Extract all utility functions to separate files"
- "Audit code quality across entire codebase"
Token savings: 97-99% for bulk operations (25K → 600 tokens)
code-transfer
Transfer code between files with line-based precision. Auto-uses execution mode for 10+ file operations.
Activates when: User requests copying code between files, moving functions/classes, extracting code, or inserting at specific line numbers.
Example usage:
- "Copy the authenticate function from auth.py to utils.py"
- "Move this class to a separate file"
- "Extract this function to a new file"
- "Insert this code at line 45"
Key feature: Includes Python script for precise line-number-based insertion where Edit tool's string matching isn't