Initial commit

.claude-plugin/plugin.json

@@ -0,0 +1,15 @@
+{
+  "name": "firecrawl",
+  "description": "Firecrawl plugin for Claude Code",
+  "version": "1.0.0",
+  "author": {
+    "name": "Nathan Vale",
+    "email": "hi@nathanvale.com"
+  },
+  "skills": [
+    "./skills"
+  ],
+  "commands": [
+    "./commands"
+  ]
+}

README.md

@@ -0,0 +1,3 @@
+# firecrawl
+
+Firecrawl plugin for Claude Code

commands/extract.md

@@ -0,0 +1,36 @@
+---
+description: Extract structured data from a URL using LLM
+argument-hint: <url> --prompt "..." [--schema '{...}']
+---
+
+# Firecrawl Extract
+
+Extract data from: `$ARGUMENTS`
+
+## Instructions
+
+1. Parse the arguments:
+   - First argument is the URL to extract from
+   - Required `--prompt "text"` - What to extract
+   - Optional `--schema '{...}'` - JSON Schema for structured output
+
+2. Run the CLI command:
+   ```bash
+   cd /Users/nathanvale/code/side-quest-marketplace/plugins/firecrawl && bun run src/cli.ts extract $ARGUMENTS
+   ```
+
+3. Present the extracted data to the user
+
+## Example Usage
+
+```
+/firecrawl:extract https://example.com --prompt "Extract the main heading and description"
+/firecrawl:extract https://store.example.com/product --prompt "Extract price and name" --schema '{"price": {"type": "number"}, "name": {"type": "string"}}'
+```
+
+## Notes
+
+- Extraction is async - the command polls for completion
+- May take 10-30 seconds depending on page complexity
+- Use --schema for type-safe structured output
+- Requires FIRECRAWL_API_KEY environment variable

commands/map.md

@@ -0,0 +1,35 @@
+---
+description: Discover all URLs on a website
+argument-hint: <url> [--limit N]
+---
+
+# Firecrawl Map
+
+Map URLs on the website: `$ARGUMENTS`
+
+## Instructions
+
+1. Parse the arguments:
+   - First argument is the base URL to map
+   - Optional `--limit N` flag (default: 100)
+
+2. Run the CLI command:
+   ```bash
+   cd /Users/nathanvale/code/side-quest-marketplace/plugins/firecrawl && bun run src/cli.ts map $ARGUMENTS
+   ```
+
+3. Present the discovered URLs to the user
+
+## Example Usage
+
+```
+/firecrawl:map https://docs.example.com
+/firecrawl:map https://example.com --limit 50
+```
+
+## Notes
+
+- Returns up to 50 URLs in output (configurable via --limit)
+- Includes page titles when available
+- Useful for understanding site structure before scraping specific pages
+- Requires FIRECRAWL_API_KEY environment variable

commands/scrape.md

@@ -0,0 +1,34 @@
+---
+description: Scrape content from a URL as markdown
+argument-hint: <url> [--format markdown|summary]
+---
+
+# Firecrawl Scrape
+
+Scrape content from the URL: `$ARGUMENTS`
+
+## Instructions
+
+1. Parse the arguments:
+   - First argument is the URL to scrape
+   - Optional `--format` flag: `markdown` (default) or `summary`
+
+2. Run the CLI command:
+   ```bash
+   cd /Users/nathanvale/code/side-quest-marketplace/plugins/firecrawl && bun run src/cli.ts scrape $ARGUMENTS
+   ```
+
+3. Present the results to the user in a clean format
+
+## Example Usage
+
+```
+/firecrawl:scrape https://docs.example.com/api
+/firecrawl:scrape https://example.com --format summary
+```
+
+## Notes
+
+- Returns markdown content by default
+- Content is truncated at 8000 characters to save tokens
+- Requires FIRECRAWL_API_KEY environment variable

