Latency issues in MEV systems are hard to isolate across calls and transaction stages. This skill guides span hierarchy, instrumentation, aggregation, and alert thresholds.

Long coding tasks often fail because tests, lint checks, or completion criteria are not retried consistently. This skill provides a bounded loop pattern for Claude, Codex, and Claude Code workflows.

Crypto derivatives teams need rigorous signals, sizing, and backtests. This skill guides DeFi trading research with practical quantitative workflows and risk checks.

Large changes can hide regressions across security, types, performance, and product surfaces. This skill coordinates review checklists and targeted expertise for a structured pre-commit report.

Distributed failures are hard to trace when logs do not share context. This skill guides structured JSON logs and correlation IDs across services.

DeFi registry changes often require synchronized edits across several frontend, backend, shared, and Rust files. This skill gives Claude, Codex, and Claude Code checklists and templates for complete token, protocol, chain, and RPC updates.

DeFi and MEV bots often fail when backtests ignore latency, gas, reorgs, and adversarial orderflow. This skill guides realistic simulation, risk controls, AMM math, and private bundle submission.

DeFi integrations often fail because token units, decimals, and protocol formats are easy to mix up. This skill guides Claude, Codex, and Claude Code through checks for safer protocol code.

Development teams miss recurring framework and security mistakes during busy reviews. This skill routes code changes to targeted pitfall checks and summarizes review concerns.

Code reviews can miss architecture, quality, security, and product risks. This skill guides a structured review and returns prioritized findings.

Cross-language type drift can cause precision loss and contract bugs. This skill guides Claude, Codex, and Claude Code through Rust, TypeScript, and PostgreSQL checks.

Modern product teams need consistent, polished UI guidance. This skill gives Claude, Codex, and Claude Code practical Apple-inspired rules for typography, color, spacing, components, motion, and UX review.

Self-hosted AppFlowy automation requires correct authentication, headers, identifiers, and mutation safeguards. This skill provides documented workflows for API queries, database changes, migrations, snapshots, and rollback.

Visual generation requires careful prompts, parameters, and workflow selection. VisionCraft maps natural-language requests to documented Agnes AI image and video workflows.

Manual OCR of PDFs and screenshots is slow and inconsistent. This skill guides Claude, Codex, and Claude Code to extract document text into structured Markdown files.

Review feedback can be scattered across files, severities, and threads. This skill organizes comments, guides fixes, verifies changes, and posts clear replies.

Pull request merges need consistent validation before repository changes happen. This skill guides Claude, Codex, or Claude Code through checks, confirmation, merge, and cleanup.

Preparing pull requests can miss context, tests, and labels. This skill gathers git history, validates tests, drafts Conventional Commit content, and guides GitHub CLI creation.

Agent-assisted coding can drift into unclear scope, weak validation, or inconsistent style. This skill gives Claude, Codex, and Claude Code structured guidelines for safer collaboration and maintainable delivery.

Mobile projects need clear guidance for setup, platform differences, and common interface patterns. This skill provides focused React Native and Expo workflows for building and troubleshooting mobile apps.