Skip to content

Latest commit

 

History

History
108 lines (80 loc) · 3.21 KB

CLAUDE.md

File metadata and controls

108 lines (80 loc) · 3.21 KB

CLAUDE.md

1. Think Before Coding

Don't assume. Don't hide confusion. Surface tradeoffs.

Before implementing:

  • State your assumptions explicitly. If uncertain, ask.
  • If multiple interpretations exist, present them - don't pick silently.
  • If a simpler approach exists, say so. Push back when warranted.
  • If something is unclear, stop. Name what's confusing. Ask.

2. Simplicity First

Minimum code that solves the problem. Nothing speculative.

  • No features beyond what was asked.
  • No abstractions for single-use code.
  • No "flexibility" or "configurability" that wasn't requested.
  • No error handling for impossible scenarios.
  • If you write 200 lines and it could be 50, rewrite it.

Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.

3. Surgical Changes

Touch only what you must. Clean up only your own mess.

When editing existing code:

  • Don't "improve" adjacent code, comments, or formatting.
  • Don't refactor things that aren't broken.
  • Match existing style, even if you'd do it differently.
  • If you notice unrelated dead code, mention it - don't delete it.

When your changes create orphans:

  • Remove imports/variables/functions that YOUR changes made unused.
  • Don't remove pre-existing dead code unless asked.

The test: Every changed line should trace directly to the user's request.

4. Goal-Driven Execution

Define success criteria. Loop until verified.

Transform tasks into verifiable goals:

  • "Add validation" → "Write tests for invalid inputs, then make them pass"
  • "Fix the bug" → "Write a test that reproduces it, then make it pass"
  • "Refactor X" → "Ensure tests pass before and after"

For multi-step tasks, state a brief plan:

1. [Step] → verify: [check]
2. [Step] → verify: [check]
3. [Step] → verify: [check]

Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.

5. Comment Style

Consistent, purposeful comments. Not noise.

JSDoc for public APIs

Every exported function, interface, and type gets JSDoc documentation:

/**
 * Brief description of what it does
 *
 * @param foo - Description of parameter
 * @returns Description of return value
 */
export function myFunction(foo: string): number { ... }

Section markers inside functions

Use /** SECTION NAME */ to mark logical sections within complex functions:

function complexFunction() {
  /** PARSE OPTIONS */
  const { foo, bar } = options;

  /** VALIDATE INPUT */
  if (!foo) throw new Error('foo required');

  /** EXECUTE MAIN LOGIC */
  const result = doSomething(foo, bar);

  /** CLEANUP */
  return result;
}

Common section names: STATE, REFS, GUARDS, HELPERS, CLEANUP, EFFECT 1: ..., HANDLE ERROR

Inline explanations

Use // comment for explaining specific logic:

// Only sync if auto-sync is not explicitly disabled
const shouldAutoSync = options?.autoSync !== false;

// On Android, the native call blocks for ~10-15s if offline
if (Platform.OS === 'android') { ... }

What NOT to comment

  • Obvious code (// increment counter before count++)
  • Code that's already clear from good naming
  • Every single line - only where it adds value