Level 2 — Daily Workflow

Cost-effective usage, Git mastery, CLAUDE.md, and tech-stack workflows

Node.js / Express / Lambda Vue 3 React Native QA

Use to reveal tips • to go back • next slide • previous slide

Level 2 — Daily Workflow

Saving Your Usage Limit — The DOs

10 practices that will stretch your token budget dramatically.

1. Be specific upfront: "Add a GET /users/:id/orders endpoint to src/routes/users.ts that returns paginated results using the existing OrderService" beats "add an endpoint for orders."
2. Use /clear between tasks: Switching from a bug fix to a feature? Clear the context. Old context bloats every subsequent message.
3. Use /compact when context grows: /compact keep the API schema and test results — tells Claude what matters. Reduces context by 50-70%.
4. Default to Sonnet: Sonnet handles ~80% of tasks. Use /model opus only for deep architectural analysis, complex debugging, or large refactors.
5. Reference files, don't paste them: Say "read src/services/auth.js and fix the token refresh bug" instead of pasting 200 lines into the chat.
6. Use Plan Mode for big tasks: Shift+Tab → plan → review → execute. Avoids costly trial-and-error on complex changes.
7. Set /effort appropriately: /effort low for simple renames, formatting. /effort high for security reviews, architecture. Match effort to task complexity.
8. One-shot for quick questions: claude -p "what does the --strict flag do in tsc?" — no session overhead, instant answer, minimal tokens.
9. Use CLAUDE.md effectively: Project conventions in CLAUDE.md = Claude stops asking "which style guide?" every session. Saves rounds of clarification.
10. Scope your requests: "Fix the null check in processOrder() at line 42" is cheaper than "there's a bug somewhere in the order processing."
Level 2 — Daily Workflow

Saving Your Usage Limit — The DON'Ts

10 anti-patterns that silently burn through your allocation.

1. Don't have marathon sessions: After 30+ exchanges, Claude carries massive context overhead. Start fresh sessions for new tasks.
2. Don't paste entire files: "Here's my 500-line component, fix it" forces Claude to process everything. Point to the file and describe the issue instead.
3. Don't be vague: "Make the app better" or "fix the tests" gives Claude no anchor. It will explore broadly, read many files, and burn tokens figuring out what you mean.
4. Don't use Opus for boilerplate: CRUD endpoints, simple tests, config files — Sonnet handles these perfectly. Opus costs ~5x more per token.
5. Don't skip /init: Without a CLAUDE.md, Claude re-discovers your project structure every session. That discovery phase is pure token waste.
6. Don't ask Claude to "read everything": "Read the entire src/ directory and tell me about it" can consume your whole context window. Be selective.
7. Don't repeat instructions: If you tell Claude the same coding convention every session, put it in CLAUDE.md instead. Every repetition costs tokens.
8. Don't ignore auto-compact warnings: When Claude warns about context limits, proactively /compact with guidance. Auto-compact may drop important context.
9. Don't chain unrelated tasks: "Fix the login bug, then refactor the database layer, then write docs for the API" — each topic inflates context for the others. Separate sessions.
10. Don't add pleasantries: "Hi Claude, I hope you're doing well! Could you please kindly..." — every token counts. Be direct: "Add input validation to the signup form."
Level 2 — Daily Workflow

Git with Claude — Daily Commands

Let Claude handle your routine git operations via the gh CLI.

Status check: "what's the git status? any uncommitted changes?" — Claude runs git status, git diff --stat and summarises.
Smart commit: "commit my changes with a good message following conventional commits" — Claude analyses the diff, writes a semantic commit message, and runs git commit.
Branch management: "create a branch feat/user-orders from main and push it" — Claude handles checkout, branch creation, and push in one go.
Interactive rebase help: "squash the last 3 commits into one with a clean message" — Claude handles the rebase non-interactively, preserving your changes.
Cherry-pick & backport: "cherry-pick commit abc123 onto the release/2.1 branch" — Claude switches branches, cherry-picks, handles conflicts, and pushes.
Stash management: "stash my current work, pull latest main, then pop the stash" — Claude handles the full flow and alerts you about conflicts.
Level 2 — Daily Workflow

Git with Claude — PR Workflow

From opening a PR to reviewing a colleague's code.

