Teams need code that is correct, readable, maintainable, and aligned with project standards. This skill guides style review, safe refactoring, documentation checks, and quality reporting after functionality is validated.

Sequential AI workflows often lose context between steps. This skill defines stream-chain patterns that pass each result into the next task.

Product launches need coordinated research, development, marketing, sales, and support work. This skill provides a 10-week SOP with agent assignments, deliverables, and metrics.

Large reviews can miss security, performance, and documentation issues. This skill guides Claude, Codex, and Claude Code through a staged multi-agent review workflow.

Building a production REST API requires aligned requirements, implementation, testing, documentation, and deployment. This skill provides a two-week TDD workflow for coordinating specialized agents.

Bug fixes can fail when teams skip root cause analysis. This skill guides Claude, Codex, and Claude Code through diagnosis, implementation, tests, and validation.

Repeated AI workflows are slow when users rely on long natural language prompts. This skill helps define concise slash commands with routing, validation, chaining, and help text.

Creating reusable AI skills can become inconsistent when requirements, resources, and validation steps are unclear. Skill Forge provides a structured process for designing, testing, and packaging production-ready skills.

Complex skills often produce inconsistent results when one prompt handles every step. This skill guides Claude Code to create reusable skills backed by specialist agents.

Sandbox settings are hard to balance when projects need networks, Docker, or local servers. This skill guides Claude Code policy choices with clear trade-offs.

Complex projects fail when teams plan from assumptions and miss known risks. This skill guides evidence collection, task planning, and pre-mortem review before implementation.

Agents often repeat weak strategies because outcomes are not captured for later use. This skill shows how to record experiences, learn patterns, and recommend better strategies with ReasoningBank.

AI agents often repeat weak decisions because they do not retain evaluated reasoning. This skill guides trajectory tracking, verdict scoring, and pattern reuse with AgentDB.

Quick code reviews often miss security, style, test, and placeholder issues. This skill runs parallel checks and returns a severity-ranked quality report.

Reusable AI prompts often fail because goals, context, and output requirements are unclear. This skill helps you analyze, restructure, and improve prompts with systematic checks.

Production releases can fail when quality, security, documentation, and rollback checks happen late. This skill guides Claude, Codex, and Claude Code through a structured pre-deployment audit.

PowerPoint decks are hard because they combine analysis, narrative, layout, and accessibility requirements. This skill gives Claude, Codex, and Claude Code a structured workflow for planning, generating, and validating presentations.

Claude Flow swarms can slow down when bottlenecks are hard to see. This skill guides Claude, Codex, and Claude Code through performance reports and optimization planning.

Complex implementation plans are hard to assign, validate, and integrate across many agents. This skill provides a structured Loop 2 workflow for agent selection, parallel execution, testing, and delivery packaging.

Developers need structured collaboration when building, testing, and refactoring code. This skill guides pair programming sessions with modes, reviews, tests, and quality checks.