{ "schemaVersion": "1.0", "item": { "slug": "brave-headless", "name": "Headless Brave Browser", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/kelexine/brave-headless", "canonicalUrl": "https://clawhub.ai/kelexine/brave-headless", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/brave-headless", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=brave-headless", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "package-lock.json", "package.json", "ARCHITECTURE.md", "SKILL.md", "scripts/search.js", "scripts/circuit-breaker.js" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/brave-headless" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/brave-headless", "agentPageUrl": "https://openagent3.xyz/skills/brave-headless/agent", "manifestUrl": "https://openagent3.xyz/skills/brave-headless/agent.json", "briefUrl": "https://openagent3.xyz/skills/brave-headless/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "brave-search", "body": "Headless web search and content extraction via the Brave Search API." }, { "title": "Setup", "body": "Run once before first use:\n\ncd \nnpm ci\n\nRequired environment variable:\n\nexport BRAVE_API_KEY=\"your-key-here\"\n\nGet a free API key at brave.com/search/api." }, { "title": "Search", "body": "node scripts/search.js \"query\" # Basic (5 results)\nnode scripts/search.js \"query\" -n 10 # Up to 20 results\nnode scripts/search.js \"query\" --content # Include page content\nnode scripts/search.js \"query\" -n 3 --content # Combined\nnode scripts/search.js \"query\" --json # Newline-delimited JSON\nnode scripts/search.js --help # Full options + env vars" }, { "title": "Extract page content", "body": "node scripts/content.js https://example.com/article\nnode scripts/content.js https://example.com/article --json\nnode scripts/content.js https://example.com/article --max-length 8000" }, { "title": "Output format (plain text)", "body": "--- Result 1 ---\nTitle: Page Title\nURL: https://example.com/page\nSnippet: Description from Brave Search\nContent:\n # Page Title\n\n Extracted markdown content...\n\n--- Result 2 ---\n...\n\nPass --json to get one JSON object per line instead, suitable for piping." }, { "title": "Exit codes", "body": "CodeMeaning0Success1Invalid input or configuration error2Page had no extractable content (content.js)130Interrupted (SIGINT)" }, { "title": "Configuration (environment variables)", "body": "All behaviour is configurable without touching code:\n\nVariableDefaultDescriptionBRAVE_API_KEY—Required. Brave Search subscription tokenLOG_LEVELinfodebug · info · warn · error · silentLOG_JSONfalseEmit logs as newline-delimited JSON to stderrFETCH_TIMEOUT_MS15000Per-page fetch timeoutSEARCH_TIMEOUT_MS10000Brave API call timeoutMAX_CONTENT_LENGTH5000Max chars of extracted contentMAX_RETRY_ATTEMPTS3Retry attempts on transient errorsRETRY_BASE_DELAY_MS500Base delay for exponential backoffRETRY_MAX_DELAY_MS30000Backoff delay capCONCURRENCY_LIMIT3Parallel page fetches when --content is setCB_FAILURE_THRESHOLD5Consecutive failures before circuit opensCB_RESET_TIMEOUT_MS60000Circuit breaker reset window\n\nAll variables are validated at startup — misconfigured runs fail immediately with a descriptive\nlist of every bad value rather than crashing mid-execution." }, { "title": "Architecture", "body": "See references/ARCHITECTURE.md for a full module breakdown.