ask-me-about
Ask Me About
Interview the user about a topic to build a complete, shared mental model. Ask questions one at a time, or in small related clusters when they share context.
Your dual role: You are both an interviewer extracting knowledge and a critical thinker stress-testing it. Don't just collect answers — probe gaps, challenge assumptions, and surface contradictions. The hard questions are the valuable ones: they either confirm the user's thinking is solid or reveal where it needs more work.
Getting started
- Establish scope first — if the topic is broad ("ask me about our product"), ask what aspect matters most right now
- If the topic relates to the codebase, explore it to ground your questions in reality. If the topic is conceptual or not codebase-related, skip codebase exploration and focus entirely on questioning.
How to interview
- Start with the big picture — what is this, why does it matter, who is it for?
- Walk down each branch of the concept, resolving dependencies between decisions before moving on
- For each answer, consider:
- Does this conflict with something said earlier?
- What's the implicit assumption here — is it valid?
- What happens at the edges — scale, failure, misuse?
More from shhac/skills
image-to-svg
Convert raster images (photos, illustrations, AI-generated art) into high-quality SVG recreations. Breaks the image into isolated features, builds each as a standalone SVG layer, then composites them. Use when the user wants to recreate an image as SVG, create vector versions of artwork, or extract specific elements from images as scalable graphics.
89orchestrate-subagents
Activate orchestrator mode for complex multi-task work using subagents. Use when you need to coordinate multiple independent Task subagents to accomplish work while keeping the main context window clean.
65team-solve
Investigate and solve problems using a team of specialist agents. Use when facing complex, multi-faceted problems that benefit from parallel research and structured implementation.
27multi-review
Review code changes from multiple specialist perspectives in parallel. Use when you want a thorough review of a PR, branch, or set of changes covering security, performance, correctness, edge cases, and ripple effects. Spawns parallel reviewer agents that each focus on a different lens, then synthesizes into a unified review.
26competing-hypotheses
Debug problems by investigating multiple hypotheses in parallel. Use when you have a bug, unexpected behaviour, or mystery where the root cause is unclear. Spawns parallel investigator agents each pursuing a different theory, then compares evidence to identify the most likely cause and fix.
26sync-fork
Sync a forked repository with its upstream. Fetches both remotes, shows divergence, resets shared branches to upstream, re-merges local-only branches, cleans up branches already merged upstream, and pushes. Use when upstream has accepted PRs or moved ahead and you need to bring your fork in line.
21