GitHub
dspy-configuration
DSPy configuration, LM setup, caching, and version management. Use when configuring language models, enabling caching, managing dependencies, or setting up multi-provider configurations.
☆ 1查看技能
数据与 AI AI 技能
发现 数据与 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: 数据与 AI
数据与 AI 清除筛选
全部技能
GitHub
sub-agents
Create and configure Claude Code sub-agents with custom prompts, tools, and models
☆ 1查看技能
GitHub
wan2122-i2v-comfyui
This skill should be used when the user asks to "implement Wan I2V", "set up Wan2.1", "configure Wan2.2", "image to video with Wan", "ComfyUI video generation", "low VRAM video generation", "GGUF Wan model", "s...
☆ 1查看技能
GitHub
recall
Query memory system for relevant learnings from past sessions
☆ 1查看技能
GitHub
agentica-claude-proxy
Guide for integrating Agentica SDK with Claude Code CLI proxy
☆ 1查看技能
GitHub
math-help
Guide to the math cognitive stack - what tools exist and when to use each
☆ 1查看技能
GitHub
sag
ElevenLabs text-to-speech with mac-style say UX.
☆ 1查看技能
GitHub
agentica-spawn
Spawn Agentica multi-agent patterns
☆ 1查看技能
GitHub
code-fixer
Skill especializada para diagnosticar y reparar errores en el motor AGCCE v4.0. Integra análisis de telemetría (logs/telemetry.jsonl), estado del Blackboard, y recuperación de agentes (Graceful Recovery).
☆ 1查看技能
GitHub
error-recovery
Handle errors, timeouts, and failures in multi-agent workflows. Use when dealing with external model timeouts, API failures, partial success, user cancellation, or graceful degradation. Trigger keywords - "erro...
☆ 1查看技能
GitHub
spec-task-management
This skill should be used when the user asks to "analyze a specification", "break down a spec", "create tasks from a PRD", "decompose requirements", "generate a task list from a design document", or mentions wo...
☆ 1查看技能
GitHub
codex-agent
Run Codex tasks via the ai_cli Task Tool runner.
☆ 1查看技能
GitHub
dspy-optimization-workflow-for-skills-fleet
Use when optimizing DSPy programs in skills-fleet, implementing quality improvements, using optimization API endpoints, or troubleshooting DSPy issues. Complete 3-phase implementation guide (signatures → traini...
☆ 1查看技能
GitHub
llm-ops-engineer
Specialist in deploying, fine-tuning, and monitoring Large Language Models (LLMs). Expert in RAG pipelines, vector databases, prompt engineering, and maintaining robust AI infrastructure.
☆ 1查看技能
GitHub
agents-md-guidelines
Guidelines for writing small, stable AGENTS.md files. Use when creating, refactoring, or reviewing AGENTS.md.
☆ 1查看技能
GitHub
agentica-prompts
Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity
☆ 1查看技能
GitHub
claudeception-setup
How to set up Claudeception continuous learning in a project. Use when: (1) User asks to install or set up Claudeception (2) User wants automatic skill extraction (3) "embedded git repository" warning when addi...
☆ 1查看技能
GitHub
session-start-routine
Execute work session initialization routine at conversation start. Identifies new skills, researches improvements for existing skills, and updates skill library. Triggers automatically at session start.
☆ 1查看技能
GitHub
loogle-search
Search Lean 4 mathlib using Loogle API
☆ 1查看技能
GitHub
voice-command-intelligence
Design and optimize voice commands, handle speech recognition, execute smart actions with context awareness
☆ 1查看技能
GitHub
prompt-engineering-specialist
Expert in crafting, optimizing, and evaluating effective prompts for Large Language Models. Specializes in advanced prompting techniques (CoT, ReAct, Few-Shot) to maximize model performance and reliability.
☆ 1查看技能
GitHub
xml-standards
XML tag structure patterns for Claude Code agents and commands. Use when designing or implementing agents to ensure proper XML structure following Anthropic best practices.
☆ 1查看技能
GitHub
agent-orchestration
Agent Orchestration Rules
☆ 1查看技能
GitHub
interview
Gather structured user input via web form. Use when you need multiple clarifying questions answered, collecting design mockups/images, or getting user decisions on implementation choices. Better than sequential...
☆ 1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。