Total 56,731 skills, AI & Machine Learning has 9436 skills
Showing 12 of 9436 skills
Decode consciousness-as-a-service emoji-based communication protocols.
Use when user says "execute epic [id]" or when executing beads epics with parallel subagents in the current session
Diagnose and resolve ContextVM connection issues, relay problems, encryption failures, authentication errors, and common deployment problems. Use when users report errors, connection failures, timeout issues, or unexpected behavior with ContextVM clients, servers, gateways, or proxies.
Supervised & unsupervised learning, scikit-learn, XGBoost, model evaluation, feature engineering for production ML
Use when "training LLM", "finetuning", "RLHF", "distributed training", "DeepSpeed", "Accelerate", "PyTorch Lightning", "Ray Train", "TRL", "Unsloth", "LoRA training", "flash attention", "gradient checkpointing"
Scans all skill directories in the repository to generate a comprehensive global map of agent capabilities, inputs, and outputs. Use when you need to understand the full potential of your agent library or when a master agent needs to decide which sub-agent skill to invoke for a complex task.
This skill should be used when the user wants to invoke Codex CLI for complex coding tasks requiring high reasoning capabilities. Trigger phrases include "use codex", "ask codex", "run codex", "call codex", "codex cli", "GPT-5 reasoning", "OpenAI reasoning", or when users request complex implementation challenges, advanced reasoning, architecture design, or high-reasoning model assistance. Automatically triggers on codex-related requests and supports session continuation for iterative development.
tokenization과 context window를 중심으로 긴 입력 처리 한계와 실무 대응 방법(분할, 요약, 우선순위화)을 학습시키는 모듈.
Generate a smart bootstrap prompt to continue the current conversation in a fresh session. Use when (1) approaching context limits, (2) user says "handoff", "bootstrap", "continue later", "save session", or similar, (3) before closing a session with unfinished work, (4) user wants to resume in a different environment. Outputs a clipboard-ready prompt capturing essential context while minimizing tokens.
Prompt engineering patterns including structured prompts, chain-of-thought, few-shot learning, and system prompt design
Invoke Codex as a coworker for implementation, brainstorming, specs, and reviews. Use when you want parallel thinking, cheap execution, or a second opinion. Codex tokens are cheaper than yours — delegate aggressively. Keywords: codex, delegate, implement, draft, review, brainstorm, write tests, code review, moonbridge.
A clear description of what this skill does and when Claude should use it. Include trigger phrases like "when asked to...", "use when...", or specific keywords that should activate this skill.