commands/search.md

@@ -0,0 +1,43 @@
+---
+description: Search the web and get results with content
+argument-hint: <query> [--limit N]
+---
+
+# Firecrawl Search
+
+Search the web for: `$ARGUMENTS`
+
+## Instructions
+
+1. Parse the arguments:
+   - All non-flag arguments form the search query
+   - Optional `--limit N` flag (default: 5)
+
+2. Run the CLI command:
+   ```bash
+   cd /Users/nathanvale/code/side-quest-marketplace/plugins/firecrawl && bun run src/cli.ts search $ARGUMENTS
+   ```
+
+3. Present the search results to the user
+
+## Example Usage
+
+```
+/firecrawl:search typescript error handling best practices
+/firecrawl:search "react hooks" --limit 10
+/firecrawl:search site:github.com firecrawl examples
+```
+
+## Search Operators
+
+- `"exact phrase"` - Match exact phrase
+- `-term` - Exclude term
+- `site:example.com` - Limit to domain
+- `intitle:word` - Word in page title
+- `inurl:word` - Word in URL
+
+## Notes
+
+- Returns up to 10 results with titles, URLs, and descriptions
+- Includes scraped markdown content when available
+- Requires FIRECRAWL_API_KEY environment variable

plugin.lock.json

@@ -0,0 +1,61 @@
+{
+  "$schema": "internal://schemas/plugin.lock.v1.json",
+  "pluginId": "gh:nathanvale/side-quest-marketplace:plugins/firecrawl",
+  "normalized": {
+    "repo": null,
+    "ref": "refs/tags/v20251128.0",
+    "commit": "ed09532002431a9e5d5ba51192ce3ef8b00139c1",
+    "treeHash": "0e13ccb8c53587c0b955044810575ee39dd9f499a3b232d85ec9e6d41b7d7797",
+    "generatedAt": "2025-11-28T10:27:16.117501Z",
+    "toolVersion": "publish_plugins.py@0.2.0"
+  },
+  "origin": {
+    "remote": "git@github.com:zhongweili/42plugin-data.git",
+    "branch": "master",
+    "commit": "aa1497ed0949fd50e99e70d6324a29c5b34f9390",
+    "repoRoot": "/Users/zhongweili/projects/openmind/42plugin-data"
+  },
+  "manifest": {
+    "name": "firecrawl",
+    "description": "Firecrawl plugin for Claude Code",
+    "version": "1.0.0"
+  },
+  "content": {
+    "files": [
+      {
+        "path": "README.md",
+        "sha256": "9a9da2b2acff95b3bf6836478e18d6ac5a28259b07492cb72ce286818a567c69"
+      },
+      {
+        "path": ".claude-plugin/plugin.json",
+        "sha256": "5ae05dbd9b7cda39cc43cf6e3d50a3ed78fb6dae126056b05f4757928431261f"
+      },
+      {
+        "path": "commands/search.md",
+        "sha256": "aad8741bea57f3d2eef66361a0680477c8623f9d19effc03eac5f246291174ff"
+      },
+      {
+        "path": "commands/map.md",
+        "sha256": "ec3bc473621fea05ebf604c650efaa9f95d5c88aecea543286f3f7513152f843"
+      },
+      {
+        "path": "commands/extract.md",
+        "sha256": "9c7e7d60aed2b25cdec7b30fbd5d3d31410446201cf9fa0df113a961e1c62924"
+      },
+      {
+        "path": "commands/scrape.md",
+        "sha256": "4d2a4ee16bd217b5803534c2f1aecd0c385742b63863975534569eb6d5b5adc9"
+      },
+      {
+        "path": "skills/firecrawl/SKILL.md",
+        "sha256": "2c2261bcb98091f855bf48f98122eef3f3a7dbe7cd2445da1f2468b10877de14"
+      }
+    ],
+    "dirSha256": "0e13ccb8c53587c0b955044810575ee39dd9f499a3b232d85ec9e6d41b7d7797"
+  },
+  "security": {
+    "scannedAt": null,
+    "scannerVersion": null,
+    "flags": []
+  }
+}