Open a PR: "create a PR to main with a description of what changed and a test plan" — Claude runs gh pr create with a well-structured title, summary, and test plan.
Review a peer's PR: "review PR #142 — focus on security and error handling" — Claude uses gh pr diff 142, reads the changes, and provides inline-style feedback.
Address review comments: "read the review comments on PR #142 and fix them" — Claude fetches comments via gh api, makes fixes, commits, and pushes.
PR status dashboard: "show me all open PRs assigned to me and their CI status" — Claude runs gh pr list --assignee @me and gh pr checks.
Merge when ready: "squash-merge PR #142 after checks pass" — Claude monitors checks with gh pr checks --watch and merges with gh pr merge --squash.
GitHub Actions helper: "why is the CI failing on PR #142?" — Claude runs gh run view, reads the logs, identifies the failure, and suggests a fix.
Level 2 — Daily Workflow

CLAUDE.md — Project Level

Your team's shared "instruction manual" for Claude, checked into git at the project root.

What it is: A markdown file at your project root that Claude reads at the start of every session. Think of it as .editorconfig but for AI behaviour.
Example 1 — Build commands:
# Build & Test
- Build: `npm run build`
- Test all: `npm test`
- Test single: `npm test -- --grep "test name"`
- Lint: `npm run lint`
Example 2 — Code style:
# Code Style
- Use TypeScript strict mode
- Prefer async/await over .then() chains
- Use Zod for request validation, not manual checks
- Error responses follow RFC 7807 (Problem Details)
Example 3 — Architecture rules:
# Architecture
- Routes go in src/routes/, services in src/services/
- Every route must have a corresponding OpenAPI spec in api/
- Lambda handlers are in src/handlers/ — use claudia.js conventions
- Never import from src/handlers/ in src/services/
Example 4 — Git conventions:
# Git
- Use Conventional Commits: feat|fix|chore|docs|refactor(scope): message
- Always squash-merge PRs to main
- Branch naming: feat/*, fix/*, chore/*
Example 5 — Testing rules:
# Testing
- Use Vitest for unit tests, Supertest for API integration tests
- Every new endpoint needs at least: happy path, 400, 401, 404 tests
- Mock external services using msw (Mock Service Worker)
- Test files live next to source: foo.ts → foo.test.ts
Keep it lean: ~100-150 lines max. For each line, ask: "Would Claude make a mistake without this?" If not, cut it. Every unnecessary line dilutes the ones that matter.
Level 2 — Daily Workflow

CLAUDE.md — Global Level

Personal preferences at ~/.claude/CLAUDE.md — applies to every project.

What it is: Your personal CLAUDE.md at ~/.claude/CLAUDE.md. Applies across all projects. Great for coding style preferences, language, and personal workflow.
Example 1 — Personal preferences:
# Personal Preferences
- I prefer concise explanations — skip the preamble
- Always show the file path before code changes
- When writing commit messages, include the ticket number from the branch name
Example 2 — Editor integration:
# Environment
- I use VSCode with Prettier (format on save)
- After editing a file, no need to run formatters — it happens automatically
- My terminal is iTerm2 with Zsh
Example 3 — Communication style:
# Communication
- When unsure, ask before making changes
- If a change touches more than 5 files, show me the plan first
- Explain trade-offs when suggesting architectural decisions
Example 4 — Default tools:
# Tools
- Use gh CLI for all GitHub operations
- Prefer npx over global installs
- Use jq for JSON processing in bash
Example 5 — Security rules:
# Security
- Never commit .env files or secrets
- Always check for hardcoded credentials before committing
- Flag any use of eval() or unsanitised user input
Hierarchy: Global CLAUDE.md → Parent directory → Project root → Child directories. More specific files override more general ones. Child CLAUDE.md files are loaded on demand.
Level 2 — Daily Workflow

Stack-Specific: Node.js + Express + Claudia.js

Prompts and CLAUDE.md tips for the backend team.

OpenAPI-first development: "Read api/openapi.yaml and generate the Express route + Zod validation for the POST /orders endpoint" — Claude generates code that matches your spec exactly.
Lambda handler scaffolding: "Create a new Lambda handler in src/handlers/ for the user-notifications service following the existing pattern in src/handlers/orders.js"
Claudia.js deployment checks: Add to CLAUDE.md: Deploy with: claudia update --handler src/lambda.handler. Claude will use the right command.
API testing helper: "Write Supertest integration tests for all endpoints in src/routes/orders.ts, covering 200, 400, 401, and 404 responses"
CLAUDE.md snippet for backend:
# Backend Stack
- Runtime: Node.js 20 on AWS Lambda via Claudia.js
- Framework: Express with OpenAPI 3.1 specs in api/
- Validation: Zod schemas auto-generated from OpenAPI
- Deploy: `npx claudia update` (never `claudia create` on existing)
Debugging Lambda locally: "Help me debug this Lambda timeout — read the CloudWatch log snippet I pasted and suggest fixes"
Level 2 — Daily Workflow

Stack-Specific: Vue 3

Prompts and tips for the frontend team.

