thinkkit

Strategic boardroom debate with AI advisors. Use this skill when the user wants to pressure-test a decision by having multiple AI-simulated business leaders debate it. Trigger on phrases like "boardroom", "get my advisors to debate", "strategic debate", "board of directors", "what would X think about", or any request to simulate multiple expert perspectives arguing about a decision. Also use when the user says "/thinkkit:boardroom".

CISO-perspective security review for enterprise adoption decisions. Use this skill when the user wants to evaluate a vendor, product, SaaS tool, open-source dependency, API service, internal proposal, or any technology decision from a security perspective. This covers both evaluating third-party suppliers AND pressure-testing your own approach through a CISO's eyes (e.g., "will this pass a CISO review?", "how will enterprise security teams react to this?"). Trigger on phrases like "ciso review", "security review", "vendor assessment", "should we adopt this", "is this safe to use", "evaluate this product", "supplier risk", "third-party risk", "will this pass security review", "pressure test this from a security perspective", or any request to apply CISO-level scrutiny. Also use when the user says "/thinkkit:ciso-review".

Convene an LLM council to pressure-test a question or decision. Use this skill when the user wants a fast, multi-perspective gut-check — several independent advisors answer the same question from different thinking lenses, critique each other's answers blind, and a chairman synthesizes a final call with clear next steps. Trigger on phrases like "council", "convene a council", "ask the council", "get a few perspectives on this", "what would different advisors say", "stress-test this decision", "I'm too close to this — give me other angles", or any request for a quick round of diverse opinions on a question. Based on Andrej Karpathy's LLM Council. Also use when the user says "/thinkkit:council". For a heavier, formal debate with named real-world advisors and shareable deliverables, use /thinkkit:boardroom instead.

Reverse-engineer any codebase into a reconstruction-grade specification — a document thorough enough that a fresh Claude Code session could rebuild a functionally equivalent repo from scratch using only the spec. Supports both initial creation and incremental updates (detects an existing spec and updates only what changed), and scales from small projects to large monorepos (triages repo size, asks the user about depth vs. breadth, and switches to a hierarchical multi-file spec under `SPECIFICATION/` when appropriate, with optional multi-session coverage). Use this skill whenever the user asks to "create a spec", "write a specification", "update the spec", "reverse-engineer this codebase", "create a blueprint", or says anything about producing or refreshing a document that captures everything needed to recreate a project. Also trigger when the user wants to "snapshot the architecture" or "write a technical spec for this repo". Note: this is different from map-the-repo, which generates a browsable wiki. This skill produces a reconstruction-grade specification.

Structured exploration and discovery through interviewing. Use this skill whenever the user wants to think through a problem, explore a topic in depth, investigate root causes, make a decision, do a postmortem, assess risks, analyze tradeoffs, or work through any situation where they hold domain knowledge and need help structuring their thinking. Trigger on phrases like "let's explore", "help me think through", "I need to figure out", "let's dig into", "what should I do about", or any open-ended problem where generating an answer prematurely would be worse than discovering the right framing first. Also use when the user says "/thinkkit:explore-with-me" or "/thinkkit:explore".