GitHub
genetic-algorithms
Genetic Algorithms for AI optimization - EvoPrompt, hyperparameter tuning, evolutionary strategies.
☆ 0查看技能
research llm ai AI 技能
发现 research llm ai 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
分类目录: research llm ai
research llm ai 清除筛选
全部技能
GitHub
ml-model-deployment
Serve models with A/B testing, monitoring, retraining.
☆ 0查看技能
GitHub
ai-engineer
AI Engineer building LLM features with focus on reliability, evals, cost control, latency, and user trust.
☆ 0查看技能
GitHub
new-feature-planner
Interactive feature planning through conversational interview
☆ 0查看技能
GitHub
compound-concepts
Analyzes conversations for automation, systematization, and delegation opportunities using compound engineering principles
☆ 0查看技能
GitHub
strong-prompt
Analyze user requests to ensure clarity, safety, and strategic alignment without causing "Prompt Fatigue."
☆ 0查看技能
GitHub
personal-preferences
Apply personal preferences to all conversations - Chinese responses, modern tech stack, concise communication
☆ 0查看技能
GitHub
mem0-memory-management
This skill should be used when the user asks about "memory", "remember this", "what do you know about me", "recall", "forget this", "search memories", "save preference", or when Claude needs guidance on using m...
☆ 0查看技能
GitHub
research
Research Agent role responsible for its domain tasks. Activate when needed.
☆ 0查看技能
GitHub
ai-coaching-analysis
GPT-powered hand analysis, coaching, and personalized feedback
☆ 0查看技能
GitHub
parallel-development
Run multiple Claude Code sessions simultaneously using git worktrees. Use when discussing parallel work, worktrees, concurrent development, or multiple sessions.
☆ 0查看技能
GitHub
lean4-prove
Retrieval-augmented Lean4 proof generation. Queries 94k+ exemplars from DeepSeek-Prover V1+V2, uses hybrid search (BM25 + semantic + graph), generates via Claude, compiles in Docker, retries on failure.
☆ 0查看技能
GitHub
call-cursor-agent
Call cursor-agent to perform a task.
☆ 0查看技能
GitHub
empty-state-compassion
Use this agent to redesign empty states with encouragement and gentle guidance instead of just "No items yet". User: "Empty states just say 'No items' with no context" Agent: Use empty-state-compassion to add...
☆ 0查看技能
GitHub
agent-ops-create-skill
Create new AgentOps skills via interactive interview. Supports from-scratch and clone modes with tiered complexity.
☆ 0查看技能
GitHub
ai-empathy
Use this agent to fix the AI Concierge system prompt to prioritize empathy and compassionate responses for death planning context. THIS IS CRITICAL. User: "The AI feels cold and task-focused" Agent: Use ai-em...
☆ 0查看技能
GitHub
github
GitHub Copilot skills 路由器與專案整合指引 - 提供 skills 自動載入、README.md 強制維護、軟路由機制
☆ 0查看技能
GitHub
grief-aware-executor
Use this agent to create specialized "Executor Mode" with grief-aware language and simplified workflows for users handling a loved one's estate. User: "Executors see the same interface as people planning" Age...
☆ 0查看技能
GitHub
meta-evolve
Evolve agent prompts using genetic algorithms and historical performance data
☆ 0查看技能
GitHub
meta-improve
Master weekly improvement pipeline orchestrating all meta-learning commands
☆ 0查看技能
GitHub
generate-image
Generate an image for a worldbuilding entity using OpenAI's gpt-image-1.5 model. Reads the filled prompt from the entity file, generates the image, downloads it locally, and updates the entity to reference it.
☆ 0查看技能
GitHub
strands-agent-architect
Design, build, deploy, and troubleshoot AI agents using AWS Strands Agents Framework (PRIMARY), Google ADK v1.0, A2A (Agent-to-Agent) protocols, and AWS Bedrock AgentCore. Use when creating new agents, implemen...
☆ 0查看技能
GitHub
gemini-cli
Gemini CLIを呼び出して、Claude Codeの機能を補完する。以下の場合に使用: (1) マルチモーダル分析 - 画像/音声/動画/PDFファイルの処理 (2) 大規模コンテキスト分析 - プロジェクト全体のコード分析（100万トークン活用） (3...
☆ 0查看技能
GitHub
aristotle-emulator
Эмулирует рабочий процесс системы Aristotle для автономного доказательства теорем в Lean 4. Принимает на вход утверждение теоремы и опционально — набросок доказательства на естественном языке.
☆ 0查看技能
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。