Skip to content

eric-cielo/moflo / .claude/skills/spell-builder

spell-builder

Verified

Create, edit, and validate spell definitions (YAML/JSON) that compose connectors and step commands into end-to-end spells. Use when building new spell definitions, modifying existing ones, or exploring available spell components.

FileKindSize
SKILL.mdskill md12.9 KB
architecture.mdmarkdown8.5 KB
connectors/github-cli/README.mdmarkdown2.0 KB
connectors/http/README.mdmarkdown1.4 KB
connectors/local-outlook/README.mdmarkdown1.9 KB
connectors/playwright/README.mdmarkdown1.7 KB
permissions.mdmarkdown4.3 KB
preflight.mdmarkdown4.1 KB
steps/agent/README.mdmarkdown1.8 KB
steps/bash/README.mdmarkdown1005 B
steps/browser/README.mdmarkdown2.1 KB
steps/condition/README.mdmarkdown1.1 KB
steps/github/README.mdmarkdown1.6 KB
steps/loop/README.mdmarkdown1.2 KB
steps/memory/README.mdmarkdown1.6 KB
steps/outlook/README.mdmarkdown2.9 KB
steps/parallel/README.mdmarkdown1.1 KB
steps/prompt/README.mdmarkdown923 B
steps/wait/README.mdmarkdown667 B

connectors/playwright/README.md

View on GitHub
# `playwright` — Browser Automation Connector

**Purpose:** Use this connector for low-level browser automation via Playwright. Choose this when you need direct browser control from a step command, or when building browser-based connectors like `local-outlook`.

## Usage

From a spell, reach this connector through the `browser` step, which delegates to it:

```yaml
- id: take-screenshot
  type: browser
  config:
    actions:
      - action: navigate
        url: "https://myapp.com"
      - action: screenshot
```

> Earlier revisions of this file showed an `agent` step calling `context.tools.execute(...)` from a prompt. The `agent` step type has never been executable — use the `browser` step, a composite step's `tool` action, or a custom step command.

## Actions

| Action | Parameters | Description |
|--------|------------|-------------|
| `navigate` | `url` | Navigate to a URL |
| `click` | `selector` | Click an element matching the selector |
| `fill` | `selector`, `value` | Fill an input field with a value |
| `screenshot` | — | Capture a screenshot of the current page |
| `evaluate` | `expression` | Run JavaScript in the page context |

## Direct Usage

```javascript
await context.tools.execute('playwright', 'navigate', {
  url: 'https://dashboard.example.com/login'
});
await context.tools.execute('playwright', 'fill', {
  selector: '#email',
  value: 'admin@example.com'
});
await context.tools.execute('playwright', 'click', {
  selector: 'button[type="submit"]'
});
const shot = await context.tools.execute('playwright', 'screenshot', {});
```

## Capabilities

`read`, `write`

## Prerequisites

Requires `playwright` as a peer dependency.

## Source

`src/cli/spells/connectors/playwright.ts`
brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 322kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 198kUpdated Claude CodeCodexVerifiedInstall