{"id":"40f716df-504b-4f88-9385-eabc414bbe6a","entityType":"agent","slug":"clawhub-kn7a9xzb480qbhze2nkfjxtzan7zvabd-firecrawl-skills","name":"Firecrawl Skills","canonicalUrl":"https://www.xpersona.co/agent/clawhub-kn7a9xzb480qbhze2nkfjxtzan7zvabd-firecrawl-skills","canonicalPath":"/agent/clawhub-kn7a9xzb480qbhze2nkfjxtzan7zvabd-firecrawl-skills","generatedAt":"2026-10-10T06:29:52.868Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"description":"Firecrawl CLI for web scraping, crawling, and search. Scrape single pages or entire websites, map site URLs, and search the web with full content extraction. Returns clean markdown optimized for LLM context. Use for research, documentation extraction, competitive intelligence, and content monitoring. Skill: Firecrawl Skills Owner: kn7a9xzb480qbhze2nkfjxtzan7zvabd Summary: Firecrawl CLI for web scraping, crawling, and search. Scrape single pages or entire websites, map site URLs, and search the web with full content extraction. Returns clean markdown optimized for LLM context. Use for research, documentation extraction, competitive intelligence, and content monitoring. Tags: latest:1.0.0 Version history: v1.0.0 |","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 5.2K downloads reported by the source. Last updated 4/15/2026.","installCommand":"clawhub skill install kn7a9xzb480qbhze2nkfjxtzan7zvabd:firecrawl-skills","sourceUrl":"https://clawhub.ai/kn7a9xzb480qbhze2nkfjxtzan7zvabd/firecrawl-skills","homepage":"https://clawhub.ai/kn7a9xzb480qbhze2nkfjxtzan7zvabd/firecrawl-skills","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/kn7a9xzb480qbhze2nkfjxtzan7zvabd/firecrawl-skills","kind":"source"}],"safetyScore":84,"overallRank":62,"popularityScore":68,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Firecrawl CLI for web scraping, crawling, and search. Scrape single pages or entire websites, map site URLs, and search the web with full content extraction. Re"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":"No protocol or capability metadata is available."},"protocols":[],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":0,"capabilityMatrix":{"rows":[],"flattenedTokens":""}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"stars":null,"forks":null,"downloads":5249,"packageName":null,"latestVersion":"1.0.0","tractionLabel":"5.2K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-02-28T17:17:00.915Z","emptyReason":null},"lastUpdatedAt":"2026-04-15T00:45:39.800Z","lastCrawledAt":"2026-02-28T17:17:00.915Z","lastIndexedAt":null,"nextCrawlAt":"2026-03-01T17:17:00.915Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.0","createdAt":"2026-02-03T17:57:50.984Z","changelog":"Initial release of Firecrawl CLI with full documentation. - Introduces the firecrawl command-line tool for web scraping, crawling, site mapping, and search. - Supports extracting clean markdown, HTML, links, screenshots, and JSON, optimized for LLM context windows. - Provides authentication, credit management, and result storage conventions. - Includes detailed command usage examples for search, scrape, crawl, and map operations. - Offers extensive filtering and formatting options for each command.","fileCount":3,"zipByteSize":4558}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install kn7a9xzb480qbhze2nkfjxtzan7zvabd:firecrawl-skills","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kn7a9xzb480qbhze2nkfjxtzan7zvabd-firecrawl-skills/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kn7a9xzb480qbhze2nkfjxtzan7zvabd-firecrawl-skills/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kn7a9xzb480qbhze2nkfjxtzan7zvabd-firecrawl-skills/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-kn7a9xzb480qbhze2nkfjxtzan7zvabd-firecrawl-skills/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-kn7a9xzb480qbhze2nkfjxtzan7zvabd-firecrawl-skills/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-kn7a9xzb480qbhze2