{ "checker": { "claims": [ { "claim": "CLI extracts a page to Markdown", "command": " run cli.ts extract https://example.com --mode fast", "evidence": "documentation examples without needing permission. This is not a service; avoid relying on it for testing and monitoring purposes.\n", "expected": "Markdown text of the page", "input": "https://example.com", "kind": "claim", "outcome": "Real input produced the expected result: documentation examples", "returncode": 0, "source": "bun run cli.ts extract https://news.ycombinator.com --mode fast", "source_checked": true, "source_file": "README.md", "verdict": "yes" }, { "claim": "MCP server exposes extract_web_content tool", "command": " run index.ts tools/call {\"tool\": \"extract_web_content\", \"arguments\": {\"url\": \"https://example.com\", \"mode\": \"fast\"}}", "evidence": "documentation examples without needing permission. This is not a service; avoid relying on it for testing and monitoring purposes.\"}]}", "expected": "Markdown text returned by the tool", "input": "{\"tool\": \"extract_web_content\", \"arguments\": {\"url\": \"https://example.com\", \"mode\": \"fast\"}}", "kind": "claim", "outcome": "Real input produced the expected result: documentation examples", "source": "**Tools:** `extract_web_content`, `crawl_website`, `map_website`", "source_checked": true, "source_file": "README.md", "verdict": "yes" }, { "claim": "CLI scores buying intent of a text", "command": " run cli.ts intent 'Procuro um sof\u00e1 at\u00e9 R$ 2.500'", "evidence": "\"isLead\": true,\n \"score\": 85,\n \"matched\": [\n \"procuro\"\n ],\n \"region\": null,\n \"budget\": 2500\n}\n", "expected": "JSON with isLead true", "input": "Procuro um sof\u00e1 at\u00e9 R$ 2.500", "kind": "claim", "outcome": "Real input produced the expected result: \"isLead\": true", "returncode": 0, "source": "bun run cli.ts intent \"Procuro um sof\u00e1 at\u00e9 R$ 2.500\"", "source_checked": true, "source_file": "README.md", "verdict": "yes" } ], "cycle_checks": [ { "claim": "Scheduled or looping main behavior", "command": "", "evidence": "Entry points inspected (cli.ts, index.ts, package.json scripts, README). No cron, scheduler, --once/--now, or webhook loop is documented. The only long-running items are the MCP stdio/SSE server (serve) and the Maps daemon (daemon start), which are request servers rather than scheduled cycles. setInterval in browser-manager.ts is an idle browser sweeper, not a product cycle.", "expected": "identify the product trigger", "input": "source inspection", "kind": "cycle", "outcome": "Entry points inspected (cli.ts, index.ts, package.json scripts, README). No cron, scheduler, --once/--now, or webhook loop is documented. The only long-running items are the MCP stdio/SSE server (serve) and the Maps daemon (daemon start), which are request servers rather than scheduled cycles. setInterval in browser-manager.ts is an idle browser sweeper, not a product cycle.", "source": "repository entry points", "verdict": "yes" } ], "details": { "argv": [ "", "run", "index.ts" ], "kind": "mcp", "scope": "product operation", "serverInfo": { "name": "lookacrawler", "version": "1.1.2" }, "tool_result": { "content": [ { "text": "> [!NOTE] This content was retrieved from local cache.