Search skill packs and skills together

Teams often miss blockers and cycles when reading issue lists by hand. This skill turns Beads data into focused triage, planning, and agent workflow guidance.

Large AI coding projects fail when implementation starts before the architecture is clear. This skill provides a planning workflow for detailed markdown plans, model review, and task handoff.

Multi-agent work can fail when tasks overlap or depend on hidden context. This skill helps Claude, Codex, and Claude Code plan bounded subagent assignments.

iOS simulator debugging often requires many separate build, launch, UI, and log steps. This skill gives Claude a clear XcodeBuildMCP workflow for inspecting app behavior in one guided session.

Teams lose time choosing the next CC-DevFlow command during complex delivery work. This skill maps project status, phase gates, and user intent to the right Claude, Codex, or Claude Code workflow.

Distributed vector search needs careful replication, metrics, monitoring, and deployment planning. This skill gives a phased AgentDB workflow for scalable hybrid search systems.

Reinforcement learning projects need structured setup, training loops, evaluation, and deployment checks. This skill guides AgentDB users through algorithm selection, training, benchmarking, and production rollout.

Large AI projects need clear agent roles, durable memory, and reliable decisions. This skill guides Claude Flow hive minds with queen-led coordination and consensus 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.

Agent workflows often lose context between stages. This skill shows how to pass outputs through memory or streams with validation steps.

Pydantic AI projects need clear patterns for agents, tools, dependencies, and structured outputs. This skill provides concise guidance and examples for building type-safe Python agent applications.

Inconsistent error handling can hide failures and confuse users. This skill guides Claude, Codex, and Claude Code toward clear exceptions, validation, cleanup, and recovery paths.