By oscarqjh
Full-lifecycle engineering skills for AI coding agents — orchestration chain from brainstorm to ship, with production-grade engineering standards at every step.
Check for plugin conflicts and suggest complementary MCP servers for your workflow
Execute the implementation plan using subagent-driven development
Systematic debugging — find root cause before attempting fixes
Break work into small verifiable tasks with acceptance criteria and dependency ordering
Request a five-axis code review — correctness, readability, architecture, security, performance
Senior architect that evaluates design decisions, coupling, dependency structure, and interface quality. Use when changes modify module boundaries, introduce abstractions, add public APIs, or restructure significant code.
Designs feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create/modify, component designs, data flows, and build sequences. Use when writing-plans needs deep codebase pattern analysis before task decomposition.
Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, understanding patterns and abstractions, and documenting dependencies to inform new development. Use when brainstorming needs to understand an existing codebase before designing, or when any skill needs deep codebase analysis.
Senior code reviewer that evaluates changes across five dimensions -- correctness, readability, architecture, security, and performance. Use for thorough code review before merge.
Supply chain security specialist that audits dependencies for vulnerabilities, license compliance, and maintenance health. Use before adding dependencies, before releases, or for periodic health checks.
Tests in real browsers. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data via Chrome DevTools MCP.
Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.
Executes multi-stream parallel feature development across isolated worktrees. Use when writing-plans detects 2+ independent work streams in the plan and the user chooses compound execution at the handoff.
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Executes bash commands
Hook triggers when Bash tool is used
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
No model invocation
Executes directly as bash, bypassing the AI model
No model invocation
Executes directly as bash, bypassing the AI model
One command. Full lifecycle. An opinionated Claude Code plugin that turns "I want to build X" into shipped code — with specs, plans, tests, reviews, and documentation along the way.
Just type /superthink and the plugin handles the rest.
/superthink I want to build a task management API
The agent brainstorms the design, writes the spec, plans the implementation, dispatches subagents to build it, runs code reviews, and prompts you when it's ready to ship. Every step follows production-grade engineering standards — TDD, 5-axis code review, STRIDE threat modeling, anti-rationalization tables that catch when the agent tries to cut corners.
# From marketplace
/plugin marketplace add oscarqjh/super-agent-skills
/plugin install super-agent-skills@oscarqjh-super-agent-skills
# Or load locally
git clone https://github.com/oscarqjh/super-agent-skills.git
claude --plugin-dir ./super-agent-skills
SSH errors? The marketplace clones via SSH. Either add your SSH key or run:
git config --global url."https://github.com/".insteadOf "[email protected]:"
Replaces both
superpowersandagent-skills. Do not install either alongside this plugin. Run/super-agent-skills:auditto check for conflicts.
| Environment | Guide |
|---|---|
| Claude Code | docs/claude-code-setup.md |
| Cursor | docs/cursor-setup.md |
| OpenCode | docs/opencode-setup.md |
| Gemini CLI | docs/gemini-cli-setup.md |
| Windsurf | docs/windsurf-setup.md |
| GitHub Copilot | docs/copilot-setup.md |
| Any agent | docs/getting-started.md |
/superthink classifies your intent and routes to the right workflow:
/superthink [what you want to do]
│
├── "build X" ──────── Full lifecycle chain (see below)
├── "fix X" ────────── Root-cause debugging (not guessing)
├── "review code" ──── 5-axis code review
├── "test X" ───────── TDD with spec-driven test generation
├── "simplify X" ──── Reduce complexity, preserve behavior
├── "ship it" ──────── Pre-merge checklist → merge/PR
└── "plan X" ───────── Task breakdown with dependency graphs
When you're building something new, the plugin runs the complete lifecycle:
① Brainstorming Ask questions, explore approaches, write design spec
│ + dispatches code-explorer agent for codebase context
│ + generates acceptance test skeletons
▼ + invokes threat-modeling if security-sensitive
② Writing Plans Break spec into bite-sized tasks with vertical slicing
│ + dispatches code-architect agent for design blueprint
│ + maps dependency graph, adds checkpoints
▼ + 3-option execution handoff (compound / subagent / inline)
③ Building Dispatch fresh subagent per task (TDD, incremental)
│ + domain skills auto-trigger: API, frontend, security...
│ + parallel dispatch for independent tasks (max 3)
▼ + spec compliance review + code quality review per task
④ Code Review 5-axis review with self-healing fix loop (3 rounds)
│ + architecture reviewer for design-significant changes
▼
⑤ You Choose "Wrap up" (commit + next task) OR "Ship it" (merge/PR)
Every step has anti-rationalization tables that catch shortcuts, and hooks that enforce handoffs. See Architecture for the complete process graph with all skills, agents, and hooks.
29 skills, 9 agent personas, 6 reference guides, 12 slash commands, 4 hook types.
Skills carry structured capability frontmatter (phase, produces, requires, companions, chainsTo) that auto-generates a routing index at session start — the agent knows valid next steps without hand-maintained routing tables.
See Architecture for the full inventory and how everything connects.
npx claudepluginhub p/oscarqjh-super-agent-skills-plugins-super-agent-skillsConsult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex and antigravity CLIs when installed) to get diverse perspectives on coding problems
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
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.
Complete developer toolkit for Claude Code
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Supergraph enforces a complete, evidence-based coding pipeline — scan → plan → TDD → fix → verify → review — grounded in real codebase analysis at every step. It combines AST dependency graphs, LSP-level code intelligence, and a structured skill chain so Claude never guesses about impact before making a change.