pids-jre-simulator

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Picks up after /build to publish a GitHub release. Pre-flights the staged artifacts, drafts release_notes.md from commits since the last tag, tags master, then hands the gh release create upload command to the user. Stops short of running the upload — that's user-driven.

Spawn a fresh-context Opus 4.7 agent to give an independent take when Claude and the user are talking past each other on a contested logic interpretation, OR to validate behavioral self-observations from /session-recap Step 0. User-triggered or claude self-proposed at impasse.

End-of-session recap — codify learnings synchronously into their canonical homes; daily logs hold narrative continuity only.

Review dirty code and fix iteratively using Ralph loop pattern. When user say to "loop to fix dirty" or "review+fix"

Review dirty code changes using Claude Code Agent tool. When user say to "review" or "review changes" or "review dirty code"

Sanity-scan the production codebase for cruft that piles up after AI-assisted feature work — duplicated logic, dead helpers, half-finished implementations, speculative architecture, stale comments. Discussion-first, item-by-item; smoke-tests every fix.

Build the JRE-PA-Simulator Windows executable + staged distribution folder (no GitHub release). Embeds version in exe metadata.

README / i18n maintenance — keep English and translated READMEs in sync, extract language-agnostic content, apply the project's Chinese phrasing preferences.

Direct-manipulation pixel-tuning for E235 LCD elements — how to launch the in-app editor, add a new tuneable element (extract magic numbers → module-level `_TUNEABLES_*` dict → register → smoke-test), and wire a brand-new train model. Use when adding/tuning LCD display elements or forking a new train model's display.

Visually iterate on UI layout by comparing screenshots against ground truth

Commit hygiene — before creating a commit, detect and flag unrelated changes (especially stray data fixes bundled into program commits) so they can be split into their own commits.

Periodic audit of domain docs (DISPLAY.md, DISPLAY_E235.md, DATA_FORMAT.md, auto_input/README.md, plus future per-series DISPLAY_*.md) — scan for accumulated bloat (history notes, code-snippet illustrations, speculative future sections, design-rationale prose, cross-doc duplication, cumulative staleness). Discussion-first, item-by-item; user approves each removal before any edit lands.

End-to-end PA (public-address announcement) processing for a route — optional Whisper-based timestamp generation, splitting the source mp3 into per-segment files, route.json updates, and silence-bracket validation. PA-only; for STA (departure melody) processing see sta-make.

Periodic audit of the rules corpus (principles.md, conventions.md, critical_lessons.md). Scan for accumulated bloat — recurrence lists, sibling cross-refs, connective tissue, nested sub-rules, multi-paragraph incident traces. Discussion-first, item-by-item. Restructure + rephrase allowed.

Split a continuous source mp3 (PA announcements or STA melodies) into per-segment files for a new route, applying naming conventions and updating route.json so the simulator picks them up.

End-to-end STA (departure-melody + closing-door announcement) processing for a route — splitting source mp3s into per-segment files, trimming silences, validating sta_cut placement, and a by-ear verification gate. STA-only; for PA see pa-make.