nkfjxtzan7zvabd-firecrawl-skills/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":[]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T06:29:52.868Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kn7a9xzb480qbhze2nkfjxtzan7zvabd-firecrawl-skills/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kn7a9xzb480qbhze2nkfjxtzan7zvabd-firecrawl-skills/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kn7a9xzb480qbhze2nkfjxtzan7zvabd-firecrawl-skills/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kn7a9xzb480qbhze2nkfjxtzan7zvabd-firecrawl-skills/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"readme":"Skill: Firecrawl Skills\n\nOwner: kn7a9xzb480qbhze2nkfjxtzan7zvabd\n\nSummary: Firecrawl CLI for web scraping, crawling, and search. Scrape single pages or entire websites, map site URLs, and search the web with full content extraction. Returns clean markdown optimized for LLM context. Use for research, documentation extraction, competitive intelligence, and content monitoring.\n\nTags: latest:1.0.0\n\nVersion history:\n\nv1.0.0 | 2026-02-03T17:57:50.984Z | auto\n\nInitial release of Firecrawl CLI with full documentation.\n\n- Introduces the firecrawl command-line tool for web scraping, crawling, site mapping, and search.\n- Supports extracting clean markdown, HTML, links, screenshots, and JSON, optimized for LLM context windows.\n- Provides authentication, credit management, and result storage conventions.\n- Includes detailed command usage examples for search, scrape, crawl, and map operations.\n- Offers extensive filtering and formatting options for each command.\n\nArchive index:\n\nArchive v1.0.0: 3 files, 4558 bytes\n\nFiles: rules/install.md (2164b), SKILL.md (9202b), _meta.json (135b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: firecrawl-cli\ndescription: |\n  Firecrawl CLI for web scraping, crawling, and search. Scrape single pages or entire websites, map site URLs, and search the web with full content extraction. Returns clean markdown optimized for LLM context. Use for research, documentation extraction, competitive intelligence, and content monitoring.\n---\n\n# Firecrawl CLI\n\nUse the `firecrawl` CLI to fetch and search the web. Firecrawl returns clean markdown optimized for LLM context windows, handles JavaScript rendering, bypasses common blocks, and provides structured data.\n\n## Installation\n\nCheck status, auth, and rate limits:\n\n```bash\nfirecrawl --status\n```\n\nOutput when ready:\n\n```\n  🔥 firecrawl cli v1.0.2\n\n  ● Authenticated via FIRECRAWL_API_KEY\n  Concurrency: 0/100 jobs (parallel scrape limit)\n  Credits: 500,000 remaining\n```\n\n- **Concurrency**: Max parallel jobs. Run parallel operations close to this limit but not above.\n- **Credits**: Remaining API credits. Each scrape/crawl consumes credits.\n\nIf not installed: `npm install -g firecrawl-cli`\n\nAlways refer to the installation rules in [rules/install.md](rules/install.md) for more information if the user is not logged in.\n\n## Authentication\n\nIf not authenticated, run:\n\n```bash\nfirecrawl login --browser\n```\n\nThe `--browser` flag automatically opens the browser for authentication without prompting.\n\n## Organization\n\nCreate a `.firecrawl/` folder in the working directory unless it already exists to store results. Add `.firecrawl/` to the `.gitignore` file if not already there. Always use `-o` to write directly to file (avoids flooding context):\n\n```bash\n# Search the web (most common operation)\nfirecrawl search \"your query\" -o .firecrawl/search-{query}.json\n\n# Search with scraping enabled\nfirecrawl search \"your query\" --scrape -o .firecrawl/search-{query}-scraped.json\n\n# Scrape a page\nfirecrawl scrape https://example.com -o .firecrawl/{site}-{path}.md\n```\n\nExamples:\n\n```\n.firecrawl/search-react_server_components.json\n.firecrawl/search-ai_news-scraped.json\n.firecrawl/docs.github.com-actions-overview.md\n.firecrawl/firecrawl.dev.md\n```\n\n## Commands\n\n### Search - Web search with optional scraping\n\n```bash\n# Basic search (human-readable output)\nfirecrawl search \"your query\" -o .firecrawl/search-query.txt\n\n# JSON output (recommended for parsing)\nfirecrawl search \"your query\" -o .firecrawl/search-query.json --json\n\n# Limit results\nfirecrawl search \"AI news\" --limit 10 -o .firecrawl/search-ai-news.json --json\n\n# Search specific sources\nfirecrawl search \"tech startups\" --sources news -o .firecrawl/search-news.json --json\nfirecrawl search \"landscapes\" --sources images -o .firecrawl/search-images.json --json\nfirecrawl search \"machine learning\" --sources web,news,images -o .firecrawl/search-ml.json --json\n\n# Filter by category (GitHub repos, research papers, PDFs)\nfirecrawl search \"web scraping python\" --categories github -o .firecrawl/search-github.json --json\nfirecrawl search \"transformer architecture\" --categories research -o .firecrawl/search-research.json --json\n\n# Time-based search\nfirecrawl search \"AI announcements\" --tbs qdr:d -o .firecrawl/search-today.json --json  # Past day\nfirecrawl search \"tech news\" --tbs qdr:w -o .firecrawl/search-week.json --json          # Past week\n\n# Location-based search\nfirecrawl search \"restaurants\" --location \"San Francisco,California,United States\" -o .firecrawl/search-sf.json --json\nfirecrawl search \"local news\" --country DE -o .firecrawl/search-germany.json --json\n\n# Search AND scrape content from results\nfirecrawl search \"firecrawl tutorials\" --scrape -o .firecrawl/search-scraped.json --json\nfirecrawl search \"API docs\" --scrape --scrape-formats markdown,links -o .firecrawl/search-docs.json --json\n```\n\n**Search Options:**\n\n| Option | Description |\n|--------|-------------|\n| `--limit <n>` | Maximum results (default: 5, max: 100) |\n| `--sources <sources>` | Comma-separated: web, images, news (default: web) |\n| `--categories <categories>` | Comma-separated: github, research, pdf |\n| `--tbs <value>` | Time filter: qdr:h (hour), qdr:d (day), qdr:w (week), qdr:m (month), qdr:y (year) |\n| `--location <location>` | Geo-targeting (e.g., \"Germany\") |\n| `--country <code>` | ISO country code (default: US) |\n| `--scrape` | Enable scraping of search results |\n| `--scrape-formats <formats>` | Scrape formats when --scrape enabled (default: markdown) |\n| `-o, --output <path>` | Save to file |\n\n### Scrape - Single page content extraction\n\n```bash\n# Basic scrape (markdown output)\nfirecrawl scrape https://example.com -o .firecrawl/example.md\n\n# Get raw HTML\nfirecrawl scrape https://example.com --html -o .firecrawl/example.html\n\n# Multiple formats (JSON output)\nfirecrawl scrape https://example.com --format markdown,links -o .firecrawl/example.json\n\n# Main content only (removes nav, footer, ads)\nfirecrawl scrape https://example.com --only-main-content -o .firecrawl/example.md\n\n# Wait for JS to render\nfirecrawl scrape https://spa-app.com --wait-for 3000 -o .firecrawl/spa.md\n\n# Extract links only\nfirecrawl scrape https://example.com --format links -o .firecrawl/links.json\n\n# Include/exclude specific HTML tags\nfirecrawl scrape https://example.com --include-tags article,main -o .firecrawl/article.md\nfirecrawl scrape https://example.com --exclude-tags nav,aside,.ad -o .firecrawl/clean.md\n```\n\n**Scrape Options:**\n\n| Option | Description |\n|--------|-------------|\n| `-f, --format <formats>` | Output format(s): markdown, html, rawHtml, links, screenshot, json |\n| `-H, --html` | Shortcut for `--format html` |\n| `--only-main-content` | Extract main content only |\n| `--wait-for <ms>` | Wait before scraping (for JS content) |\n| `--include-tags <tags>` | Only include specific HTML tags |\n| `--exclude-tags <tags>` | Exclude specific HTML tags |\n| `-o, --output <path>` | Save to file |\n\n### Crawl - Crawl an entire