skills/firecrawl/SKILL.md

@@ -0,0 +1,160 @@
+---
+name: firecrawl
+description: Web scraping, search, and data extraction using Firecrawl API. Use when users need to fetch web content, discover URLs on sites, search the web, or extract structured data from pages.
+---
+
+# Firecrawl
+
+## Overview
+
+Firecrawl is a powerful web scraping and search API. This plugin provides a token-efficient interface for Claude Code through slash commands.
+
+## When to Use This Skill
+
+- **Scraping**: Fetch content from a single URL as markdown
+- **Mapping**: Discover all URLs on a website
+- **Searching**: Search the web and optionally scrape results
+- **Extracting**: Pull structured data from pages using LLM
+
+## Quick Reference
+
+| Task | Command |
+|------|---------|
+| Scrape a page | `/firecrawl:scrape <url>` |
+| Map a site | `/firecrawl:map <url>` |
+| Search the web | `/firecrawl:search <query>` |
+| Extract data | `/firecrawl:extract <url> --prompt "..."` |
+
+## Commands
+
+### Scrape - Get Page Content
+
+Fetches and converts a web page to clean markdown.
+
+```
+/firecrawl:scrape https://example.com
+/firecrawl:scrape https://example.com --format summary
+```
+
+**Options:**
+- `--format markdown|summary` - Output format (default: markdown)
+
+**Best for:**
+- Reading documentation
+- Fetching article content
+- Getting page text for analysis
+
+### Map - Discover URLs
+
+Finds all URLs on a website. Useful for understanding site structure.
+
+```
+/firecrawl:map https://example.com
+/firecrawl:map https://example.com --limit 50
+```
+
+**Options:**
+- `--limit N` - Maximum URLs to return (default: 100)
+
+**Best for:**
+- Understanding site structure
+- Finding specific pages before scraping
+- Discovering documentation sections
+
+### Search - Web Search
+
+Searches the web and returns results with optional content scraping.
+
+```
+/firecrawl:search typescript tutorials
+/firecrawl:search "react hooks guide" --limit 10
+```
+
+**Options:**
+- `--limit N` - Maximum results (default: 5)
+
+**Supports search operators:**
+- `"exact phrase"` - Exact match
+- `-term` - Exclude term
+- `site:example.com` - Limit to domain
+- `intitle:word` - Word in title
+
+**Best for:**
+- Finding information across the web
+- Researching topics
+- Finding documentation
+
+### Extract - Structured Data
+
+Extracts specific data from pages using LLM prompts.
+
+```
+/firecrawl:extract https://example.com --prompt "Extract the main heading and description"
+/firecrawl:extract https://example.com/product --prompt "Extract price and features" --schema '{"price": {"type": "number"}, "features": {"type": "array"}}'
+```
+
+**Options:**
+- `--prompt "text"` - What to extract (required)
+- `--schema '{...}'` - JSON Schema for structured output
+
+**Best for:**
+- Extracting specific data points
+- Getting structured information
+- Pulling prices, names, dates, etc.
+
+## Environment Setup
+
+Requires `FIRECRAWL_API_KEY` environment variable.
+
+Get your API key from: https://firecrawl.dev
+
+## Examples
+
+### Research a Topic
+```
+/firecrawl:search "best practices for TypeScript error handling" --limit 5
+```
+
+### Read Documentation
+```
+/firecrawl:scrape https://docs.example.com/api/authentication
+```
+
+### Map a Documentation Site
+```
+/firecrawl:map https://docs.example.com --limit 200
+```
+
+### Extract Product Info
+```
+/firecrawl:extract https://store.example.com/product/123 --prompt "Extract product name, price, and availability"
+```
+
+## Token Efficiency
+
+This plugin is designed for minimal token consumption:
+
+- **Scrape**: Returns clean markdown, truncated at 8000 chars
+- **Map**: Shows up to 50 URLs with titles
+- **Search**: Limits to 10 results with summaries
+- **Extract**: Returns only requested data
+
+Compare to the full MCP server which loads ~14k tokens just from tool definitions.
+
+## Error Handling
+
+Common errors:
+- `API key required` - Set FIRECRAWL_API_KEY
+- `Invalid URL` - Check URL format
+- `Rate limited` - Wait and retry (auto-handled)
+- `Site blocked` - Some sites block scraping
+
+## Pricing Note
+
+Firecrawl charges per operation:
+- Scrape: 1 credit per page
+- Map: 1 credit per call
+- Search: 1 credit per result
+- Extract: Varies by complexity
+
+Check https://firecrawl.dev/pricing for current rates.