koldovsky

Add Gmail integration to map-poi-agent. Can be configured as a tool (agent reads/sends emails when triggered from WhatsApp) or as a full channel (emails can trigger the agent, schedule tasks, and receive replies). Guides through GCP OAuth setup and implements the integration.

Add Slack as a channel. Can replace WhatsApp entirely or run alongside it. Uses Socket Mode (no public URL needed).

Add Telegram as a channel. Can replace WhatsApp entirely or run alongside it. Also configurable as a control-only channel (triggers actions) or passive channel (receives notifications only).

Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".

Add voice message transcription to map-poi-agent using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.

Switch from Docker to Apple Container for macOS-native container isolation. Use when the user wants Apple Container instead of Docker, or is setting up on macOS and prefers the native runtime. Triggers on "apple container", "convert to apple container", "switch to apple container", or "use apple container".

Add new capabilities or modify map-poi-agent behavior. Use when user wants to add channels (Telegram, Slack, email input), change triggers, add integrations, modify the router, or make any other customizations. This is an interactive skill that asks questions to understand what the user wants.

Debug container agent issues. Use when things aren't working, container fails, authentication problems, or to understand how the container system works. Covers logs, environment variables, mounts, and common issues.

Analyze bundle size, check for forbidden imports, and identify large dependencies in the Excalidraw project. Use when optimizing bundle size, reviewing imports, or checking for unauthorized dependencies.

Create React components for the Excalidraw project following established patterns, conventions, and architecture. Use when creating new UI components, panels, dialogs, or toolbar items in Excalidraw.

Understand Excalidraw's architecture: state management, rendering pipeline, monorepo structure, and package dependencies. Use when making architectural decisions, understanding data flow, or debugging state-related issues.

Review pull requests and local diffs for the Excalidraw monorepo: correctness, architecture, project conventions, tests, and bundle/import hygiene. Use when reviewing code changes, before merge, after `git diff`, or when the user asks for a code review, PR review, or pre-merge check.

Suggests the best Ukrainian city for a short trip by weather — for near-term dates and ANY preference (cool, warm, dry, sunny, even rainy). Self-contained: it fetches live weather itself, needs no app, no setup, no API key. Use whenever the user asks where to go / the best place to travel in Ukraine for a weekend or specific upcoming days.

Recommends where to travel in Ukraine for given near-term dates by reasoning over live weather. Handles ANY weather preference in the question — cool, warm, dry, sunny, "for hiking", "just nice" — not a fixed set. Use whenever the user asks where to go / the best place to travel / where the weather is best in Ukraine for a weekend or specific upcoming dates.

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

Use when the user wants to build, deliver, scaffold, or govern a software project with a rigorous spec-driven multi-agent process — e.g. "set up project factory", "build this to spec", "bring this repo under spec-driven delivery", "orchestrate the delivery", "run the factory", or hands over requirements/an RFP to turn into a working, QA-proven product. Drives the full lifecycle (requirements → OpenSpec specs → capability slices → test-first build → adversarial review → evals → QA proof → UAT) through deterministic gates, dispatching specialized subagents and workflows. Works on new (greenfield) and existing repos.

Applies the Надворі / Weather Explorer design system when building or reviewing frontend UI — tokens, components, typography, Ukrainian voice, and accessibility. Use when implementing pages, components, styles, layouts, themes, copy, or any visual work in this project.

Use this skill to generate well-branded interfaces and assets for Надворі (Nadvori) / Weather Explorer — a calm, Ukrainian-first weather app — either for production or throwaway prototypes/mocks. Contains design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.

Add a new slide to the Slidev deck (slides.md or pages/*.md) with consistent frontmatter, layout, and speaker notes. Use when the user asks to add a slide, insert a section, create a new page, or extend the deck. Keeps slides concise, uses v-clicks for long lists, and puts long citations into HTML-comment notes.

Verify the Slidev deck builds and runs cleanly after non-trivial edits to slides.md, pages/, components/, layouts/, or global-top.vue. Use after creating/modifying slides, components, or layouts to catch broken Markdown, invalid Mermaid, missing imports, or frontmatter parsing errors before the user runs the deck.

Author Mermaid diagrams inside Slidev slides without breaking the parser or the print/PDF export. Use whenever a slide needs a flow, hierarchy, sequence, state, or class diagram — Mermaid is preferred over new raster images.

Design and edit Slidev workshop decks for business analyst audiences: typography, layout, colors, speaker notes, exercise slides, timers, and PDF-friendly styling. Use when creating or polishing slides.md, workshop decks, facilitator materials, or visual consistency for BA training sessions.

Fix Slidev presentation PDF export issues: slides not filling the page, black margins, broken backgrounds, zoom/scale problems, and content clipping. Use when working with Slidev, slidev export, PDF generation from slides, or when the user mentions slides not fitting the page, black bars in PDF, or content overflow in presentations.

Use when the user wants to build, deliver, scaffold, or govern a software project with a rigorous spec-driven multi-agent process — e.g. "set up project factory", "build this to spec", "bring this repo under spec-driven delivery", "orchestrate the delivery", "run the factory", or hands over requirements/an RFP to turn into a working, QA-proven product. Drives the full lifecycle (requirements → OpenSpec specs → capability slices → test-first build → adversarial review → evals → QA proof → UAT) through deterministic gates, dispatching specialized subagents and workflows. Works on new (greenfield) and existing repos.

Run a layered AI code review on this Next.js notes API: prioritize data-boundary failures, server-owned metadata influenced by request data, schema/domain mismatches, secret/internals leaks, and weak tests.

Run a layered AI code review on a PR or local diff for this Next.js notes API: prioritize Broken Access Control / IDOR, owner-from-client, missing Zod validation, secret/internals leaks, and tests tuned to pass. Use when reviewing code changes, before merge, after `git diff`, or when asked for a code review.

Independently review a completed task, diff, PR, file/directory, whole project, spec, or config using a clean-context subagent so the implementing agent's bias does not leak into the verdict. Use when the user asks to review, validate, verify, audit, check, or get a "second pair of eyes" on any of these targets, or after completing a non-trivial task before declaring it done.

Author Mermaid diagrams inside Slidev slides without breaking the parser or the print/PDF export. Use whenever a slide needs a flow, hierarchy, sequence, state, or class diagram — Mermaid is preferred over new raster images.

Independently review any course-prep artifact — a blueprint, module outline, single lecture, code samples, task, quiz, full module, complete course package, compiled deliverable, raw imported source, or a finished course end-to-end — using a clean-context subagent so the author's bias does not leak into the verdict. Use when the user asks to review, validate, verify, audit, fact-check, or get a 'second pair of eyes' on educational content, or as a mandatory gate before declaring any course-prep milestone done. Triggers: review course, validate lecture, audit course, verify quiz, fact-check, review module, check the slides, vet the references, sanity-check the blueprint, course QA, course-review.