mydotbot

Standard editorial template for any standalone HTML output (reports, RCAs, dashboards, diagrams, slides, recaps). Use EVERY time you generate an HTML file so output follows one consistent house style instead of ad-hoc theming.

Findings-first review agent for code changes. Use when the user asks to review a branch, PR, diff, commit range, or recent changes and wants prioritized, actionable issues instead of implementation work.

Scan and clean stale Claude Code sessions from the shared store at ~/.local/share/claude/projects (used by all .claude / .claude-accountN dirs via symlink). Removes session JSONLs older than N days, orphan subagent dirs, and reports reclaimable space.

Triage ShopHelp XCTest/Swift Testing failures before proposing fixes.

Manage Jira issues through jhelp shell functions (jv, jm, jd, jc, jforward, etc.). Use when the user wants to view, transition, assign, comment on, edit, search, or create Jira work items; when they provide a bare issue number, Jira issue key, or Jira URL; or when the task involves the current git branch ticket.

Create git commits. Use when user says "commit", "commit this", "commit changes", "split commit", "split commit change", "split the changes".

Scaffolds a complete feature module with Screen, View, ViewModel, Coordinator, and Dependencies. Use when creating a new screen or feature.

Scaffolds a UseCase protocol and implementation following Clean Architecture. Use when creating a new UseCase.

Scaffolds a ViewModel with @MainActor, ObservableObject, async/await, and Swinject DI. Use when creating a new ViewModel.

Debugs iOS app issues by analyzing logs, crash reports, and code flow. Use when debugging, fixing bugs, or analyzing crashes.

Registers a new dependency in Swinject DI container. Use when adding new UseCase, Repository, or Service to DI.

Analyzes source code architecture and implementation, generates Mermaid diagrams, and outputs documented results to an artifacts folder. Use when asked to analyze code, explain architecture, understand code flow, or generate code diagrams.

Analyzes video files by splitting into frames using FFmpeg and reading frames to understand UI/feature requirements. Use when given a video to implement, replicate a UI from a video, or understand a feature shown in a video.

Validate Clean Architecture boundaries and dependencies

Scaffolds a Repository protocol and implementation with network or database layer. Use when creating a new Repository.

Symptom-first debugging and root-cause investigation agent. Use when the user starts with logs, crashes, failing tests, screenshots, odd runtime behavior, or mixed evidence and wants the most likely causes plus next probes.

Plans iOS feature implementation with architecture decisions, file changes, and data flow. Use when asked to plan, design, or architect a new feature.

Reviews Swift code against project standards and CLAUDE.md rules. Use when asked to review code, check quality, or validate changes.

Show Claude Code usage stats from cache, then optionally build the HTML dashboard (24h / 7d / 30d / all)

Generate a concise merge request description from git diff and commit history.

Implements Liquid Glass design effects in SwiftUI and UIKit. Use when adding glass effects, glass buttons, glass containers, morphing transitions, or adopting Apple Liquid Glass design system.

Simulator validation flow using tmux + lldb + xcrun simctl + axe for iOS apps. Use when you need repeatable validation, log capture, debugger attach, or gesture automation (swipe/tap) without browser/UI tooling.

Create, send, and debug iOS simulator APNS push notifications for visible alerts, silent/background pushes, and mixed content-available diagnostics. Use when Codex needs to simulate notification delivery with xcrun simctl push, generate .apns payload files, verify bundle id/device state, attach debugger breakpoints, or explain why visible push works but silent push callbacks do not fire.

Writes unit tests using XCTest and Cuckoo mocks following project testing patterns. Use when creating or adding tests.

AI-optimized browser automation CLI with context-efficient snapshots. Use for long autonomous sessions, self-verifying workflows, video recording, and cloud browser testing (Browserbase).

Generate images via Nano Banana with 129 curated prompts. Mandatory validation interview refines style/mood/colors (use --skip to bypass). 3 modes: search, creative, wild. Styles: Ukiyo-e, Bento grid, cyberpunk, cinematic, vintage patent.

Analyze images/audio/video with Gemini API (better vision than Claude). Generate images (Imagen 4), videos (Veo 3). Use for vision analysis, transcription, OCR, design extraction, multimodal AI.

Answer technical and architectural questions with expert consultation.

Build backends with Node.js, Python, Go (NestJS, FastAPI, Django). Use for REST/GraphQL/gRPC APIs, auth (OAuth, JWT), databases, microservices, security (OWASP), Docker/K8s.

Add authentication with Better Auth (TypeScript). Use for email/password, OAuth providers (Google, GitHub), 2FA/MFA, passkeys/WebAuthn, sessions, RBAC, rate limiting.

Bootstrap new projects with research, tech stack, design, planning, and implementation. Modes: full (interactive), auto (default), fast (skip research), parallel (multi-agent).

Brainstorm solutions with trade-off analysis and brutal honesty. Use for ideation, architecture decisions, technical debates, feature exploration, feasibility assessment, design discussions.

Automate browsers with Puppeteer CLI scripts and persistent sessions. Use for screenshots, performance analysis, network monitoring, web scraping, form automation, JavaScript debugging.

ClaudeKit usage guide — discover commands, skills, workflows naturally.

Review code quality, receive feedback with technical rigor, verify completion claims. Use before PRs, after implementing features, when claiming task completion. Includes scout-based edge case detection and native Task pipeline orchestration.

Set coding experience level for tailored explanations and output format.

Check context usage limits, monitor time remaining, optimize token consumption, debug context failures. Use when asking about context percentage, rate limits, usage warnings, context optimization, agent architectures, memory systems.

ALWAYS activate this skill before implementing EVERY feature, plan, or fix.

Conversion copywriting formulas, headline templates, email copy patterns, landing page structures, CTA optimization, and writing style extraction. Activate for writing high-converting copy, crafting headlines, email campaigns, landing pages, or applying custom writing styles from assets/writing-styles/ directory.

Design schemas, write queries for MongoDB and PostgreSQL. Use for database design, SQL/NoSQL queries, aggregation pipelines, indexes, migrations, replication, performance optimization, psql CLI.