WakaTime

@WakaTime show me my coding activity for the last 7 days broken down by project and language

Based on your WakaTime data, you logged 32 hours 14 minutes over the past week. Your top projects were: api-refactor (14h 22m), mobile-app (9h 41m), and docs-site (5h 18m). By language: TypeScript accounted for 18h 5m, Python 8h 12m, and Markdown 3h 44m. Your most active day was Wednesday with 6h 51m. This is an illustrative summary — actual breakdowns depend on your tracked editors and project configurations.

WakaTime aggregates time from IDE plugins, so accuracy depends on which editors you have configured. OAuth scope must include read access to your personal stats. Data reflects when your editor was open and active, not necessarily when code was committed or deployed.

@WakaTime compare my productivity this month versus last month and highlight any significant changes in my work patterns

This month you've logged 118 hours compared to 142 hours last month — a 17% decrease. Your average daily coding time dropped from 6.4 hours to 5.1 hours. Notable shifts: Go usage increased 340% (from 4h to 18h), while React time fell 28%. Your most productive hours shifted earlier — 9-11am now accounts for 31% of your activity versus 22% last month. Weekend coding dropped from 12% to 4% of total time. This analysis is illustrative; trends become more reliable with consistent tracking over multiple months.

Month-over-month comparisons require at least two full months of data. WakaTime's API provides historical summaries, but the AI synthesizes patterns — verify critical insights against the WakaTime dashboard. Useful for retrospectives or adjusting work habits, but don't treat minor fluctuations as definitive trends.

@WakaTime what were my top 5 most-used files yesterday and how much time did I spend in each?

Yesterday's top files by active time: 1) src/api/auth.ts (1h 47m), 2) tests/integration/login.spec.ts (1h 12m), 3) components/UserProfile.tsx (52m), 4) README.md (38m), 5) package.json (19m). Total tracked time for the day was 6h 23m across 47 different files. Auth.ts saw three separate editing sessions, suggesting iterative debugging or feature work. This breakdown is illustrative — file-level granularity depends on your WakaTime plugin reporting file paths correctly.

File-level tracking works best in projects with clear file structures. Minified files, generated code, or files opened briefly for reference may skew results. Requires OAuth read access to detailed stats. Useful for understanding where time actually goes versus where you think it goes, especially during focused feature work.

Track coding time across distributed engineers without micromanaging

A 6-person remote engineering team wants visibility into who's blocked versus who's shipping without turning standup into a surveillance exercise. WakaTime's OAuth2 integration lets Switchy pull aggregate coding time by project and language, so the lead can spot patterns—like someone spending 80% of their week in YAML instead of Python, signaling infra firefighting. The MCP works when you need passive context for 1-on-1s or sprint retros, not real-time alerts. If your team treats time-tracking as a performance metric rather than a debugging tool, this will backfire. Use it to ask better questions, not to rank developers.

When automated time logs beat manual timesheets for contract work

A solo consultant or small agency bills clients by the hour and needs defensible records without stopping to click a timer every 20 minutes. WakaTime logs editor activity automatically, and Switchy can query it to generate weekly summaries grouped by project or client tag. This works if your contract defines billable work as 'time in the codebase'—it won't capture meetings, Slack, or research. The threshold: if more than 30% of your billable hours happen outside the editor, WakaTime undercounts and you'll need a second source. For pure dev work, it's the lowest-friction audit trail you can hand a client.

Diagnose your own context-switching without a coach or app-blocker

An individual developer wants to understand why some days feel productive and others don't, but doesn't want to hire a productivity consultant or install another Pomodoro app. WakaTime tracks which projects, languages, and editors you used each day, and Switchy can surface trends—like realizing you wrote 4x more code on days you avoided switching between three repos before lunch. The MCP is useful if you're willing to look at the data weekly and change one habit at a time. If you're hunting for motivation or accountability, raw time logs won't provide it. This is a mirror, not a motivator—use it when you're ready to act on what you see.