Machine Learning

Guidance for querying ML model leaderboards and benchmarks (MTEB, HuggingFace, embedding benchmarks). This skill applies when tasks involve finding top-performing models on specific benchmarks, comparing model performance across leaderboards, or answering questions about current benchmark standings. Covers strategies for accessing live leaderboard data, handling temporal requirements, and avoiding common pitfalls with outdated sources.

Guidance for filtering JavaScript and XSS attack vectors from HTML while preserving original formatting. This skill should be used when tasks involve removing script content, sanitizing HTML, filtering XSS payloads, or creating security filters that must preserve the original document structure unchanged.

Native HTML dialog patterns for Rails with Turbo and Stimulus. Use when building modals, confirmations, alerts, or any overlay UI. Triggers on modal, dialog, popup, confirmation, alert, or toast patterns.

Read project config from .agents.yml and .agents.local.yml with local overrides. Supports dot notation for nested fields. Invoke with args "<field> <default>".

This skill provides guidance for retrieving and verifying information from dynamic ML leaderboards (MTEB, Scandinavian Embedding Benchmark, HuggingFace leaderboards, etc.) with specific temporal requirements. It should be used when tasks involve finding top-performing models, rankings, or benchmark results as of a specific date, especially when the data source is frequently updated.

Capture solved problems as categorized documentation with YAML frontmatter for fast lookup

Guidance for building CompCert, a formally verified C compiler. This skill applies when tasks involve compiling CompCert from source, setting up Coq/OCaml environments with opam, or building software with strict proof assistant dependencies. Use for CompCert compilation, Coq-dependent project builds, or formal verification toolchain setup.

Builds interactive HTML presentation with 6 tabs (Overview, Requirements, Architecture/C4, Tech Spec, Roadmap, Guides). Creates presentation/README.md hub. L2 Worker under ln-100-documents-pipeline.

Test, validate, and add new AI models to the eval suite. Use when user asks to add new models, test model access, check pricing, or update models.yml.

This skill guides writing cloud-init configurations for VM provisioning. Use when creating user_data blocks in Terraform/OpenTofu, or cloud-init YAML for AWS, DigitalOcean, GCP, or Azure instances.

Guidance for creating Python packages and serving them via a local PyPI server. This skill applies when tasks involve building Python packages (with pyproject.toml or setup.py), setting up local package repositories, or serving packages via HTTP for pip installation. Use when the goal is to create installable Python packages and make them available through a local index URL.

When html or jinja are being written or edited.

Enforce Maven POM dependency ordering rules. This skill should be used when editing pom.xml files.

Guidance for building and training with the Caffe deep learning framework on CIFAR-10 dataset. This skill applies when tasks involve compiling Caffe from source, training convolutional neural networks on image classification datasets, or working with legacy deep learning frameworks that have compatibility issues with modern systems.

This skill provides guidance for XSS filter bypass tasks where the goal is to craft HTML payloads that execute JavaScript despite sanitization filters. Use this skill when tasks involve bypassing HTML sanitizers (like BeautifulSoup), exploiting parser differentials between server-side sanitizers and browsers, or security testing/CTF challenges involving XSS filter evasion.

Guidance for processing, classifying, and extracting data from financial documents (invoices, receipts, statements). This skill should be used when tasks involve OCR extraction, document classification, data validation from financial PDFs/images, or batch processing of financial documents. Covers safe file operations, incremental testing, and data extraction verification.

This skill guides deploying Rails applications with Kamal. Use when configuring deploy.yml, setting up accessories, managing secrets, or preparing servers for container deployment.

Guidance for implementing minimal GPT-2 inference in constrained environments (code golf challenges). This skill should be used when implementing neural network inference from scratch, parsing binary checkpoint formats, implementing BPE tokenization, or working on code golf challenges involving ML models. Covers verification strategies and common pitfalls for checkpoint parsing and model inference.

This skill provides guidance for merging data from multiple heterogeneous sources (CSV, JSON, Parquet, XML, etc.) into unified output formats with conflict detection and resolution. Use when tasks involve combining data from different file formats, field mapping between schemas, priority-based conflict resolution, or generating merged datasets with conflict reports.

Guide for building CompCert, the formally verified C compiler, from source. This skill should be used when compiling, building, or installing CompCert, or when working with Coq-based software that has strict dependency version requirements. Covers OCaml/opam setup, Coq version compatibility, memory management, and common build pitfalls.