Flaky tests often fail because they guess how long async work takes. This skill shows Claude, Codex, and Claude Code how to wait for real conditions instead of fixed delays.

Skill authors need clear evidence from real agent sessions. This skill extracts transcripts and turns them into prompts for improving or creating skills.

Complex code projects are hard to understand, plan, and improve consistently. This skill provides runtime workflows for exploration, learning, planning, implementation, memory, and reflection.

Large codebases make text search miss structural patterns. This skill guides Claude, Codex, and Claude Code to use ast-grep for syntax-aware search, linting, and rewrites.

Code edits can lose context, overwrite work, or be hard to reverse. Safe Edit adds backups, diffs, rollback notes, modular planning, and verification.

Messy repositories make navigation, ownership, and refactoring harder. This skill provides safe folder layouts and cleanup workflows for JavaScript and frontend projects.

Feature ideas often fail because requirements and task boundaries stay unclear. This skill turns discovery answers into a structured implementation plan.

Performance regressions are hard to catch when teams review LCP, INP, and CLS late. This skill gives Claude, Codex, and Claude Code focused guidance for measuring, diagnosing, and fixing Core Web Vitals issues.

Hardcoded values make code harder to change and can expose secrets. This skill guides reviews toward constants, configuration files, and environment variables.

Connecting AI assistants to services requires careful server design. This skill guides planning, TypeScript structure, tool annotations, testing, and evaluation for MCP servers.

Large implementation files are hard to review, test, and maintain. This skill checks line counts and guides modular refactoring with clear thresholds.

Weak error handling hides failures and exposes technical messages to users. This skill guides Claude, Codex, and Claude Code toward safer recovery patterns.

API teams lose time when contracts are unclear or written after implementation. This skill guides OpenAPI-first design, TypeScript generation, validation, documentation, and mock workflows.

Accessibility defects make products difficult to use and increase compliance risk. This skill guides Claude, Codex, and Claude Code through WCAG 2.2 checks for UI work.

Agent frameworks often hide how tools are registered, validated, and retried. This skill guides a structured review of tool abstractions, schemas, built-in tools, and error feedback.

Multi-agent systems can hide brittle handoffs, shared-state coupling, and unclear communication paths. This skill guides Claude, Codex, or Claude Code to map coordination models and produce a structured review.

Agent frameworks often hide how context, memory, and token budgets interact. This skill gives Claude, Codex, and Claude Code a structured way to inspect memory flow and compare design choices.

Agent framework audits often miss the translation layer between internal state and provider APIs. This skill guides Claude, Codex, and Claude Code through message formats, tool calls, streaming events, and provider abstractions.

Agent frameworks hide concurrency, topology, events, and hooks across many files. This skill guides Claude, Codex, or Claude Code through a structured execution-engine review.

Framework extension points can be hard to compare across codebases. This skill guides Claude, Codex, and Claude Code through abstraction, dependency injection, and configuration analysis.