发现优质的 AI Agent 技能

来自 openclaw/skills 技能

来自 openclaw/skills 技能

A collection of practical examples demonstrating how to use zotero-cli for various research workflows.

Building stateful agents and multi-step workflows with BAML.

BAML supports multiple language targets beyond Python and TypeScript. The workflow is consistent across all languages: define `.baml` files → run `baml-cli generate` → import generated client.

Generate type-safe LLM extraction code. Use when creating structured outputs, classification, RAG, or agent workflows.

Detailed step-by-step workflows for complex operations.

Complete interaction examples demonstrating key workflows.

N8N/Zapier/Make workflows break silently, can't be version-controlled, and cost $50-500/month in SaaS fees. This skill rewrites them as standalone scripts that run forever with zero subscription cost. Each migration is a $500-5000 billable deliverable.

80% of "Claude built the wrong thing" failures come from jumping into code before the spec is clear. This skill forces the right order: **spec → approval → implementation**.

Transform OpenClaw cron jobs into Lobster workflows with approval gates and resumable execution.

- Workflow 1: Create Opportunity - Workflow 2: Progress Stage - Workflow 3: Track Activities - Workflow 4: Update Forecast - Workflow 5: Close Deal