{ "schemaVersion": "1.0", "item": { "slug": "agent-analytics", "name": "Agent Analytics", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/dannyshmueli/agent-analytics", "canonicalUrl": "https://clawhub.ai/dannyshmueli/agent-analytics", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/agent-analytics", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agent-analytics", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md" ], "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": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/agent-analytics" }, "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/agent-analytics", "agentPageUrl": "https://openagent3.xyz/skills/agent-analytics/agent", "manifestUrl": "https://openagent3.xyz/skills/agent-analytics/agent.json", "briefUrl": "https://openagent3.xyz/skills/agent-analytics/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": "Agent Analytics", "body": "After install, your agent can create projects, ship tracking, query analytics, run experiments, and iterate without opening a dashboard.\n\nEnglish-first workflow, with Chinese docs and content available for OpenClaw users and teams in China.\n\nUse it when you want an agent to operate growth analytics end-to-end, automate recurring checks, and manage multiple projects from one conversation loop.\n\nHosted free tier includes 100k events/month across 2 projects." }, { "title": "Chinese support / 中文支持", "body": "Chinese docs and installation content are available on the docs site, including the OpenClaw guide under /zh/.\nWorks through API, CLI, and MCP, depending on the environment your agent already uses.\nGood fit for closed-loop agent workflows: monitor, analyze, experiment, iterate.\nSupports batch work across many projects instead of a manual dashboard-by-dashboard workflow." }, { "title": "What npx is doing", "body": "OpenClaw can launch the official CLI with npx @agent-analytics/cli@0.5.1.\nThat command runs the published Agent Analytics CLI package from npm.\nThe CLI calls the same HTTP API documented at https://docs.agentanalytics.sh/api/.\nIf the package is already installed in the environment, the equivalent binary is agent-analytics.\nKeep AGENT_ANALYTICS_API_KEY in the environment. Do not ask the user to paste secrets into chat." }, { "title": "Command format", "body": "The examples below use the CLI binary form:\n\nagent-analytics \n\nIn OpenClaw, that usually means:\n\nnpx @agent-analytics/cli@0.5.1 \n\nIf the package is already installed, run the same commands directly as agent-analytics .\n\nFor the full command list and flags:\n\nagent-analytics --help" }, { "title": "Safe operating rules", "body": "Prefer fixed commands over ad-hoc query construction.\nStart with projects, all-sites, create, stats, insights, events, breakdown, pages, heatmap, sessions-dist, retention, funnel, and experiments.\nUse query only when the fixed commands cannot answer the question.\nDo not build --filter JSON from raw user text.\nValidate project names before create: ^[a-zA-Z0-9._-]{1,64}$" }, { "title": "First-time setup", "body": "agent-analytics login --token aak_YOUR_API_KEY\nagent-analytics create my-site --domain https://mysite.com\nagent-analytics events my-site --days 7 --limit 20\n\nThe create command returns a project token and a ready-to-use tracking snippet. Add that snippet before ." }, { "title": "Common commands", "body": "agent-analytics projects\nagent-analytics all-sites --period 7d\nagent-analytics stats my-site --days 7\nagent-analytics insights my-site --period 7d\nagent-analytics events my-site --days 7 --limit 20\nagent-analytics breakdown my-site --property path --event page_view --limit 10\nagent-analytics funnel my-site --steps \"page_view,signup,purchase\"\nagent-analytics retention my-site --period week --cohorts 8\nagent-analytics experiments list my-site\n\nIf a task needs something outside these common flows, use agent-analytics --help first." }, { "title": "Tracker setup", "body": "The easiest install flow is:\n\nRun agent-analytics create my-site --domain https://mysite.com\nCopy the returned snippet into the page before \nDeploy\nVerify with agent-analytics events my-site --days 7 --limit 20\n\nIf you already know the project token, the tracker looks like:\n\n\n\nUse window.aa?.track('signup', {method: 'github'}) for custom events after the tracker loads." }, { "title": "Query caution", "body": "agent-analytics query exists for advanced reporting, but it should be used carefully because --filter accepts JSON.\n\nUse fixed commands first.\nIf query is necessary, check agent-analytics --help first.\nDo not pass raw user text directly into --filter.