claude-init
01Plugin Claude Code
Plugin marketplace listing 1 plugin: claude-init.
Plugin Claude Code
Plugin marketplace listing 1 plugin: claude-init.
Plugin Claude Code
Make any repo AI-native. Analyzes your codebase and generates a complete Claude Code configuration — agents, skills, rules, and hooks tailored to your stack.
Skill Claude CodeCodex
Analyze any codebase and generate a complete .claude/ configuration to make it AI-native. Use when setting up Claude Code for a new or existing repo. Handles cold-start by detecting stack, framework, patterns, and generating tailored CLAUDE.md, agents, skills, rules, and hooks.
Skill Claude CodeCodex
Validate your .claude/ configuration. Checks that commands work, paths exist, hooks are valid, and agents are well-formed. Use after /claude-init or /update to catch issues.
Skill Claude CodeCodex
Quick onboarding to an existing codebase. Generates a mental model of the architecture, key patterns, and how things connect. Use when joining a new repo or when a teammate needs to get up to speed fast.
Skill Claude CodeCodex
Re-analyze a repo and update its existing .claude/ configuration. Detects stack changes, new dependencies, and config drift without overwriting customizations. Use when the codebase has evolved since initial /claude-init.
Instructions file
Instructions for yash-gadodia/claude-init, covering claude-init, what this does, usage, or load the repo as a plugin and then, in the target repo.
Agent
System design and architecture decisions. Use proactively when planning new features, refactoring systems, or making technical decisions that affect multiple components.
Agent
Senior developer for implementation work. Use when writing features, fixing bugs, or refactoring code. Follows project conventions and writes tests.
Agent
Infrastructure, CI/CD, and deployment specialist. Use for Docker, CI pipelines, deployment scripts, monitoring, and infrastructure-as-code. Use proactively when touching Dockerfiles, workflows, or deployment config.
Agent
QA and test specialist. Use when writing tests, verifying features, or checking test coverage. Knows the project's test framework and patterns.
Agent
Codebase researcher and documentation generator. Use for deep exploration, architecture mapping, understanding legacy code, or generating docs for an existing service.
Agent
Code review specialist. Use after writing or modifying code. Checks for bugs, security issues, convention violations, and unnecessary complexity.
Agent
Documentation and communication specialist. Use for READMEs, API docs, changelogs, PR descriptions, architecture docs, and onboarding guides.
Skill Claude CodeCodex
Turn vague requests into structured, testable specs through collaborative design. Auto-triggered when requirements are ambiguous. Explores intent, constraints, and alternatives before implementation. Also available as /clarify.
Skill Claude CodeCodex
Challenge a plan, design, or PR by finding every flaw, risk, and wrong assumption. Use before committing to an architecture or shipping a major change.
Skill Claude CodeCodex
Land completed work — verify tests, present options (merge/PR/keep/discard), execute chosen workflow. Auto-triggered after implementation and review pass. Also available as /finish.
Skill Claude CodeCodex
Create a detailed implementation plan with bite-sized tasks. Auto-triggered for non-trivial work. Includes design exploration, devil's advocate challenge, and subagent review. Also available as /plan.
Skill Claude CodeCodex
Two-stage code review: spec compliance first, then code quality. Auto-triggered after implementation. Also available as /review.
Skill Claude CodeCodex
Execute implementation plans using fresh subagents per task with two-stage review. Auto-triggered for plans with multiple independent tasks. Also available as /subagent-dev.
Skill Claude CodeCodex
Test-driven development — RED-GREEN-REFACTOR cycle. Auto-triggered during implementation. Write the test first, watch it fail, write minimal code to pass. Also available as /tdd.
Skill Claude CodeCodex
Verification before completion — no success claims without fresh evidence. Auto-triggered before any completion claim. Also available as /verify.