Agent Building skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

kaggle-benchmarks

Write benchmark tasks to evaluate LLMs using the kaggle_benchmarks Python library. Covers task decorators, structured outputs, assertions, tools, dataset evaluation (including failure-tolerant retry patterns for large datasets), and multi-turn conversations.

183 repo starsObserved in 1 repos

Agent Building

claude-delegate

接收 CC 派发任务 + 反向调用 CC

182 repo starsObserved in 2 repos

Agent Building

cunzhi

寸止协议 - Pause and wait mechanism for human confirmation at critical decision points. Prevents AI from proceeding autonomously past important checkpoints. Core safety and collaboration mechanism.

182 repo starsObserved in 2 repos

Agent Building

multi-ai

Multi-AI coordination for Claude Code, Codex CLI, and Gemini CLI. Handles task delegation, context handoff, and result synchronization across different AI engines. Works with orchestrator.yaml.

182 repo starsObserved in 2 repos

Agent Building

multi-ai-sync

多 AI 协调同步协议 - 解决 Claude/Codex/Gemini 如何协同工作

182 repo starsObserved in 2 repos

Agent Building

phase-router

Intent recognition and workflow routing. Analyzes user input to determine task type and routes to appropriate agent. Core decision layer.

182 repo starsObserved in 2 repos

Agent Building

reflexion

E 阶段自我反思

182 repo starsObserved in 2 repos

Agent Building

inspire

Inspire Platform Operating Model For Agents: Decide Workspace, Resources, Paths, Workload Type, Observation, Cleanup, And Load Focused References; Use CLI Help For Command Syntax.

182 repo starsObserved in 1 repos

Agent Building

lessons-loop

自我改进循环 — 用户纠正后触发, 写入 knowledge.md 教训段

182 repo starsObserved in 1 repos

Agent Building

model-router

Intelligent task-to-model routing based on benchmark data. Routes tasks to Claude Code or Codex CLI based on task type and model strengths. New in v8.0.

182 repo starsObserved in 1 repos

Agent Building