Agent Claude CodeOpenCode
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.
Agent Claude CodeOpenCode
Simplifies and refines code for clarity, consistency, and maintainability while preserving behavior. Focus on recently modified code unless instructed otherwise.
Agent Claude CodeOpenCode
Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.
Command Claude CodeOpenCode
Alias — find 10x product opportunities via the game-changing-features skill.
Command Claude CodeOpenCode
Read-only Q&A — answer the question, don't change anything.
Command Claude CodeOpenCode
Alias — lightweight brainstorm via superpowers:brainstorming (with overrides).
Command Claude CodeOpenCode
Alias — sharp code review via the code-reviewer agent.
Command Claude CodeOpenCode
Alias — systematic debugging via superpowers:systematic-debugging.
Command Claude CodeOpenCode
Alias — humanize text via the the-humanizer skill.
Command Claude CodeOpenCode
Alias — channel Steve Jobs via the steve-jobs-perspective skill.
Command Claude CodeOpenCode
Alias — learn any brand and generate a complete design system from it.
Command Claude CodeOpenCode
Alias — enforce precise, minimal design via the design skill.
Command Claude CodeOpenCode
Alias — refine a raw prompt via the prompt-optimizer skill.
Command Claude CodeOpenCode
Alias — security review via the security-reviewer agent.
Command Claude CodeOpenCode
Alias — apply baseline coding standards via the coding-standards skill.
Command Claude CodeOpenCode
Alias — simplify recently changed code via the code-simplifier agent.
Command Claude CodeOpenCode
Alias — UI/UX design intelligence via the design skill (ui-ux-pro-max).
Command Claude CodeOpenCode
Alias — audit UI quality across 8 dimensions and catch AI sameness.
Skill OpenCode
The shared coding floor — immutable defaults, files under 800 lines, functions under 50, error handling at every layer, named constants over magic numbers. Defer to framework-specific skills for stack patterns.
Skill OpenCode
Enforces precise, minimal design for dashboards and admin interfaces. Use when building SaaS UIs, data-heavy interfaces, or any product needing pixel-level discipline.
Skill OpenCode
Find 10x product opportunities and high-leverage improvements. Use when user wants strategic product thinking, mentions '10x', wants to find high-impact features, or says 'what would make this 10x better', 'product strategy', or 'what should we build next'.
Skill OpenCode
A prompt-editing guide that turns a vague request into a clearer, ready-to-use instruction.
Skill OpenCode
Self-educating humanizer skill that keeps up with the latest LinkedIn AI slop patterns. Auto-detects channel, scores the original, returns a humanized rewrite with the patterns it fixed listed. TRIGGER on "humanize", "sounds like AI", "AI detection", "make it sound human", "rewrite in my voice", "voice check", "blog…
Skill OpenCode
Audit UI quality across 8 dimensions and catch AI sameness. Scores design system compliance, visual hierarchy, spacing, contrast, typography, responsive, interactions, and accessibility. Returns a scorecard with priority-ordered fixes. TRIGGER on "vibe check", "UI audit", "design review", "does this look right"…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: