Claude Skills by lidge-jun

Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.

Train/fine-tune LLMs using TRL on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO, reward modeling, GGUF conversion, dataset validation, hardware selection, cost estimation, Trackio monitoring, and model persistence. Invoke for cloud GPU training or GGUF conversion.

HWP/HWPX create, read, edit, review, template-fill, QA. Triggers: 한글, .hwp, .hwpx, HWP, HWPX, Korean documents, 한컴오피스, OWPML.

Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background removal or replacement, transparent background, product shots, concept art, covers, or batch variants); run the bundled CLI (`scripts/image_gen.py`) and require `OPENAI_API_KEY` for live calls.

Detects fail-open insecure defaults (hardcoded secrets, weak auth, permissive security) that allow apps to run insecurely in production. Use when auditing security, reviewing config management, or analyzing environment variable handling.

Demand forecasting, safety stock optimization, replenishment planning, and promotional lift estimation at multi-location retailers. Includes forecasting method selection, ABC/XYZ analysis, seasonal transition management, and vendor negotiation frameworks. Use when forecasting demand, setting safety stock, planning replenishment, managing promotions, or optimizing inventory levels.

Draft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications for fundraising. Use when the user wants outreach to angels, VCs, strategic investors, or accelerators and needs concise, personalized, investor-facing messaging.

Pattern for progressively refining context retrieval in multi-agent workflows.

Java coding standards for Spring Boot services: naming, immutability, Optional usage, streams, exceptions, generics, and project layout.

Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.

Kotlin Coroutines and Flow patterns for Android and KMP — structured concurrency, Flow operators, StateFlow, error handling, and testing.

JetBrains Exposed ORM patterns including DSL queries, DAO pattern, transactions, HikariCP connection pooling, Flyway migrations, and repository pattern.

Ktor server patterns including routing DSL, plugins, authentication, Koin DI, kotlinx.serialization, WebSockets, and testApplication testing.

Idiomatic Kotlin patterns, best practices, and conventions for building robust, efficient, and maintainable Kotlin applications with coroutines, null safety, and DSL builders.

Kotlin testing patterns with Kotest, MockK, coroutine testing, property-based testing, and Kover coverage. Follows TDD methodology with idiomatic Kotlin practices.

Laravel architecture patterns, routing/controllers, Eloquent ORM, service layers, queues, events, caching, and API resources for production apps.

Laravel security best practices for authn/authz, validation, CSRF, mass assignment, file uploads, secrets, rate limiting, and secure deployment.

Test-driven development for Laravel with PHPUnit and Pest, factories, database testing, fakes, and coverage targets.

Verification loop for Laravel projects: env checks, linting, static analysis, tests with coverage, security scans, and deployment readiness.

Transcribe audio lectures into structured markdown notes using LLM-based STT (Gemini 3 Flash Preview) with contextual prompting. Supports PDF slide guides, domain-aware term hints, and local Whisper fallback. Triggers: "강의 전사", "STT", "lecture transcription", "오디오 전사", "강의 녹음", "audio to text", "lecture notes", "음성 변환", "녹음 텍스트", "전사해줘", "transcribe", "whisper"

Manage issues, projects & team workflows in Linear. Use when the user wants to read, create or updates tickets in Linear.

Explain lint errors and propose fixes. Use when a junior developer needs help resolving common lint or format warnings.

Summarize noisy logs into likely causes and next steps. Use when a junior developer needs help interpreting logs.

Freight exception handling: shipment delays, damages, losses, carrier disputes. Includes escalation protocols, carrier-specific behaviors, claims procedures, and judgment frameworks.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Persistent long-term memory across sessions. Search, read, and save durable knowledge in the current instance; use dashboard memory only for explicit read-only cross-instance lookup.

Configures Python projects with modern tooling (uv, ruff, ty). Use when creating projects, writing standalone scripts, or migrating from pip/Poetry/mypy/black.

Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).

Deploy web projects to Netlify using the Netlify CLI (`npx netlify`). Use when the user asks to deploy, host, publish, or link a site/repo on Netlify, including preview and production deploys.

Capture conversations and decisions into structured Notion pages; use when turning chats/notes into wiki entries, how-tos, decisions, or FAQs with proper linking.

Prepare meeting materials with Notion context and Codex research; use when gathering context, drafting agendas/pre-reads, and tailoring materials to attendees.

Research across Notion and synthesize into structured documentation; use when gathering info from multiple Notion sources to produce briefs, comparisons, or reports with citations.

Turn Notion specs into implementation plans, tasks, and progress tracking; use when implementing PRDs/feature specs and creating Notion plans + tasks from them.

Notion API for creating and managing pages, databases, and blocks.

Process, convert, OCR, extract, redact, sign, and fill documents using the Nutrient DWS API. Works with PDFs, DOCX, XLSX, PPTX, HTML, and images.

Nuxt 4 app patterns for hydration safety, performance, route rules, lazy loading, and SSR-safe data fetching with useFetch and useAsyncData.

Work with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli.

Accessibility checks and remediation for Office documents. Alt-text validation, color contrast, reading order, heading hierarchy, and WCAG 2.1 AA compliance.

CJK (Korean/Japanese/Chinese) text handling overlay for OfficeCLI. Ensures correct fonts, language tags, line-break rules, and encoding for East Asian documents.

Pandas DataFrame → Excel pipeline. Export CSV/TSV from pandas, import with officecli, then format and validate. Supports CJK headers, number formatting, conditional formatting, and charts.

Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, model capabilities or limits); prioritize OpenAI docs MCP tools and restrict any fallback browsing to official OpenAI domains.

Control Philips Hue lights and scenes via the OpenHue CLI.

PDF RAG pipeline: text extraction + Apple Vision OCR + API embedding + cosine search. Triggers: "pdf 읽기", "pdf rag", "문서 검색", "pdf 분석", "pdf 청크", "pdf-expert", "pdf 임베딩"

Use when tasks involve reading, creating, editing, or reviewing PDF files. Visual layout checks via Poppler (pdftoppm). Python tools: reportlab (create), pdfplumber/pypdf (extract), nano-pdf (natural-language page editing). Also covers DOCX→PDF conversion via soffice.

Modern Perl 5.36+ idioms, best practices, and conventions for building robust, maintainable Perl applications.

Comprehensive Perl security covering taint mode, input validation, safe process execution, DBI parameterized queries, web security (XSS/SQLi/CSRF), and perlcritic security policies.

Perl testing patterns using Test2::V0, Test::More, prove runner, mocking, coverage with Devel::Cover, and TDD methodology.

Write-time code quality enforcement using Plankton — auto-formatting, linting, and agent-powered fixes on every file edit via hooks.

PostgreSQL database patterns for query optimization, schema design, indexing, and security.

Execute read-only SQL queries against multiple PostgreSQL databases. Use when: (1) querying PostgreSQL databases, (2) exploring database schemas/tables, (3) running SELECT queries for data analysis, (4) checking database contents. Supports multiple database connections with descriptions for intelligent auto-selection. Blocks all write operations (INSERT, UPDATE, DELETE, DROP, etc.) for safety.