website\n\n```bash\n# Start a crawl (returns job ID)\nfirecrawl crawl https://example.com\n\n# Wait for crawl to complete\nfirecrawl crawl https://example.com --wait\n\n# With progress indicator\nfirecrawl crawl https://example.com --wait --progress\n\n# Check crawl status\nfirecrawl crawl <job-id>\n\n# Limit pages\nfirecrawl crawl https://example.com --limit 100 --max-depth 3\n\n# Crawl blog section only\nfirecrawl crawl https://example.com --include-paths /blog,/posts\n\n# Exclude admin pages\nfirecrawl crawl https://example.com --exclude-paths /admin,/login\n\n# Crawl with rate limiting\nfirecrawl crawl https://example.com --delay 1000 --max-concurrency 2\n\n# Save results\nfirecrawl crawl https://example.com --wait -o crawl-results.json --pretty\n```\n\n**Crawl Options:**\n\n| Option | Description |\n|--------|-------------|\n| `--wait` | Wait for crawl to complete |\n| `--progress` | Show progress while waiting |\n| `--limit <n>` | Maximum pages to crawl |\n| `--max-depth <n>` | Maximum crawl depth |\n| `--include-paths <paths>` | Only crawl matching paths |\n| `--exclude-paths <paths>` | Skip matching paths |\n| `--delay <ms>` | Delay between requests |\n| `--max-concurrency <n>` | Max concurrent requests |\n\n### Map - Discover all URLs on a site\n\n```bash\n# List all URLs (one per line)\nfirecrawl map https://example.com -o .firecrawl/urls.txt\n\n# Output as JSON\nfirecrawl map https://example.com --json -o .firecrawl/urls.json\n\n# Search for specific URLs\nfirecrawl map https://example.com --search \"blog\" -o .firecrawl/blog-urls.txt\n\n# Limit results\nfirecrawl map https://example.com --limit 500 -o .firecrawl/urls.txt\n\n# Include subdomains\nfirecrawl map https://example.com --include-subdomains -o .firecrawl/all-urls.txt\n```\n\n**Map Options:**\n\n| Option | Description |\n|--------|-------------|\n| `--limit <n>` | Maximum URLs to discover |\n| `--search <query>` | Filter URLs by search query |\n| `--sitemap <mode>` | include, skip, or only |\n| `--include-subdomains` | Include subdomains |\n| `--json` | Output as JSON |\n| `-o, --output <path>` | Save to file |\n\n### Credit Usage\n\n```bash\n# Show credit usage\nfirecrawl credit-usage\n\n# Output as JSON\nfirecrawl credit-usage --json --pretty\n```\n\n## Reading Scraped Files\n\nNEVER read entire firecrawl output files at once unless explicitly asked - they can be 1000+ lines. Instead, use grep, head, or incremental reads:\n\n```bash\n# Check file size and preview structure\nwc -l .firecrawl/file.md && head -50 .firecrawl/file.md\n\n# Use grep to find specific content\ngrep -n \"keyword\" .firecrawl/file.md\ngrep -A 10 \"## Section\" .firecrawl/file.md\n```\n\n## Parallelization\n\nRun multiple scrapes in parallel using `&` and `wait`:\n\n```bash\n# Parallel scraping (fast)\nfirecrawl scrape https://site1.com -o .firecrawl/1.md &\nfirecrawl scrape https://site2.com -o .firecrawl/2.md &\nfirecrawl scrape https://site3.com -o .firecrawl/3.md &\nwait\n```\n\nFor many URLs, use xargs with `-P` for parallel execution:\n\n```bash\ncat urls.txt | xargs -P 10 -I {} sh -c 'firecrawl scrape \"{}\" -o \".firecrawl/$(echo {} | md5).md\"'\n```\n\n## Combining with Other Tools\n\n```bash\n# Extract URLs from search results\njq -r '.data.web[].url' .firecrawl/search-query.json\n\n# Get titles from search results\njq -r '.data.web[] | \"\\(.title): \\(.url)\"' .firecrawl/search-query.json\n\n# Count URLs from map\nfirecrawl map https://example.com | wc -l\n```\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn7a9xzb480qbhze2nkfjxtzan7zvabd\",\n  \"slug\": \"firecrawl-skills\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1770141470984\n}\n\nFile v1.0.0:rules/install.md\n\n---\nname: firecrawl-cli-installation\ndescription: |\n  Install the Firecrawl CLI and handle authentication errors.