matthiasn
@matthiasn
Public Skills
design-review-panel
by matthiasn
Run a multi-agent design review on a UI surface — capture reproducible baseline screenshots, then rate them with a panel of design experts (one agent per craft dimension) and, optionally, a panel of user personas with different cognitive styles. Iterate implement → re-screenshot → re-rate until every panel hits a numeric target (e.g. avg ≥8/10). Use when polishing or redesigning a screen/modal/dialog and the user wants grounded, scored design feedback ("summon the design panel", "rate this with the experts", "run the persona panel").
tutorial-videos
by matthiasn
Build, debug, extend, localize, or publish the automated tutorial videos — the workbench that drives the real Linux app under Xvfb (virtual mic, live Voxtral transcription, task-agent proposals), records the screen, narrates with Gemini TTS, fast-forwards waits, composes MP4s via OpenMontage, and uploads finished videos to Cloudflare R2 for docs-site embedding. Use when asked to "build/regenerate the tutorial video(s)", add a tutorial scenario, add a tutorial locale, fix a broken tutorial run, adapt the pipeline, or upload/publish a video.
release
by matthiasn
Cut a Lotti release — assemble the changelog.d/ fragments into CHANGELOG.md and the Flathub metainfo, bump the version, open the release PR, then tag. Use when asked to cut or prepare a release, assemble the changelog, publish a new version, or work out what is unreleased.
skeptical-review
by matthiasn
Act as a skeptical senior engineer performing a detailed code review of the latest changes on the current branch (or a given PR) — best practices, maintainability, performance, security, and readability. Objective and concise; only real issues, with a clear "no issues" verdict when the code is clean. Replaces CodeRabbit / Gemini Code Review.
review-comments
by matthiasn
Fetch PR review comments, address each one in code, and post resolution replies
beads
by matthiasn
Use for authorized Lotti maintainer work that needs private durable task tracking, issue dependencies, blocker management, multi-session handoff, or shared agent memory. Public contributors use GitHub Issues instead.
maintain-docusaurus-manual
by matthiasn
Maintain a Docusaurus product manual whose prose, navigation, localized page trees, screenshots, coverage metadata, and release build must stay aligned with the application. Use when adding or revising manual pages, documenting a product change, updating translated MDX, repairing locale parity, adding registered screenshots, auditing stale documentation, or validating a multilingual Docusaurus site before publication.
add-flutter-docusaurus-locale
by matthiasn
Add, complete, or audit a locale across a Flutter application's ARB catalogs and a localized Docusaurus manual, including generated localization code, locale selectors, native platform declarations, translated MDX, screenshot fixtures, tests, and parity validation. Use when introducing a new language, finishing an incomplete app or manual translation, aligning manual terminology with UI strings, or reviewing whether a locale is production-ready end to end.
app-screenshots
by matthiasn
Capture in-app screenshots of a widget or flow at mobile + desktop sizes — offline, deterministic, real fonts and icons — using the reusable screenshot harness. Use when asked to "show me X in the app", "screenshot this screen", or to preview a UI change for review on phone vs desktop.
analyze-db-logs
by matthiasn
Analyze Drift / SQLite slow-query and super-slow-query logs against this app's known stall patterns (read waves, N+1, transaction scoping, MultiExecutor contention, WAL/OS factors)