CLAUDE.md

Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.

Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment.

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.

These guidelines are working if: fewer unnecessary changes in diffs, fewer rewrites due to overcomplication, and clarifying questions come before implementation rather than after mistakes.

Project notes

Activity page power curve — comparison lines (future)

The activity page shows a single-activity power curve from detail.mmp (pre-computed at extract time, zero extra requests). Adding "last 365 d / last 90 d" comparison overlays requires the pre-computed power_curve.last_365d / power_curve.last_90d arrays, which currently live only in athlete.json. Loading athlete.json at activity-page time is wasteful (it's a large file with all activity summaries).

Clean solution when the time comes: at render time (inside _merge_edits or a dedicated step in bincio/render/cli.py), bake the comparison curves into each activity's detail JSON — e.g. add a power_curve_context key with all_time, last_365d, last_90d. The activity page then gets them for free with the detail JSON it already fetches. Requires a one-time bincio render (no code changes to the extractor). Component to update: site/src/components/ActivityPowerCurve.svelte.

3.3 KiB Raw Permalink Blame History