coach
FeaturedSenior-engineer coaching session: explains a topic in plain language with one concrete analogy then walks example → exercise → critique; or dissects code just generated in this session section-by-section (what it does / why this way over the obvious alternative / where it breaks first in prod); or surfaces an unresolved gap from a past duck session and teaches it. Manual-invocation only — call with /coach <topic>, /coach <file>, or /coach alone, e.g. "/coach embeddings" or "/coach src/foo.ts".
Install
Quality Score: 90/100
Skill Content
Details
- Author
- LeeJuOh
- Repository
- LeeJuOh/claude-code-zero
- Created
- 7 months ago
- Last Updated
- today
- Language
- JavaScript
- License
- MIT
Integrates with
Bundled in these plugins
Similar Skills
Semantically similar based on skill content — not just same category
coach
Programming mentor with four selectable modes — hardcore (pure Socratic, zero code from the AI), standard (Socratic + pseudo-code/generic examples), architect (AI writes boilerplate, user writes core logic), pair (AI writes the real, complete solution directly, no coaching gate, logs a Learning Log entry only when something genuinely worth remembering comes up) — plus an optional fun or dictator tone overlay that changes delivery style only. Each mode supports a user-requested override for one-off items the user wants done directly instead of coached. Also supports /coach study, which quizzes the user on entries from their own accumulated Learning Log instead of teaching something new. Use this skill whenever the user invokes /coach, says they're stuck on a bug, asks you to explain/teach/walk them through a concept, wants to learn instead of just get an answer, asks for a review/mentor/second opinion on their own code, wants the AI to just write the code without the mentoring overhead but still track real ins
sd-coach
Personal system design interview coach with five modes — coach (teacher walks you through a scenario with model answers and proactive concept teaching), mock (45-min in-character interview sim, no teaching), tutor (Socratic walkthrough, interruptible), drill (rapid 5-rep practice on capacity, inference-capacity, single-component, or failure-mode tracks), and teach (concept Q&A like "explain Kafka" or "compare Kinesis vs SQS"). Calibrated for FAANG L3–L5 SWE roles (SDE1 through senior). Question banks cover product/web, data & streaming, platform/infra, and the ML/LLM inference stack (serving, RAG, feature stores, model rollout). Companies seeded — Netflix, Google, Meta, Nuro; any other company works via JD-derived calibration or FAANG-generic defaults. Maintains a personal concept wiki at concepts/. Use when the user wants to practice or learn system design, or pastes a JD, interview question, role description, or freeform system design prompt.
coach
Progressive help for any topic. Repeat to go deeper: concept -> procedural -> reference. Triggers on: coach, learn, explain, teach me, tell me more, how does, what is, go deeper.