Pre-ship risk audit — security, breaking changes, scalability, dependency CVEs
Break features into phases with output to local files, Notion, or Linear
Explain a codebase or subsystem — architecture, patterns, history, and the "why"
Print a random motivational message
Route questions to Metis (project), Clio (git), or Mimir (external research)
Task manager — add, list, complete, and remove personal todos via kratos binary or fallback file
Architecture reviewer for technical soundness
Implementation specialist for writing code
QA specialist for test planning
PM specialist for PRD creation and requirements review
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Uses power 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.
Uses Bash, Write, or Edit tools
Uses Bash, Write, or Edit tools
npx claudepluginhub lizardliang/lizard-market --plugin kratosCode review plugin channeling Linus Torvalds - brutally honest, technically precise, zero fluff
Discord remote control for Claude Code — forwards tool permission requests, PreToolUse hooks, and AskUserQuestion hooks to Discord DMs. Approve or deny from your phone using emoji reactions.
Multi-project Discord orchestrator — routes channels to projects via Claude Agent SDK
Taiwan ETF / stock research, buy-sell decisions, and personal holdings tracking. Finds common holdings between ETFs (e.g. 0050 / 0052), recommends what to buy and why with an entry/exit plan from a live quote, records the trades you make, and reviews your holdings to suggest what to sell. Always fetches live data via agent-browser; never guesses or derives prices.
Build beautiful, interactive technical diagrams (system / architecture / sequence / flow) as a single self-contained HTML file — pure HTML, CSS, and vanilla JS, no build step. Tabbed multi-view, pan / zoom / drag, connected-chain highlight, double-click pin, dark mode (Tokyo Night), overlap auto-fix, and SVG / PNG export.
HelloAGENTS — The orchestration kernel that makes any AI CLI smarter. Adds intelligent routing, unified QA gates, safety guards, and notifications.
This skill should be used when the model's ROLE_TYPE is orchestrator and needs to delegate tasks to specialist sub-agents. Provides scientific delegation framework ensuring world-building context (WHERE, WHAT, WHY) while preserving agent autonomy in implementation decisions (HOW). Use when planning task delegation, structuring sub-agent prompts, or coordinating multi-agent workflows.
Autonomous, personalized research loops for Claude Code. Set a topic, walk away, come back to a quality-gated report adapted to your projects.
Multi-agent orchestration with AI SDK v5 - handoffs, routing, and coordination for any AI provider (OpenAI, Anthropic, Google)
Dynamically assemble expert agent teams for complex tasks using Claude Code's agent teams feature
18 universal AI skills for Claude Code — skill creation, deep research, strategic planning, content processing, solution architecture, and orchestration workflows