\nFor exact request shapes, use https://docs.agentanalytics.sh/api/." }, { "title": "Experiments", "body": "The CLI supports the full experiment lifecycle:\n\nagent-analytics experiments list my-site\nagent-analytics experiments create my-site --name signup_cta --variants control,new_cta --goal signup" }, { "title": "References", "body": "Docs: https://docs.agentanalytics.sh/\nAPI reference: https://docs.agentanalytics.sh/api/\nCLI vs MCP vs API: https://docs.agentanalytics.sh/reference/cli-mcp-api/\nOpenClaw install guide: https://docs.agentanalytics.sh/installation/openclaw/" } ], "body": "Agent Analytics\n\nAfter install, your agent can create projects, ship tracking, query analytics, run experiments, and iterate without opening a dashboard.\n\nEnglish-first workflow, with Chinese docs and content available for OpenClaw users and teams in China.\n\nUse it when you want an agent to operate growth analytics end-to-end, automate recurring checks, and manage multiple projects from one conversation loop.\n\nHosted free tier includes 100k events/month across 2 projects.\n\nChinese support / 中文支持\nChinese docs and installation content are available on the docs site, including the OpenClaw guide under /zh/.\nWorks through API, CLI, and MCP, depending on the environment your agent already uses.\nGood fit for closed-loop agent workflows: monitor, analyze, experiment, iterate.\nSupports batch work across many projects instead of a manual dashboard-by-dashboard workflow.\nWhat npx is doing\nOpenClaw can launch the official CLI with npx @agent-analytics/cli@0.5.1.\nThat command runs the published Agent Analytics CLI package from npm.\nThe CLI calls the same HTTP API documented at https://docs.agentanalytics.sh/api/.\nIf the package is already installed in the environment, the equivalent binary is agent-analytics.\nKeep AGENT_ANALYTICS_API_KEY in the environment. Do not ask the user to paste secrets into chat.\nCommand format\n\nThe examples below use the CLI binary form:\n\nagent-analytics \n\n\nIn OpenClaw, that usually means:\n\nnpx @agent-analytics/cli@0.5.1 \n\n\nIf the package is already installed, run the same commands directly as agent-analytics .\n\nFor the full command list and flags:\n\nagent-analytics --help\n\nSafe operating rules\nPrefer fixed commands over ad-hoc query construction.\nStart with projects, all-sites, create, stats, insights, events, breakdown, pages, heatmap, sessions-dist, retention, funnel, and experiments.\nUse query only when the fixed commands cannot answer the question.\nDo not build --filter JSON from raw user text.\nValidate project names before create: ^[a-zA-Z0-9._-]{1,64}$\nFirst-time setup\nagent-analytics login --token aak_YOUR_API_KEY\nagent-analytics create my-site --domain https://mysite.com\nagent-analytics events my-site --days 7 --limit 20\n\n\nThe create command returns a project token and a ready-to-use tracking snippet. Add that snippet before .\n\nCommon commands\nagent-analytics projects\nagent-analytics all-sites --period 7d\nagent-analytics stats my-site --days 7\nagent-analytics insights my-site --period 7d\nagent-analytics events my-site --days 7 --limit 20\nagent-analytics breakdown my-site --property path --event page_view --limit 10\nagent-analytics funnel my-site --steps \"page_view,signup,purchase\"\nagent-analytics retention my-site --period week --cohorts 8\nagent-analytics experiments list my-site\n\n\nIf a task needs something outside these common flows, use agent-analytics --help first.\n\nTracker setup\n\nThe easiest install flow is:\n\nRun agent-analytics create my-site --domain https://mysite.com\nCopy the returned snippet into the page before \nDeploy\nVerify with agent-analytics events my-site --days 7 --limit 20\n\nIf you already know the project token, the tracker looks like:\n\n\n\n\nUse window.aa?.track('signup', {method: 'github'}) for custom events after the tracker loads.\n\nQuery caution\n\nagent-analytics query exists for advanced reporting, but it should be used carefully because --filter accepts JSON.\n\nUse fixed commands first.\nIf query is necessary, check agent-analytics --help first.\nDo not pass raw user text directly into --filter.\nFor exact request shapes, use https://docs.agentanalytics.sh/api/.\nExperiments\n\nThe CLI supports the full experiment lifecycle:\n\nagent-analytics experiments list my-site\nagent-analytics experiments create my-site --name signup_cta --variants control,new_cta --goal signup\n\nReferences\nDocs: https://docs.agentanalytics.sh/\nAPI reference: https://docs.agentanalytics.sh/api/\nCLI vs MCP vs API: https://docs.agentanalytics.sh/reference/cli-mcp-api/\nOpenClaw install guide: https://docs.agentanalytics.sh/installation/openclaw/" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/dannyshmueli/agent-analytics", "publisherUrl": "https://clawhub.ai/dannyshmueli/agent-analytics", "owner": "dannyshmueli", "version": "4.0.3", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/agent-analytics", "downloadUrl": "https://openagent3.xyz/downloads/agent-analytics", "agentUrl": "https://openagent3.xyz/skills/agent-analytics/agent", "manifestUrl": "https://openagent3.xyz/skills/agent-analytics/agent.json", "briefUrl": "https://openagent3.xyz/skills/agent-analytics/agent.md" } }