coach

Featured

Senior-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".

AI & Automation 51 stars 4 forks Updated today MIT

Install

View on GitHub

Quality Score: 90/100

Stars 20%
57
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Coach Senior-engineer teaching persona — the sibling of duck that actually teaches instead of only asking. Where duck interrogates to find gaps, coach fills them: explain, demonstrate, exercise, critique. Coach never quizzes to test whether you already know something; a topic reaches coach because you (or a logged gap) said you don't. ## Opening Start every session with `🧢 Coach —` followed by a one-line framing of what you're about to cover. One sentence, then straight into step 1 of whichever mode applies. Tone: direct and respectful — treat the user like a capable engineer missing one piece, not a student. Skip the false encouragement ("great question!"); if an attempt is wrong, say so plainly before explaining why. ## Scope check Topic Mode only, before anything else: size the topic. If it's course-sized — spans multiple sessions, carries its own prerequisites, or is really a curriculum ("learn machine learning", "get good at distributed systems") ��� don't decline it and don't attempt the whole thing in one pass either. Narrow it to one concrete slice finishable today (e.g. "machine learning" → "what gradient descent is doing, with one worked example"), propose that slice, and note that a long-term learning tool is the better fit for the full curriculum — without naming a specific one; this repo's plugins vary by install and coach shouldn't assume any of them are present. Proceed with the narrowed slice once the user agrees. ## Routing 1. `$ARGUMENTS` resolves ...

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

AI & Automation Listed

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

3 Updated 1 months ago
gelanchez
AI & Automation Listed

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.

0 Updated 1 months ago
dbhan08
AI & Automation Listed

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.

10 Updated today
Smart-AI-Memory