\n\nThis domain is for use in documentation examples without needing permission. This is not a service; avoid relying on it for testing and monitoring purposes.", "type": "text" } ] }, "tool_result_checked": true, "tool_schema_bytes": 20651, "tools": [ "extract_web_content", "batch_extract_web_content", "extract_structured_data", "map_website", "crawl_website", "extract_contacts", "search_places", "discover_local_leads", "deep_enrich_lead", "lint_anti_slop", "lookup_social_profile", "search_social_intent", "audit_company_website", "analyze_competitors", "generate_growth_plan", "gtm_pipeline_run" ], "working": true }, "evidence_strength": "readme_checked", "example_checks": [ { "claim": "Extract a page to Markdown from the CLI", "command": " run cli.ts extract https://example.com --mode fast", "deferred": false, "evidence": "This domain is for use in documentation examples without needing permission. This is not a service; avoid relying on it for testing and monitoring purposes.", "expected": "Markdown text of the page", "input": "https://example.com --mode fast", "kind": "example", "outcome": "command completed successfully", "returncode": 0, "source": "README.md: Quick Start & CLI Usage", "verdict": "yes" }, { "claim": "Discover sitemaps for a domain", "command": " run cli.ts map https://example.com --max-urls 5", "deferred": false, "evidence": "{\n \"host\": \"example.com\",\n \"sitemapsFound\": [\n \"https://example.com/sitemap.xml\"\n ],\n \"totalDiscovered\": 0,\n \"urls\": []\n}", "expected": "JSON listing the host and sitemaps found", "input": "https://example.com --max-urls 5", "kind": "example", "outcome": "command completed successfully", "returncode": 0, "source": "README.md: Quick Start & CLI Usage", "verdict": "yes" }, { "claim": "Lint copy for AI slop", "command": " run cli.ts antislop 'No cen\u00e1rio atual, uma solu\u00e7\u00e3o revolucion\u00e1ria'", "deferred": false, "evidence": "ed_word\",\n \"matched\": \"No cen\u00e1rio atual\",\n \"rule\": \"Abertura clich\u00ea de IA (throat-clearing)\",\n \"suggestion\": \"V\u00e1 direto ao ponto ou ao fato concreto\",\n \"index\": 0\n },\n {\n \"category\": \"banned_word\",\n \"matched\": \"revolucion\u00e1ria\",\n \"rule\": \"Hip\u00e9rbole vazia sem dados comprobat\u00f3rios\",\n \"suggestion\": \"Descreva o resultado espec\u00edfico em n\u00fameros ou tempo economizado\",\n \"index\": 30\n }\n ],\n \"metrics\": {\n \"wordCount\": 6,\n \"concreteNumbersCount\": 0,\n \"sentencesCount\": 1,\n \"averageSentenceLength\": 6,\n \"hasConcreteGrounding\": false\n }\n}", "expected": "JSON with isSlop true", "input": "No cen\u00e1rio atual, uma solu\u00e7\u00e3o revolucion\u00e1ria", "kind": "example", "outcome": "command completed successfully", "returncode": 0, "source": "README.md: Quick Start & CLI Usage", "verdict": "yes" } ], "status": "PASS" }, "deviations": [ "README says Bun 1.1+ but does not name an installer; installed Bun 1.4.4 with the official bun.sh install script (curl|sh), which put bun in ; bun was not on PATH so saved argv uses that absolute path.", "Workspace is not a git repository; no git metadata was needed for the operation.", "Maps engine (go build, build:maps) skipped: not required for extract/CLI/MCP operations and needs Go 1.26+." ], "fault_owner": null, "main_blocker": null, "operation": "Run the LookaCrawler CLI extract command and the extract_web_content MCP tool against a real page", "operation_scope": "Pinned commit bc5ce110f8b52b00a474343105c40c0de0d86fb9 in a fresh Ubuntu VM; Bun 1.4.4 runtime; public internet access to example.com. Google Maps engine (maps/gtm/intel/daemon) not built and not exercised.", "outcome": "working", "plain_failure": null, "steps": [ "curl -fsSL https://bun.sh/install | bash", "bun install (in )", "bun run cli.ts extract https://example.com --mode fast", "bun test (372 tests: 369 pass, 3 skip, 0 fail)", "bun run index.ts (stdio MCP) tools/call extract_web_content {url: https://example.com}" ], "stuck_step": null, "suggested_fix": "None for the tested operations. Note: bun is not on PATH after the curl installer; add it to PATH or use an absolute path." }