\n---\n\n# Firecrawl CLI Installation\n\n## Quick Install\n\n```bash\nnpm install -g firecrawl-cli\n```\n\n## Verify Installation\n\nCheck if installed and authenticated in one command:\n\n```bash\nfirecrawl --status\n```\n\nOutput will show:\n\n- Version number\n- Authentication status\n- Concurrency limit\n- Remaining credits\n\n## Authentication\n\nIf not authenticated, run:\n\n```bash\nfirecrawl login --browser\n```\n\nThe `--browser` flag automatically opens the browser for authentication without prompting. This is the recommended method for agents.\n\n## Error Handling\n\nIf ANY command returns an authentication error after running `firecrawl login --browser` (e.g., \"not authenticated\", \"unauthorized\", \"API key\"), use an ask user question tool if available:\n\n**Question:** \"How would you like to authenticate with Firecrawl?\"\n\n**Options:**\n\n1. **Login with browser (Recommended)** - Opens your browser to authenticate with Firecrawl\n2. **Enter API key manually** - Paste an existing API key from firecrawl.dev\n\n### If user selects browser login:\n\nRun `firecrawl login --browser` to automatically open the browser. Wait for them to confirm authentication, then retry the original command.\n\n### If user selects manual API key:\n\nAsk for their API key, then run:\n\n```bash\nfirecrawl login --api-key \"<their-key>\"\n```\n\nOr set the environment variable:\n\n```bash\nexport FIRECRAWL_API_KEY=\"<their-key>\"\n```\n\nTell them to add this export to `~/.zshrc` or `~/.bashrc` for persistence, then retry the original command.\n\n## Troubleshooting\n\n### Command not found\n\nIf `firecrawl` command is not found after installation:\n\n1. Make sure npm global bin is in PATH\n2. Try: `npx firecrawl-cli --version`\n3. Or reinstall: `npm install -g firecrawl-cli`\n\n### Permission errors\n\nIf you get permission errors during installation:\n\n```bash\n# Option 1: Fix npm permissions (recommended)\nmkdir ~/.npm-global\nnpm config set prefix '~/.npm-global'\nexport PATH=~/.npm-global/bin:$PATH\n# Add the export to your shell profile\n\n# Option 2: Use sudo (not recommended)\nsudo npm install -g firecrawl-cli\n```","readmeExcerpt":"Skill: Firecrawl Skills Owner: kn7a9xzb480qbhze2nkfjxtzan7zvabd Summary: Firecrawl CLI for web scraping, crawling, and search. Scrape single pages or entire websites, map site URLs, and search the web with full content extraction. Returns clean markdown optimized for LLM context. Use for research, documentation extraction, competitive intelligence, and content monitoring. Tags: latest:1.0.0 Version history: v1.0.0 | ","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"firecrawl --status"},{"language":"text","snippet":"🔥 firecrawl cli v1.0.2\n\n  ● Authenticated via FIRECRAWL_API_KEY\n  Concurrency: 0/100 jobs (parallel scrape limit)\n  Credits: 500,000 remaining"},{"language":"bash","snippet":"firecrawl login --browser"},{"language":"bash","snippet":"# Search the web (most common operation)\nfirecrawl search \"your query\" -o .firecrawl/search-{query}.json\n\n# Search with scraping enabled\nfirecrawl search \"your query\" --scrape -o .firecrawl/search-{query}-scraped.json\n\n# Scrape a page\nfirecrawl scrape https://example.com -o .firecrawl/{site}-{path}.md"},{"language":"text","snippet":".firecrawl/search-react_server_components.json\n.firecrawl/search-ai_news-scraped.json\n.firecrawl/docs.github.com-actions-overview.md\n.firecrawl/firecrawl.dev.md"},{"language":"bash","snippet":"# Basic search (human-readable output)\nfirecrawl search \"your query\" -o .firecrawl/search-query.txt\n\n# JSON output (recommended for parsing)\nfirecrawl search \"your query\" -o .firecrawl/search-query.json --json\n\n# Limit results\nfirecrawl search \"AI news\" --limit 10 -o .firecrawl/search-ai-news.json --json\n\n# Search specific sources\nfirecrawl search \"tech startups\" --sources news -o .firecrawl/search-news.json --json\nfirecrawl search \"landscapes\" --sources images -o .firecrawl/search-images.json --json\nfirecrawl search \"machine