Total 50,673 skills, AI & Machine Learning has 8493 skills
Showing 12 of 8493 skills
Use when creating, modifying, or refactoring Claude Code skills that require structured multi-agent review and quality validation
Expert prompt engineering for creating effective prompts for Claude, GPT, and other LLMs. Use when writing system prompts, user prompts, few-shot examples, or optimizing existing prompts for better performance.
Researches archives, contemporary accounts, and timeline reconstruction. Use when the album subject involves historical events that need primary source verification.
Determine the escalation path (Researcher vs. Human) and format the appropriate handoff. Used when the fix-engine has exhausted retry attempts.
검증문서 생성 필수 규칙 - 모든 Chapter Generator 에이전트 공통
Text-to-speech synthesis with ElevenLabs and system voices
Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.
Interact with the SlipBox semantic knowledge engine and read notes from PrivateBox. Use when capturing ideas, searching notes, browsing your knowledge graph, or running semantic analysis passes (link, cluster, tension).
セッション管理の総合窓口。初期化・記憶・状態を一手に引き受けます。Use when managing Claude Code sessions, /session command. Do NOT load for: app user sessions, login state, authentication features.
Guide VibeCoder (non-technical users) in natural language development. Use this when users ask what to do next, how to use the system, need help, or are stuck. Do NOT load this for: technical user work, direct implementation requests, or reviews.
Use when an existing agent already works without Prefactor and you need to add tracing for runs, llm calls, tool calls, and failures with minimal behavior changes.
Generate and prioritize US equity long-side edge research tickets from EOD observations, then export pipeline-ready candidate specs for trade-strategy-pipeline Phase I. Use when users ask to turn hypotheses/anomalies into reproducible research tickets, convert validated ideas into `strategy.yaml` + `metadata.json`, or preflight-check interface compatibility (`edge-finder-candidate/v1`) before running pipeline backtests.