A robust, scalable Claude Code plugin providing a multi-agent development ecosystem with specialized agents, reusable skills, slash commands, and operational guardrails.
npx claudepluginhub oiranca/claude-dev-ecosystemFull analysis and improvement workflow for an existing repository. Runs stack detection, inventory, dependency audit, architecture review, targeted improvements, and QA.
Incremental migration workflow from React + Vite to Astro using islands architecture. Validates preconditions, inventories routes, plans architecture, migrates components in batches, and validates.
Workflow for a new or bootstrapped project with few source files. Runs stack detection, inventory, architecture planning, initial implementation, and QA.
Safe, behavior-preserving refactor workflow for a specific module or file set. Includes planning, scoped implementation, and validation.
Focused security audit workflow. Prioritizes sensitive surfaces first, avoids reproducing secrets, and returns a remediation-oriented report.
Parallel multi-agent code review workflow. Coordinates Security, Performance, and QA review lanes and produces a structured final report.
Cautious analysis workflow for an unclear technology stack. Requires human review before implementation proceeds.
Repo discovery agent. Produces a minimal scoped reading plan before execution agents perform broad reads. Reduces context consumption and cycle cost. Sends a handoff message with the plan when done.
Reviews infrastructure, build configuration, runtime environment, and deployment signals to ensure the project can run and be delivered reliably.
Executes framework, architecture, or tooling migrations based on defined migration plans and migration skills.
Responds to pull request comments by analyzing feedback, locating relevant code, and proposing or implementing fixes.
Team Lead and planner. Owns scope, milestone selection, and parallel agent coordination via the Task State Engine. Avoids becoming a bottleneck — delegates broadly and lets agents self-coordinate via tasks and messages.
Review agent. Claims validation tasks or responds to handoff messages from execution agents. Can approve, request changes, return to review, or mark blocked. Runs in parallel with security-reviewer.
Builds a structural inventory of the repository including directories, dependencies, scripts, tooling, and service surfaces.
Review agent. Claims security audit tasks or responds to review_request messages from execution agents. Runs in parallel with qa-engineer. Can approve, request changes, or escalate critical issues immediately.
Execution agent. Claims implementation tasks from the Task State Engine, implements the approved milestone with minimal changes, then sends a handoff message to the review agents.
Designs the minimal technical solution for the current issue and produces a milestone-based implementation plan.
Detects the project stack, framework, runtime, package manager, validation tooling, and repository shape using evidence-backed conclusions.
Maintains repository documentation by updating README, docs, and changelog based on validated changes.
Web accessibility patterns for WCAG 2.2 compliance including ARIA, keyboard navigation, screen readers, and testing
Detect likely drift between documented architecture and the current repository structure, file boundaries, and dependency patterns.
Run available lint, type-check, test, and build commands and report results before pull request creation.
Locate relevant code, definitions, usages, route handlers, and configuration references before reading or editing files.
Reduce unnecessary context usage by identifying the minimum relevant file set for the current task before any broad repository reads occur.
Audit project dependencies for known vulnerabilities and outdated packages using the repository's native package manager tooling.
Synchronize human-facing documentation such as README and CHANGELOG using existing agent-generated documentation as the source of truth.
Check whether environment variables are documented, referenced in code, and visible in deployment-related configuration.
Detect repository changes using a git-first fingerprint strategy and classify them as none, non-material, or material to control downstream agent execution.
Incrementally migrate React + Vite components to Astro using islands architecture while preserving behavior and deferring risky components.
Build or update a lightweight repository inventory covering directory structure, manifests, dependencies, scripts, tooling, and key configuration files.
Map application routes from framework routing conventions and configuration to produce a route inventory for web projects.
Run a lightweight regex-based scan for accidentally committed secrets, tokens, credentials, and unsafe secret hygiene signals.
Run lightweight end-to-end smoke checks against a running dev or preview server to catch critical route regressions.
Identify the repository technology stack using configuration and manifest files and produce a structured stack profile with evidence.
Run a focused subset of tests related to recently changed files to validate behavior quickly.
Semantic search for Claude Code conversations. Remember past discussions, decisions, and patterns.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.