learning\" --sources web,news,images -o .firecrawl/search-ml.json --json\n\n# Filter by category (GitHub repos, research papers, PDFs)\nfirecrawl search \"web scraping python\" --categories github -o .firecrawl/search-github.json --json\nfirecrawl search \"transformer architecture\" --categories research -o .firecrawl/search-research.json --json\n\n# Time-based search\nfirecrawl search \"AI announcements\" --tbs qdr:d -o .firecrawl/search-today.json --json  # Past day\nfirecrawl search \"tech news\" --tbs qdr:w -o .firecrawl/search-week.json --json          # Past week\n\n# Location-based search\nfirecrawl search \"restaurants\" --location \"San Francisco,California,United States\" -o .firecrawl/search-sf.json --json\nfirecrawl search \"local news\" --country DE -o .firecrawl/search-germany.json --json\n\n# Search AND scrape content from results\nfirecrawl search \"firecrawl tutorials\" --scrape -o .firecrawl/search-scraped.json --json\nfirecrawl search \"API docs\" --scrape --scrape-formats markdown,links -o .firecrawl/search-docs.json --json"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: firecrawl-cli\ndescription: |\n  Firecrawl CLI for web scraping, crawling, and search. Scrape single pages or entire websites, map site URLs, and search the web with full content extraction. Returns clean markdown optimized for LLM context. Use for research, documentation extraction, competitive intelligence, and content monitoring.\n---\n\n# Firecrawl CLI\n\nUse the `firecrawl` CLI to fetch and search the web. Firecrawl returns clean markdown optimized for LLM context windows, handles JavaScript rendering, bypasses common blocks, and provides structured data.\n\n## Installation\n\nCheck status, auth, and rate limits:\n\n```bash\nfirecrawl --status\n```\n\nOutput when ready:\n\n```\n  🔥 firecrawl cli v1.0.2\n\n  ● Authenticated via FIRECRAWL_API_KEY\n  Concurrency: 0/100 jobs (parallel scrape limit)\n  Credits: 500,000 remaining\n```\n\n- **Concurrency**: Max parallel jobs. Run parallel operations close to this limit but not above.\n- **Credits**: Remaining API credits. Each scrape/crawl consumes credits.\n\nIf not installed: `npm install -g firecrawl-cli`\n\nAlways refer to the installation rules in [rules/install.md](rules/install.md) for more information if the user is not logged in.\n\n## Authentication\n\nIf not authenticated, run:\n\n```bash\nfirecrawl login --browser\n```\n\nThe `--browser` flag automatically opens the browser for authentication without prompting.\n\n## Organization\n\nCreate a `.firecrawl/` folder in the working directory unless it already exists to store results. Add `.firecrawl/` to the `.gitignore` file if not already there. Always use `-o` to write directly to file (avoids flooding context):\n\n```bash\n# Search the web (most common operation)\nfirecrawl search \"your query\" -o .firecrawl/search-{query}.json\n\n# Search with scraping enabled\nfirecrawl search \"your query\" --scrape -o .firecrawl/search-{query}-scraped.json\n\n# Scrape a page\nfirecrawl scrape https://example.com -o .firecrawl/{site}-{path}.md\n```\n\nExamples:\n\n```\n.firecrawl/search-react_server_components.json\n.firecrawl/search-ai_news-scraped.json\n.firecrawl/docs.github.com-actions-overview.md\n.firecrawl/firecrawl.dev.md\n```\n\n## Commands\n\n### Search - Web search with optional scraping\n\n```bash\n# Basic search (human-readable output)\nfirecrawl search \"your query\" -o .firecrawl/search-query.txt\n\n# JSON output (recommended for parsing)\nfirecrawl search \"your query\" -o .firecrawl/search-query.json --json\n\n# Limit results\nfirecrawl search \"AI news\" --limit 10 -o .firecrawl/search-ai-news.json --json\n\n# Search specific sources\nfirecrawl search \"tech startups\" --sources news -o .firecrawl/search-news.json --json\nfirecrawl search \"landscapes\" --sources images -o .firecrawl/search-images.json --json\nfirecrawl search \"machine