Agent skills

Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories…

ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.

Compose Multiplatform and Jetpack Compose patterns for KMP projects — state management, navigation, theming, performance, and…

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns.

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky.

Database migration best practices for schema changes, data migrations, rollbacks, and zero-downtime deployments across PostgreSQL, MySQL…

Unified media generation via fal.ai MCP — image, video, and audio.

Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshot…

Create and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and fundraising materials.

Idiomatic Kotlin patterns, best practices, and conventions for building robust, efficient, and maintainable Kotlin applications with…

Process, convert, OCR, extract, redact, sign, and fill documents using the Nutrient DWS API.

Filters and qualifies local MICE industry enterprises for event bidding, procurement sourcing, and supplier verification.

Transforms informal work logs into structured weekly, monthly, and annual business reports with automated theme extraction and knowledge…

Use when preparing a MICRO artifact for post-acceptance evaluation — packaging simulators, configs, traces, and scripts so evaluators can…

Use when reviews arrive for a MICRO submission and the rebuttal/revision window opens — triaging reviewer objections by what can change a…

Use when a MICRO paper is accepted and the camera-ready is due — the nine-week July-to-September window in the 2026 cycle…

Specify one micro-interaction completely — trigger, rules, feedback, loops, and modes.

Use when building a MICRO paper's related-work coverage and positioning — sweeping the four-venue architecture literature plus journals…

Use when hardening a MICRO paper's results for re-derivation — pinning simulator commits and configs, recording workload trace provenance…

Use when auditing a MICRO submission before HotCRP upload — the 11-page-plus-references limit with no appendix allowed, EDT (not AoE)…

Use when deciding where a MICRO paper's supporting material lives, because MICRO allows no appendix at all — triaging content into the 11…