This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.

Mandatory iPolloWork code-change gate for modern, minimal, performant, reuse-first implementation and clean repository ownership. Use whenever AI creates, edits, deletes, or refactors application code, server code, packages, scripts, tests, dependencies, schemas, routes, UI, or generated-file workflows. Reuse existing code before creating files, keep one source of truth, prevent parallel implementations and junk directories, justify every new file or dependency, and audit the current change before completion.

Official PyTorch implementation of "VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization" (CVPR 2021)

Comprehensive guide for Go database access — parameterized queries, struct scanning, NULLable columns, transactions, isolation levels, SELECT FOR UPDATE, connection pool, batch processing, context propagation, and migration tooling. Use when writing, reviewing, or debugging Golang code that interacts with PostgreSQL, MariaDB, MySQL, or SQLite; for database testing; or for questions about database/sql, sqlx, or pgx. Does NOT generate database schemas or migration SQL.

SPD V1 Batch. Process large, user-supplied sets of legitimate product, software, startup, app, and AI-tool directory URLs across Windows, macOS, and Linux-capable environments through normalization, deduplication, execution sharding, verification-first queues, authorization-controlled form work, idempotent submission, recovery, and truthful throughput reporting. Use when coverage and operational throughput matter more than deep per-site quality analysis. Do not use for ranking manipulation, bulk link spam, invented data, CAPTCHA bypass, paid-link acquisition, forced reciprocal links, or routes prohibited by a site's terms.

A curated collection of reusable AI agent skills (SKILL.md) for Claude Code, covering domains like writing, translation, and data conversion with bilingual support.

Where things live in the portal-tunnel repo (sdk/portal/types/utils/cmd/discovery/x402/frontend/extensions) and where new code belongs. Use when locating functionality or deciding where to add code.

Chinese text normalization for speech processing

SEAN: Image Synthesis with Semantic Region-Adaptive Normalization (CVPR 2020, Oral)

A TensorFlow implementation of Group Normalization on the task of image classification

Convert born-digital, scanned, or mixed PDFs into auditable Markdown while preserving reading order, equations, source-page anchors, and information-bearing images as adjacent non-original text descriptions. Use this skill whenever a user asks to transcribe, OCR, understand, or convert a PDF into Markdown, especially for scanned PDFs, image-heavy pages, formulas, multi-column layouts, page or section ranges, or token-efficient reuse. LT2MD (Long Transcribe to Markdown) is a workflow contract, not a replacement for a PDF parser or OCR/VLM backend.

Radical simplification, red-teaming, and Occam's Razor devil's advocate for software architecture, PRDs, agent workflows, and technical designs. Challenges feature creep, speculative abstractions, and bloated specifications by proposing minimum viable primitives that deliver 90% of value with 10% of moving parts. Activate when reviewing complex technical proposals, pruning bloated architectures, red-teaming design docs, eliminating speculative features, or seeking the simplest possible path to production.