learn-while-building
Keeps the user learning while coding — research unfamiliar topics, explain decisions in plain language, surface trade-offs, and end phases with concise "what…
Skill by Vinayak-RZ
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/vinayak-rz-learn-while-building
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: research
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/learn-while-building
What's inside
- Skill name
learn-while-building- Description
- Keeps the user learning while coding — research unfamiliar topics, explain decisions in plain language, surface trade-offs, and end phases with concise "what you learned" summaries. Use when the user wants to understand what is being built, learn new concepts, get research-backed explanations, or stay in the loop during implementation.
- License
- Apache-2.0
- Instructions
- 98 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Learn While Building Pair with implementation — do not block shipping unless the user asks for teach-only mode. ## Modes | User signal | Mode | |-------------|------| | "Build it" / default | **Build + brief learn** — explain key decisions inline | | "Explain", "why", "help me understand" | **Explain** — deeper teaching, analogies | | "Research", "what are options", unfamiliar tech | **Research** — search/docs first, then recommend | | "Teach me", "I want to learn" | **Learn** — Feynman-style, check understanding | ## Research workflow Before adopting unfamiliar libraries, patterns, or APIs: 1. **Search** — web, official docs, MCP if relevant 2. **Summarize for the user** — 3–5 bullets: what it is, when to use, risks, alternatives 3. **Recommend** — one clear choice with trade-offs (see `trade-offs.mdc`) 4. **Wait for approval** if the choice changes architecture or adds dependencies Do not silently pick obscure stacks. Surface sources (doc links, not vague "best practice"). ## Explain while building When making non-obvious changes, include a short **Why this way** block: ```markdown **Why this way:** [one sentence] **Alternative considered:** [name] — rejected because [reason] **Concept:** [plain-language definition if new term introduced] ``` Keep explanations proportional — one paragraph, not a lecture, unless user asked to learn. ## Keep user in the loop - Restate objective at phase start - Flag decision points **before** irreversible choices (schema, auth model, major deps) - Report discoveries that change the plan — pause and re-confirm - End phases with status the user can skim in 30 seconds ## Phase learning summary (required) At the end of each completed phase (with `quality-gates.mdc`), add: ```markdown ### What you learned (this phase) - **Concept:** [term] — [one-line plain definition] - **Pattern:** [what we applied and where in the codebase] - **Trade-off:** [choice made and why] ### Optional check (if user is learning) Can you explain [one concept from this phase] in one sentence without jargon? ``` Append the same bullets to `LEARNING.md` at project root if the file exists; create it on first phase if user has asked to learn during this project. ## LEARNING.md shape (optional project file) ```markdown # Learning log ## Session / phase entries ### Phase N — [title] — [date] - Concepts: … - Files to study: `path/to/key/file` - Further reading: [link] ``` ## Feynman technique (when user wants deep learning) 1. User explains the concept in their own words (or agent asks them to after a build) 2. Agent identifies gaps — jargon, skipped steps, hand-waving 3. Agent fills gaps with analogy + pointer to code we just wrote 4. Optional: user re-explains; agent confirms or flags remaining holes Do not withhold answers indefinitely when the user is blocked — teach, then unblock. ## Anti-patterns - ❌ Implement first, explain never - ❌ Wall-of-text tutorials mid-implementation - ❌ Research without summarizing for the user - ❌ Assuming expert-level knowledge without checking - ❌ Sycophantic "great question!" without substance ## Companion rules & skills - `learn-and-research.mdc` — always-on lightweight behavior - `communication.mdc` — decision and risk reporting - `planning.mdc` — approval before non-trivial work - `readme` / `readable-readme` — document what was built for future-you - `extensive-readme` — package-by-package internals when the dump is needed
From Vinayak-RZ/ARC, Apache-2.0.
More from Vinayak-RZ/ARC
- 0.563score
graphify
Vinayak-RZ
Turn a folder into a knowledge graph (HTML, JSON, GRAPH_REPORT.md).
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
agentic-system-design
Vinayak-RZ
Guides architecture for AI agent systems — tool use, memory, RAG, orchestration, guardrails, evals, and cost/latency trade-offs.
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
frontend-architecture
Vinayak-RZ
Guides frontend architecture decisions for React, Next.js, and modern SPAs — component boundaries, state, data fetching, rendering strategy, and design-system…
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
backend-architecture
Vinayak-RZ
Guides backend and API architecture — service layers, REST/GraphQL design, databases, caching, async jobs, and scalability trade-offs.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
extensive-readme
Vinayak-RZ
Authors a separate internals companion: how the repo runs, domain concepts, then every first-party package and why important files exist.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
graph-engineering
Vinayak-RZ
Builds a graph-of-plans for end-to-end one-shots: research then questions (must ask; do not guess), then a master graph covering docs-in, architecture…
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
copywriting
Vinayak-RZ
Writes and audits public copy others will see: product READMEs, landing pages, headlines, CTAs, marketing pages, and other shipped prose.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
graph-of-loops
Vinayak-RZ
Full product one-shot as a graph of loops: ask every product and technical question first, lock users/P0/non-goals, architecture ADRs, then execute build…
SkillBFreshness: B★ 2Claude Code +9 - 0.537score
gsap-framer-scroll-animation
Utkarsh Patrikar
Use this skill whenever the user wants to build scroll animations, scroll effects, parallax, scroll-triggered reveals, pinned sections, horizontal scroll…
SkillBFreshness: B★ 2Claude Code +9 - 0.533score
impeccable
Vinayak-RZ
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or…
SkillBFreshness: B★ 2Claude Code +9 - 0.532score
find-skills
Vinayak-RZ
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
SkillBFreshness: B★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Sep 7, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/Vinayak-RZ/ARC
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Vinayak-RZ
- 0.563score
graphify
Vinayak-RZ
Turn a folder into a knowledge graph (HTML, JSON, GRAPH_REPORT.md).
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
agentic-system-design
Vinayak-RZ
Guides architecture for AI agent systems — tool use, memory, RAG, orchestration, guardrails, evals, and cost/latency trade-offs.
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
frontend-architecture
Vinayak-RZ
Guides frontend architecture decisions for React, Next.js, and modern SPAs — component boundaries, state, data fetching, rendering strategy, and design-system…
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
backend-architecture
Vinayak-RZ
Guides backend and API architecture — service layers, REST/GraphQL design, databases, caching, async jobs, and scalability trade-offs.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
copywriting
Vinayak-RZ
Writes and audits public copy others will see: product READMEs, landing pages, headlines, CTAs, marketing pages, and other shipped prose.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
graph-engineering
Vinayak-RZ
Builds a graph-of-plans for end-to-end one-shots: research then questions (must ask; do not guess), then a master graph covering docs-in, architecture…
SkillBFreshness: B★ 2Claude Code +9
Cite this page
learn-while-building skill. Agent Mart. https://agentmart.dev/skills/vinayak-rz-learn-while-building (last updated 2026-10-24)