learning\" --sources web,news,images -o .firecrawl/search-ml.json --json\n\n# Filter by category (GitHub repos, research papers, PDFs)\nfirecrawl search \"web scraping python\" --categories github -o .firecrawl/search-github.json --json\nfirecrawl search \"transformer architecture\" --categories "},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7a9xzb480qbhze2nkfjxtzan7zvabd\",\n  \"slug\": \"firecrawl-skills\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1770141470984\n}"},{"path":"rules/install.md","content":"---\nname: firecrawl-cli-installation\ndescription: |\n  Install the Firecrawl CLI and handle authentication errors.\n---\n\n# Firecrawl CLI Installation\n\n## Quick Install\n\n```bash\nnpm install -g firecrawl-cli\n```\n\n## Verify Installation\n\nCheck if installed and authenticated in one command:\n\n```bash\nfirecrawl --status\n```\n\nOutput will show:\n\n- Version number\n- Authentication status\n- Concurrency limit\n- Remaining credits\n\n## Authentication\n\nIf not authenticated, run:\n\n```bash\nfirecrawl login --browser\n```\n\nThe `--browser` flag automatically opens the browser for authentication without prompting. This is the recommended method for agents.\n\n## Error Handling\n\nIf ANY command returns an authentication error after running `firecrawl login --browser` (e.g., \"not authenticated\", \"unauthorized\", \"API key\"), use an ask user question tool if available:\n\n**Question:** \"How would you like to authenticate with Firecrawl?\"\n\n**Options:**\n\n1. **Login with browser (Recommended)** - Opens your browser to authenticate with Firecrawl\n2. **Enter API key manually** - Paste an existing API key from firecrawl.dev\n\n### If user selects browser login:\n\nRun `firecrawl login --browser` to automatically open the browser. Wait for them to confirm authentication, then retry the original command.\n\n### If user selects manual API key:\n\nAsk for their API key, then run:\n\n```bash\nfirecrawl login --api-key \"<their-key>\"\n```\n\nOr set the environment variable:\n\n```bash\nexport FIRECRAWL_API_KEY=\"<their-key>\"\n```\n\nTell them to add this export to `~/.zshrc` or `~/.bashrc` for persistence, then retry the original command.\n\n## Troubleshooting\n\n### Command not found\n\nIf `firecrawl` command is not found after installation:\n\n1. Make sure npm global bin is in PATH\n2. Try: `npx firecrawl-cli --version`\n3. Or reinstall: `npm install -g firecrawl-cli`\n\n### Permission errors\n\nIf you get permission errors during installation:\n\n```bash\n# Option 1: Fix npm permissions (recommended)\nmkdir ~/.npm-global\nnpm config set prefix '~/.npm-global'\nexport PATH=~/.npm-global/bin:$PATH\n# Add the export to your shell profile\n\n# Option 2: Use sudo (not recommended)\nsudo npm install -g firecrawl-cli\n```"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Firecrawl CLI for web scraping, crawling, and search. Scrape single pages or entire websites, map site URLs, and search the web with full content extraction. Returns clean markdown optimized for LLM context. Use for research, documentation extraction, competitive intelligence, and content monitoring. Skill: Firecrawl Skills Owner: kn7a9xzb480qbhze2nkfjxtzan7zvabd Summary: Firecrawl CLI for web scraping, crawling, and search. Scrape single pages or entire websites, map site URLs, and search the web with full content extraction. Returns clean markdown optimized for LLM context. Use for research, documentation extraction, competitive intelligence, and content monitoring. Tags: latest:1.0.0 Version history: v1.0.0 |","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":730,"uniquenessScore":53,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"agent-directory","verified":false,"confidence":"low","updatedAt":"2026-10-10T06:29:52.868Z","emptyReason":"No close protocol neighbors were found."},"items":[],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[]}}}