Agent Skills

Prompt Caching Patterns

ai-toolkit

Guidelines and patterns for implementing prompt caching with Anthropic APIs to reduce input-token costs and latency, including TTLs, breakpoints, and hit-rate m

Prompt Engineering Patterns

openclaw-master-skills

A practical collection of prompt engineering techniques and patterns for building reliable, controllable LLM prompts: CoT, few-shot, structured outputs, templat

Claw Router

claw-router

Trait-based router that scores messages by complexity and task type to automatically select the most suitable AI model for each request.

Total Recall

total-recall

Autonomous agent memory that passively observes session transcripts, compresses them into prioritized notes, consolidates redundancies, and recovers missed cont