mp-web3

mp-web3/claude-starter-kit

Agent Claude Code

Investigates and fixes bugs. Takes a symptom, reproduces it, identifies root cause, writes the fix and a regression test.

mp-web3/claude-starter-kit

Agent Claude Code

Reviews code changes for bugs, security issues, style violations, and test coverage gaps. Read-only — never modifies files.

mp-web3/claude-starter-kit

Agent Claude Code

Implements features from a plan or spec. Writes code in dependency order, runs tests, reports what was built. Does not make architectural decisions.

mp-web3/claude-starter-kit

Agent Claude Code

Explores codebases, reads docs, and searches the web to answer technical questions. Returns structured findings. Does not write code.

mp-web3/claude-starter-kit

Skill Claude Code

Bootstrap a new project with a proper .claude/ setup for agentic development. Use when: setting up a new codebase for Claude Code, user says "set up this project", "bootstrap", "add Claude to this repo", or when .claude/ is missing in a project. Creates CLAUDE.md, CODEBASE.md, docs/, knowledge/, and optionally skills…

mp-web3/claude-starter-kit

Skill Claude Code

Create a new Claude Code skill. Use when the user wants to build a new slash-command skill, extend Claude with a specialized workflow, or asks to create/add a skill. Handles scaffolding, SKILL.md authoring, and validation.

mp-web3/claude-starter-kit

Skill Claude Code needs its repo

Guided first-session setup. Walks the user through building their personal AI assistant — profile, 12 problems, goals, subgoals, and initial tasks. Run this in the first session after setup.

mp-web3/claude-starter-kit

Skill Claude Code

Structured workflow for planning and implementing new features, skills, scripts, or major changes. Use when the user asks to build something new, add a skill, create infrastructure, or make architectural changes. Guides through explore, plan, approve, implement, verify, update.

mp-web3/claude-starter-kit

Skill Claude Code

Analyze the current or recent session(s) for corrections, preferences, and implicit feedback. Extracts learnings and routes them to the right knowledge/rules file. Run when you want to capture what was learned this session.

mp-web3/claude-starter-kit

Skill Claude Code

Manage the task backlog — add, review, complete, and measure tasks against the 12 Favorite Problems. Run /tasks to see current status.