giannimassi

Set up a team of AI agents to discuss any topic through facilitated conversation. Use this skill whenever the user wants to explore an idea with multiple perspectives, debate a decision, brainstorm solutions, get diverse viewpoints on a problem, weigh trade-offs, or have agents discuss something collaboratively. Triggers on: 'discuss', 'debate', 'let\'s think about', 'explore the idea of', 'what do you think about', 'pros and cons of', 'should we', 'help me decide', 'brainstorm with a team', 'roundtable', 'get multiple perspectives', 'multi-perspective analysis', or any request for structured group deliberation on a topic.

Recruit, cache, and reuse domain expert agent personas. Use this skill whenever you need a domain expert for a discussion, planning session, code review, or any task that benefits from specialized knowledge. Triggers on: 'recruit', 'find an expert', 'create an expert', 'domain expert', 'specialist', 'I need someone who knows', 'get me an expert on', 'who should review this', 'assemble a team', 'what experts do I need', or when another skill needs to assemble a team of experts. Also use when browsing or managing cached experts: 'list experts', 'show cached experts', 'search for an expert'.

Composable reasoning primitives for structured thinking. Use when facing a hard decision point, evaluating competing options, auditing assumptions, assessing risk, or any situation where "thinking harder" would help. Especially useful when injected into subagent prompts for implementation, review, or analysis tasks. Trigger on: thinking tools, reason through, think carefully, evaluate options, audit assumptions, pre-mortem, steelman, devil's advocate, red team, confidence check, decompose, or when dispatching agents that need structured reasoning.

Show a native macOS webview UI to the user and get structured input back. Use when an interactive macOS session needs human-in-the-loop for multi-field input, option selection from 5+ choices, approval with context, or content review — NOT for yes/no questions. Handles the full flow — spawning the webview, generating A2UI or HTML content, parsing the user's response. Triggers on "show UI", "ask user", "approval needed with context", "let me pick from these options", "fill in these fields", or any situation where a structured GUI materially beats asking in the terminal. Skip in CI/non-interactive environments.

Run a conversation retrospective — analyze what happened in this session, what worked, what didn't, and propose concrete improvements. Use when the user says "retro", "retrospective", "what happened in this session", "session review", "what did we do", "analyze this conversation", or when wrapping up a long session and wanting to capture lessons. Especially useful after using a skill you're developing — identifies what can be improved about the skill, rules, setup, or process.

Communication consultant for messages to a specific person — Slack, email, LinkedIn, PR or Linear comments, meeting prep. Use when drafting, reviewing, calibrating tone, picking register, or managing recipient profiles (look up, refresh stale). Triggers: 'draft a message to', 'reply to', 'help me respond', 'how do I tell/push back on X', 'is my draft for Y OK', 'calibrate', 'profile for', 'prep for 1:1 with', and any task where the recipient is a specific named person.