Teams need consistent slash commands that route micro-skills without confusing syntax. This skill guides command design, validation, handler generation, testing, documentation, and deployment steps.

Production API builds need clear roles, tests, and deployment gates. This skill organizes agents through planning, TDD implementation, validation, documentation, and blue-green release.

Style drift makes code reviews slower and less consistent. This skill guides Claude, Codex, or Claude Code through scans, reports, safe fixes, and validation.

AI-assisted code changes can be hard to trust before merge. This skill helps teams score outputs, run verification checks, and connect quality gates to CI, rollback, and monitoring workflows.

Placeholder code hides product risk and can reach production with fake behavior. This skill guides Claude, Codex, or Claude Code through a structured audit that finds, prioritizes, and replaces theater with real implementations.

Complex AI work can stall when one agent handles every task. This skill guides Claude, Codex, and Claude Code through agentic-flow swarm patterns for coordinated parallel work.

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.

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.

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.

Self-learning agents need durable memory to compare decisions and improve outcomes. This skill shows AgentDB patterns for trajectories, judgments, distillation, and retrieval.

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.

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.

Machine learning implementation often needs architecture, training, and validation choices aligned together. This skill gives Claude, Codex, and Claude Code a specialist workflow for PyTorch delivery.