Search skill packs and skills together

Complex agent work can fail when one context window carries every task. This skill helps Claude, Codex, and Claude Code design agent systems with clear handoffs.

AI agents can mark work complete without proof, which creates false completion risk. This skill requires independent evidence before task completion is accepted.

AI agents often lose useful context between sessions. This skill gives a structured AgentDB workflow for session memory, long-term storage, and pattern learning.

Teams need relevant document retrieval for RAG and knowledge bases. This skill guides AgentDB setup, embedding storage, indexing, API search, and relevance tuning.

Large vector databases can become slow, memory-heavy, and hard to benchmark. This skill provides a structured AgentDB optimization workflow for quantization, HNSW indexing, caching, and validation.

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.

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

Complex AI work can become slow when one agent handles every task. This skill shows how to coordinate specialized swarms for research, development, testing, and analysis.

Agents often need simple dice rolls for games, examples, or randomized test values. This skill runs a Rust dice roller through Enact and returns individual rolls with the total.

Expo teams often need web libraries inside native apps without rewriting them. This skill guides Claude, Codex, and Claude Code through safe DOM component patterns.

Publishing ADK agents to Gemini Enterprise requires the correct registration mode, resource IDs, and permissions. This skill guides Claude, Codex, or Claude Code through safe CLI registration and Agent Registry management.

Skill authors need evidence that a skill works and does not expose users to avoidable risk. SkillCheck reviews structure, security, evals, scripts, and outputs through tiered checks.