\n\nscripts/\n├── search.js ← Search CLI entry point\n├── content.js ← Content extraction CLI entry point\n├── content-fetcher.js ← HTTP fetch + Readability + DOM fallback\n├── config.js ← Schema-validated env config\n├── circuit-breaker.js ← Fault isolation (CLOSED → OPEN → HALF_OPEN)\n├── retry.js ← Exponential backoff with full jitter\n├── concurrency.js ← Bounded parallel execution pool\n├── utils.js ← htmlToMarkdown, smartTruncate, parseURL\n├── logger.js ← Structured leveled logger → stderr\n└── errors.js ← Typed error hierarchy" } ], "body": "brave-search\n\nHeadless web search and content extraction via the Brave Search API.\n\nSetup\n\nRun once before first use:\n\ncd \nnpm ci\n\n\nRequired environment variable:\n\nexport BRAVE_API_KEY=\"your-key-here\"\n\n\nGet a free API key at brave.com/search/api.\n\nUsage\nSearch\nnode scripts/search.js \"query\" # Basic (5 results)\nnode scripts/search.js \"query\" -n 10 # Up to 20 results\nnode scripts/search.js \"query\" --content # Include page content\nnode scripts/search.js \"query\" -n 3 --content # Combined\nnode scripts/search.js \"query\" --json # Newline-delimited JSON\nnode scripts/search.js --help # Full options + env vars\n\nExtract page content\nnode scripts/content.js https://example.com/article\nnode scripts/content.js https://example.com/article --json\nnode scripts/content.js https://example.com/article --max-length 8000\n\nOutput format (plain text)\n--- Result 1 ---\nTitle: Page Title\nURL: https://example.com/page\nSnippet: Description from Brave Search\nContent:\n # Page Title\n\n Extracted markdown content...\n\n--- Result 2 ---\n...\n\n\nPass --json to get one JSON object per line instead, suitable for piping.\n\nExit codes\nCode\tMeaning\n0\tSuccess\n1\tInvalid input or configuration error\n2\tPage had no extractable content (content.js)\n130\tInterrupted (SIGINT)\nConfiguration (environment variables)\n\nAll behaviour is configurable without touching code:\n\nVariable\tDefault\tDescription\nBRAVE_API_KEY\t—\tRequired. Brave Search subscription token\nLOG_LEVEL\tinfo\tdebug · info · warn · error · silent\nLOG_JSON\tfalse\tEmit logs as newline-delimited JSON to stderr\nFETCH_TIMEOUT_MS\t15000\tPer-page fetch timeout\nSEARCH_TIMEOUT_MS\t10000\tBrave API call timeout\nMAX_CONTENT_LENGTH\t5000\tMax chars of extracted content\nMAX_RETRY_ATTEMPTS\t3\tRetry attempts on transient errors\nRETRY_BASE_DELAY_MS\t500\tBase delay for exponential backoff\nRETRY_MAX_DELAY_MS\t30000\tBackoff delay cap\nCONCURRENCY_LIMIT\t3\tParallel page fetches when --content is set\nCB_FAILURE_THRESHOLD\t5\tConsecutive failures before circuit opens\nCB_RESET_TIMEOUT_MS\t60000\tCircuit breaker reset window\n\nAll variables are validated at startup — misconfigured runs fail immediately with a descriptive list of every bad value rather than crashing mid-execution.\n\nArchitecture\n\nSee references/ARCHITECTURE.md for a full module breakdown.\n\nscripts/\n├── search.js ← Search CLI entry point\n├── content.js ← Content extraction CLI entry point\n├── content-fetcher.js ← HTTP fetch + Readability + DOM fallback\n├── config.js ← Schema-validated env config\n├── circuit-breaker.js ← Fault isolation (CLOSED → OPEN → HALF_OPEN)\n├── retry.js ← Exponential backoff with full jitter\n├── concurrency.js ← Bounded parallel execution pool\n├── utils.js ← htmlToMarkdown, smartTruncate, parseURL\n├── logger.js ← Structured leveled logger → stderr\n└── errors.js ← Typed error hierarchy" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/kelexine/brave-headless", "publisherUrl": "https://clawhub.ai/kelexine/brave-headless", "owner": "kelexine", "version": "0.2.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/brave-headless", "downloadUrl": "https://openagent3.xyz/downloads/brave-headless", "agentUrl": "https://openagent3.xyz/skills/brave-headless/agent", "manifestUrl": "https://openagent3.xyz/skills/brave-headless/agent.json", "briefUrl": "https://openagent3.xyz/skills/brave-headless/agent.md" } }