Data & AI

Convert web pages to Markdown format using Jina AI's reader service. Use when the user asks to convert, generate, create, transform, or download a web page, website, or URL into Markdown, MD, or md format. Handles various phrasings like "convert this page to markdown", "generate markdown from this website", "create md file from this URL".

Docker and Kubernetes containerization best practices. Use when writing Dockerfiles, docker-compose files, or Kubernetes manifests. Triggers on mentions of Docker, container, Dockerfile, docker-compose, Kubernetes, k8s, pods, deployments, helm.

KPI for measuring first-pass verification success. Tracks how often verification passes on the first attempt. Use to reduce wasted cycles from verification failures.

Multi-agent coordination patterns for OpenCode swarm workflows. Use when working on complex tasks that benefit from parallelization, when coordinating multiple agents, or when managing task decomposition. Do NOT use for simple single-agent tasks.

Tool usage patterns for non-prompting file operations - use Glob, Read, Grep instead of Bash commands to avoid user interruptions in all agents and commands

Proactively investigates Go SSO codebase to understand authentication flows, trace gRPC request paths, analyze clean architecture patterns, and provide comprehensive backend code insights. Use when users ask about SSO implementation, service structure, database queries, or need to understand how authentication/authorization works.

Update and clean up project documentation files (primarily .ai/features/, but also README.md, PROGRESS_TRACKER.md, CLAUDE.md, and other .md files). Use when user requests documentation cleanup, organization, or updates for any feature, module, or project documentation (e.g., 'update photo viewer docs', 'clean up README', 'organize documentation'). Removes code snippets, outdated details, and redundant information while preserving essential architectural decisions and technical context.

Selects and configures agents from the agents repo based on PRD tech stack.Runs after task decomposition, before specification generation.

CLAUDE Framework coding standards for code quality, naming conventions, error handling, security, testing, database, and logging

Runs local BLAT searches for DNA sequence alignment against hg38 or CHM13 using local .2bit references. Use when a user wants to align a DNA sequence without relying on UCSC API access.

Agent Skill: Guide for structuring Netresearch skill repositories. Use when creating skills, standardizing repos, or setting up composer/release workflows. By Netresearch.

Meta-skill that teaches how to design Claude Code skills following the Box Factory philosophy. Helps you understand when to create skills, how to structure them for low maintenance, and how to add value beyond documentation. Use when creating or reviewing skills.

Psychrometric Analysis Agent

Complete markdown guide for Universal Notion Uploader. Covers 14 element types (headings, callouts, highlights, toggles, embeds, columns, databases), upload modes, and API constraints.

Automatically backs up files, saves diffs, uses agents/skills, and ensures modular code (<200 lines) before any implementation. Use this skill for ALL code changes to ensure safe, reversible, and clean implementations.

Macroeconomic and market regime analyst. Monitors Fed policy, inflation, GDP, unemployment, and global economic trends to determine overall market risk appetite and sector rotation strategies.

Automated code validation for diff review, change hygiene, and red flag detection. Use when reviewing git diffs, PRs, or changed files for test disabling patterns, secrets, path portability issues, security flags, and large deletions. Supports Python, TypeScript, JavaScript, HTML, and CSS.

Generate pytest test templates for LiquidationHeatmap modules following TDD patterns. Automatically creates RED phase tests with fixtures, coverage markers, and integration test stubs.

Handle Advent of Code answer submissions with intelligent retry logic. Submits answers via aoc-cli, parses responses, handles failures, analyzes edge cases when tests pass but submission fails, and manages exponential backoff. Use when submitting AoC answers, handling submission failures, or implementing retry logic.

Industrial-strength NLP with spaCy 3.x for text processing and custom classifier training. Use when: installing spaCy, selecting models (en_core_web_sm/md/lg/trf), tokenization, POS tagging, named entity recognition, dependency parsing, training TextCategorizer models, troubleshooting errors (E050/E941 model errors, E927 version mismatch, memory issues), batch processing with nlp.pipe, or deploying models to production. Includes data preparation scripts, config templates, and FastAPI serving examples.