Component generation: "Create a Vue 3 Composition API component for a paginated data table in src/components/DataTable.vue using <script setup> with TypeScript"
Composable extraction: "Extract the filter logic from OrderList.vue into a composable at src/composables/useOrderFilters.ts"
Pinia store scaffolding: "Create a Pinia store for the notification system with actions to fetch, mark-read, and dismiss"
CLAUDE.md snippet for frontend:
# Frontend Stack
- Framework: Vue 3 with Composition API (<script setup>)
- State: Pinia stores in src/stores/
- Styling: Tailwind CSS — no custom CSS unless absolutely necessary
- Testing: Vitest + Vue Test Utils
- Always use TypeScript, never plain JS in .vue files
Migration helper: "Refactor src/components/LegacyForm.vue from Options API to Composition API with <script setup>, preserving all functionality"
Level 2 — Daily Workflow

Stack-Specific: React Native

Prompts and tips for the mobile team.

Screen scaffolding: "Create a new screen at src/screens/OrderDetailScreen.tsx with React Navigation params for orderId, fetching data with React Query"
Platform-specific code: "Add haptic feedback on iOS and vibration on Android when the user completes a purchase — use Platform.select"
Native module debugging: "Read the Metro bundler error log and explain why the native module 'react-native-camera' isn't linking properly"
CLAUDE.md snippet for mobile:
# Mobile Stack
- Framework: React Native 0.74+ with TypeScript
- Navigation: React Navigation v6
- State: Zustand for local, React Query for server state
- Testing: Jest + React Native Testing Library
- Always handle both iOS and Android edge cases
Performance profiling: "Analyse why the FlatList in src/screens/Feed.tsx is re-rendering excessively and add memoisation where needed"
Level 2 — Daily Workflow

Stack-Specific: QA

Claude can be a powerful testing partner.

Test generation: "Read the PR diff for #156 and generate test cases covering all changed logic, edge cases, and error paths"
E2E test writing: "Write a Playwright E2E test for the user login flow: valid creds → dashboard, invalid → error message, expired session → redirect"
Bug reproduction: "Here's the bug report: [paste]. Read the relevant code and write a failing test that reproduces this issue."
Test coverage analysis: "Run the test suite, analyse the coverage report, and identify the 5 most critical untested code paths"
API contract testing: "Compare the OpenAPI spec in api/openapi.yaml with the actual API responses and flag any mismatches"
RESOURCES

References & Learning Resources

Official docs, free courses, video tutorials, and community guides to deepen your Claude Code skills.

Official Docs — Start Here: code.claude.com/docs — The complete official documentation: overview, quickstart, how it works, configuration, hooks, skills, agents, CLI reference, and more.
Quickstart Guide: code.claude.com/docs/en/quickstart — Up and running in minutes. The official first-steps walkthrough.
Best Practices (Official): code.claude.com/docs/en/best-practices — Anthropic's own guide on effective prompting, context management, and scaling workflows.
Common Workflows (Tutorials): code.claude.com/docs/en/tutorials — Step-by-step walkthroughs: exploring codebases, fixing bugs, refactoring, writing tests, creating PRs, and managing sessions.
Hooks Reference: code.claude.com/docs/en/hooks — Full reference for SessionStart, PreToolUse, PostToolUse, Stop, Notification, PostCompact events and handler types.
CLI Reference: code.claude.com/docs/en/cli-reference — Every flag, environment variable, and invocation mode documented.
Free Course — Claude Code 101: anthropic.skilljar.com/claude-code-101 — Official free Anthropic Academy course. From installation to advanced customisation, with certificate on completion.
Free Course — Claude Code in Action: anthropic.skilljar.com/claude-code-in-action — Deeper official course: building, configuring, and sharing Skills. Also free with certificate.
Video — Anthropic's YouTube Channel: youtube.com/@anthropic-ai — Official Anthropic channel with product demos, workflow walkthroughs, and feature deep-dives.
Video — Anthropic Workflows: Even Anthropic Engineers Use This Claude Code Workflow — Real-world workflow patterns from the team that built Claude Code.
GitHub — Source & Community: github.com/anthropics/claude-code — Source, issue tracker, plugins, and community discussions. Also see awesome-claude-code for curated skills, hooks, and plugins.
Community — Best Practices Repo: shanraisshan/claude-code-best-practice — 20k+ stars. 84 compiled best practices covering prompting, CLAUDE.md, skills, and debugging. A great second opinion alongside official docs.

Next: Level 3 — Customisation

Custom slash commands, hooks, MCP servers, skills, and plugins — making Claude Code truly yours.

Master these workflows first, then level up your automation game.

reveal tip   hide tip   next slide   prev slide   F fullscreen