swe-interview-coach

Graded 45-minute system-design mock interview. You draw your architecture on the local Excalidraw canvas while a realistic interviewer probes what you draw, calls time, and throws one curveball; afterward it scores a 6-axis rubric, writes coach notes, and annotates your diagram with critique. Falls back to prose when the canvas can't start.

Untimed guided coding practice: you write code in a seeded solution file in your own editor; a warm interviewer hints via a ladder, runs your code, and teaches inline. Summarized, not scored.

Guided, untimed system-design practice. The interviewer is a scribe — sketches your described architecture live on the local Excalidraw canvas while you talk, gives hints freely, throws no curveballs. Ends with a coverage summary (not a score). Falls back to prose-only when the canvas can't start.

Add a new canonical STAR story to the behavioral story bank. Two modes — cold (you describe an experience from scratch) and CV-grounded (you point at a PDF resume; Claude reads it, suggests candidates, probes the one you pick).

Migrate a legacy STAR-stories markdown file into one or more canonical story files in behavioral/stories/. Use once per legacy file; not part of the regular prep loop.

Realistic behavioral interviewer persona for mock interviews. Asks 5-7 questions over ~35-45 minutes, mixes classic + company-specific, follows up like a real interviewer, pushes back on vagueness. Use only when running /mock-behavioral.

Conducts STAR-extraction interviews to capture a single canonical story from the user's experience. Two modes: cold (no context) and CV-grounded (reads a PDF resume, lists candidate experiences, probes the user's pick). Returns a draft canonical-story markdown blob for the main session to write. Use only when running /story-add.

Loaded by /mock-coding and /practice-coding; the main session reads this file and embodies it for the interview portion of the conversation. Not a spawnable subagent.

Loaded by /mock-sysdesign and /practice-sysdesign; the main session reads this file and embodies it for the interview portion of the conversation. Not a spawnable subagent.

Reference frameworks (STAR, SBI, CARL), anti-patterns, and standard interviewer follow-ups for behavioral interview prep. Use when extracting STAR stories from user's experience, mapping stories to a specific company or JD, running mock behavioral interviews, rehearsing behavioral story delivery, or debriefing a real behavioral interview.

Reference frameworks for coding interviews — the UMPIRE method, a pattern taxonomy (two-pointers, sliding-window, BFS/DFS, backtracking, dynamic-programming, graphs, and more), a Big-O cheatsheet, Python idioms, communication guidance, and anti-patterns. Used by the coding commands (/coding-explain, /practice-coding, /mock-coding, /coding-drill, /debrief-coding) to ground teaching and scoring; not read aloud verbatim.

Reference frameworks (RESHADED, the 4S shorthand), capacity estimation cheatsheet, core building blocks (load balancing, caching, queues, sharding, replication, CAP), common tradeoffs, and anti-patterns for system design interview prep. Use when running /mock-sysdesign, /practice-sysdesign, /sysdesign-explain, or /debrief-sysdesign, or whenever discussing architecture, capacity estimation, or design tradeoffs.