Skill Creator

djimontyp

21 published skills · 0 GitHub stars across the catalog. View on GitHub ↗

api-contract-sync

djimontyp's avatarfrom djimontyp

Use this skill when backend API contracts change and frontend types need synchronization. Triggers on: Pydantic model changes, REST endpoint updates, WebSocket message formats, or GraphQL schema modifications. Dynamically detects contract type from context. NOT for unrelated type definitions or internal backend-only changes.

api-contracts

djimontyp's avatarfrom djimontyp

Sync API contracts between FastAPI backend and React frontend. Triggers on "sync api", "update contracts", "generate types", "оновити контракти", "згенерувати типи", or when backend schemas change.

ascii-diagrams

djimontyp's avatarfrom djimontyp

Create and fix ASCII diagrams, tables, wireframes, box-drawings. Use when message contains Unicode box characters (┌┐└┘│─), user asks to create/fix text visualization, align borders, or fix broken ASCII art. Triggers on "поправ діаграму", "fix diagram", "create table", "вирівняй", "align boxes".

ba

djimontyp's avatarfrom djimontyp

Business analysis methodologies, requirements engineering, RACI matrices, user stories for Pulse Radar.

backend

djimontyp's avatarfrom djimontyp

FastAPI, SQLModel, async services for Pulse Radar backend development.

design-tokens

djimontyp's avatarfrom djimontyp

Pulse Radar design system - semantic colors, spacing grid, component patterns.

docling

djimontyp's avatarfrom djimontyp

Convert documents (PPTX, PDF, DOCX, XLSX, images) to Markdown/JSON/HTML using IBM Docling. This skill should be used when user asks to convert, parse, or extract content from documents. Triggers on "convert pptx", "parse pdf", "extract from document", "конвертуй презентацію", "витягни з pdf".

docs

djimontyp's avatarfrom djimontyp

Bilingual documentation (EN/UK), MkDocs, Ukrainian plurals for Pulse Radar.

llm-pipeline

djimontyp's avatarfrom djimontyp

Pydantic-AI agents, RAG, embeddings for Pulse Radar knowledge extraction.

artifact-aggregator

djimontyp's avatarfrom djimontyp

Create tiered reports (micro/standard/comprehensive) based on task complexity. Tier 1 (200-500 words) for Level 1 tasks, Tier 2 (500-1500 words) for Level 2, Tier 3 (1500-5000 words) for Level 3 epics. Synthesizes agent outputs into concise, scannable reports without duplication. Uses density over volume, actionable over descriptive. Triggers ONLY after multi-agent completion (2+ agents) or complex investigations. NOT for single-agent trivial tasks.

brainstorming

djimontyp's avatarfrom djimontyp

Fast ideation and problem exploration. Triggers on Ukrainian/English phrases like "подумай", "поміркуй", "брейнштормінг", "brainstorm", "think through", "накидай ідеї", "generate ideas". Rapid divergent thinking to uncover insights, problems, and solutions through interactive dialogue.

frontend

djimontyp's avatarfrom djimontyp

Create distinctive, production-grade React interfaces using shadcn/ui. Triggers on frontend tasks, UI components, styling. Combines technical shadcn patterns with intentional design thinking for memorable aesthetics.

migration-database

djimontyp's avatarfrom djimontyp

This skill should be used when working with database migrations in SQLModel-based projects. Trigger when user asks to create migrations for new/modified models, generate database schema changes, or apply migrations. Enforces SQLModel as single source of truth and automatic migration generation only.

pycharm-refs

djimontyp's avatarfrom djimontyp

This skill should be used when agents need to provide clickable code references to users in reports, investigations, or bug findings. It ensures file references use the simple path:line_number format that Claude Code automatically converts to clickable links. Do not use for general documentation or conceptual explanations.

sync-docs-structure

djimontyp's avatarfrom djimontyp

Automatically sync the documentation structure from docs/content/{en,uk}/ to CLAUDE.md when changes are detected in the docs directory. This skill should be triggered when documentation files are added, removed, or reorganized, or when explicitly requested by the user or agents.

task-breakdown

djimontyp's avatarfrom djimontyp

FIRST STEP - Assess task complexity (0-20 score) and output orchestration level (0-3). Use for ANY non-trivial task BEFORE execution. Scores across scope, time, agents, dependencies, documentation. Level 0 (0-2 direct), Level 1 (3-7 single agent), Level 2 (8-14 multi-agent), Level 3 (15-20 epic). Outputs recommendation then exits. NOT for execution or agent selection (use agent-selector after).

skill-creator

djimontyp's avatarfrom djimontyp

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

smart-commit

djimontyp's avatarfrom djimontyp

This skill should be used when user asks to commit changes to git repository. Triggers on Ukrainian/English phrases like "закоміть зміни", "commit changes", "створи коміт", "зроби коміт", or any request to create git commits. Creates atomic commits with semantic file grouping using conventional commit format.

storybook

djimontyp's avatarfrom djimontyp

Storybook stories, CSF3 format, autodocs. Use for component documentation.

testing

djimontyp's avatarfrom djimontyp

pytest, Vitest, Playwright testing patterns for Pulse Radar.

frontend-flow

djimontyp's avatarfrom djimontyp

Ensures frontend code quality by enforcing Design System (9 ESLint rules), Storybook coverage, and 5-step verification pipeline. Use when creating/modifying React components in frontend/src/, especially shared/ where quality gates are mandatory. Triggers on "create component", "verify frontend", "storybook coverage", "перевір фронтенд", "frontend flow". Goal - all verification passes before task completion, knowledge captured in vault.