AGENT33-PUBLIC

Use this skill to generate well-branded interfaces and assets for AGENT-33, either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.

Scan code for security vulnerabilities and unsafe patterns with remediation guidance.

Review a code diff for correctness, logic errors, and style issues.

Propose targeted refactoring and readability improvements for reviewed code.

Diagnose and explain error messages with root cause analysis and actionable fix steps.

Assist with common git operations including branching, committing, and pull requests.

Lint source code using project-configured linters and auto-fix safe violations.

Run project tests and report results with failure diagnostics and fix suggestions.

Chunk a long document into sections and summarize each before synthesizing a full summary.

Extract the most important takeaways from a document as a prioritized list.

Generate a concise abstract suitable for academic or executive audiences.

Core concepts for goal-driven agents - architecture, node types (event_loop, function), tool discovery, and workflow overview. Use when starting agent development or need to understand agent fundamentals.

Complete workflow for building, implementing, and testing goal-driven agents. Orchestrates hive-* skills. Use when starting a new agent project, unsure which skill to use, or need end-to-end guidance.

Best practices, patterns, and examples for building goal-driven agents. Includes client-facing interaction, feedback edges, judge patterns, fan-out/fan-in, context management, and anti-patterns.

Iterative agent testing with session recovery. Execute, analyze, fix, resume from checkpoints. Use when testing an agent, debugging test failures, or verifying fixes without re-running from scratch.

Extract action items from a meeting transcript with owners and deadlines.

Identify and record key decisions made during a meeting with rationale and stakeholders.

Summarize a meeting transcript into structured, scannable meeting notes.

Guide users through official AGENT33 outcome packs with setup checks, plain-language expectations, and review-gated launch steps.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Ingest external repositories, research papers, and benchmarks using 40-agent swarms to analyze, adapt features, and improve current workflows.

Extract discrete, verifiable facts from web content with source citations.

Search the web for information on a topic and return ranked, cited results.

Synthesize multiple web search results into a coherent, source-cited summary.

Execute a Gold Standard documentation overhaul or normalize cross-links across the existing docs suite.

Review, test, lint, and prepare smart merges for all open and closed PRs, verifying features and documenting technical debt.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls. Now with automatic session recovery after /clear.