{ "schemaVersion": "1.0", "item": { "slug": "insight-engine", "name": "Insight Engine", "source": "tencent", "type": "skill", "category": "效率提升", "sourceUrl": "https://clawhub.ai/nissan/insight-engine", "canonicalUrl": "https://clawhub.ai/nissan/insight-engine", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/insight-engine", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=insight-engine", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "references/architecture.md", "scripts/prompts/daily_analyst.md", "scripts/prompts/monthly_analyst.md", "scripts/prompts/weekly_analyst.md", "scripts/src/__init__.py" ], "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/insight-engine" }, "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/insight-engine", "agentPageUrl": "https://openagent3.xyz/skills/insight-engine/agent", "manifestUrl": "https://openagent3.xyz/skills/insight-engine/agent.json", "briefUrl": "https://openagent3.xyz/skills/insight-engine/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": "insight-engine", "body": "Data-driven insights from operational logs: collect → stats → LLM interpretation → Notion." }, { "title": "Architecture", "body": "collect (Python stats only)\n ├── Langfuse OTEL traces/scores/observations\n ├── OpenClaw/gateway logs\n ├── Git activity\n └── Control plane scores\n↓\nbuild_*_data_packet() ← all stats computed in Python before LLM call\n↓\ncall_claude(system_prompt, structured_json) ← LLM interprets, doesn't compute\n↓\nwrite_*_reflection() → Notion\n\nSee references/architecture.md for full design rationale." }, { "title": "Quick start", "body": "# Install deps\npip install anthropic requests pyyaml\n\n# Configure\ncp scripts/config/analyst.yaml.example config/analyst.yaml\n# Edit config/analyst.yaml — set langfuse URL, notion IDs, model choices\n\n# Dry run (local Ollama, no Notion write)\npython3 scripts/src/engine.py --mode daily --dry-run\n\n# Print data packet + prompt to stdout (for agent consumption, no API calls)\npython3 scripts/src/engine.py --mode daily --data-only\n\n# Live run\npython3 scripts/src/engine.py --mode daily\npython3 scripts/src/engine.py --mode weekly\npython3 scripts/src/engine.py --mode monthly" }, { "title": "Required env vars", "body": "ANTHROPIC_API_KEY=sk-ant-... # Anthropic API key\nNOTION_API_KEY=secret_... # Notion integration token\nLANGFUSE_BASE_URL=http://localhost:3100 # Langfuse server URL\nLANGFUSE_PUBLIC_KEY=pk-lf-... # Langfuse public key\nLANGFUSE_SECRET_KEY=sk-lf-... # Langfuse secret key\nNOTION_ROOT_PAGE_ID= # Root Notion page for reports\nNOTION_DAILY_DB_ID= # Notion database for daily entries\n\nOr configure in config/analyst.yaml." }, { "title": "Key design principles", "body": "Stats before LLM — Python computes all numbers. The LLM interprets, doesn't aggregate.\nCitation-enforcing prompts — System prompts require every claim to cite a specific number.\nNo hallucinated trends — < 7 data points → report \"insufficient data (n=X)\"\nDry-run mode — Uses local Ollama (free) to preview output; skip Notion write.\nData-only mode — Outputs the full data packet + prompts for agent/subagent use." }, { "title": "Cron setup (LaunchAgent example)", "body": "\nStartCalendarInterval\n\n Hour23\n Minute0\n\nProgramArguments\n\n /usr/bin/python3\n /path/to/insight-engine/scripts/src/engine.py\n --modedaily\n" }, { "title": "Extending to new data sources", "body": "Add a collector in scripts/src/collectors/:\n\nCreate my_source.py with a fetch_*() function returning a plain dict\nImport and call it in build_daily_data_packet() in engine.py\nReference the new key in prompts/daily_analyst.md under \"Data sources\"" }, { "title": "See also", "body": "references/architecture.md — full design rationale and layer descriptions\nscripts/prompts/daily_analyst.md — system prompt with citation rules\nscripts/config/analyst.yaml.example — config template" } ], "body": "insight-engine\n\nData-driven insights from operational logs: collect → stats → LLM interpretation → Notion.\n\nArchitecture\ncollect (Python stats only)\n ├── Langfuse OTEL traces/scores/observations\n ├── OpenClaw/gateway logs\n ├── Git activity\n └── Control plane scores\n↓\nbuild_*_data_packet() ← all stats computed in Python before LLM call\n↓\ncall_claude(system_prompt, structured_json) ← LLM interprets, doesn't compute\n↓\nwrite_*_reflection() → Notion\n\n\nSee references/architecture.md for full design rationale.\n\nQuick start\n# Install deps\npip install anthropic requests pyyaml\n\n# Configure\ncp scripts/config/analyst.yaml.example config/analyst.yaml\n# Edit config/analyst.yaml — set langfuse URL, notion IDs, model choices\n\n# Dry run (local Ollama, no Notion write)\npython3 scripts/src/engine.py --mode daily --dry-run\n\n# Print data packet + prompt to stdout (for agent consumption, no API calls)\npython3 scripts/src/engine.py --mode daily --data-only\n\n# Live run\npython3 scripts/src/engine.py --mode daily\npython3 scripts/src/engine.py --mode weekly\npython3 scripts/src/engine.py --mode monthly\n\nRequired env vars\nANTHROPIC_API_KEY=sk-ant-... # Anthropic API key\nNOTION_API_KEY=secret_... # Notion integration token\nLANGFUSE_BASE_URL=http://localhost:3100 # Langfuse server URL\nLANGFUSE_PUBLIC_KEY=pk-lf-... # Langfuse public key\nLANGFUSE_SECRET_KEY=sk-lf-... # Langfuse secret key\nNOTION_ROOT_PAGE_ID= # Root Notion page for reports\nNOTION_DAILY_DB_ID= # Notion database for daily entries\n\n\nOr configure in config/analyst.yaml.\n\nKey design principles\nStats before LLM — Python computes all numbers. The LLM interprets, doesn't aggregate.\nCitation-enforcing prompts — System prompts require every claim to cite a specific number.\nNo hallucinated trends — < 7 data points → report \"insufficient data (n=X)\"\nDry-run mode — Uses local Ollama (free) to preview output; skip Notion write.\nData-only mode — Outputs the full data packet + prompts for agent/subagent use.\nCron setup (LaunchAgent example)\n\nStartCalendarInterval\n\n Hour23\n Minute0\n\nProgramArguments\n\n /usr/bin/python3\n /path/to/insight-engine/scripts/src/engine.py\n --modedaily\n\n\nExtending to new data sources\n\nAdd a collector in scripts/src/collectors/:\n\nCreate my_source.py with a fetch_*() function returning a plain dict\nImport and call it in build_daily_data_packet() in engine.py\nReference the new key in prompts/daily_analyst.md under \"Data sources\"\nSee also\nreferences/architecture.md — full design rationale and layer descriptions\nscripts/prompts/daily_analyst.md — system prompt with citation rules\nscripts/config/analyst.yaml.example — config template" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/nissan/insight-engine", "publisherUrl": "https://clawhub.ai/nissan/insight-engine", "owner": "nissan", "version": "1.0.3", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/insight-engine", "downloadUrl": "https://openagent3.xyz/downloads/insight-engine", "agentUrl": "https://openagent3.xyz/skills/insight-engine/agent", "manifestUrl": "https://openagent3.xyz/skills/insight-engine/agent.json", "briefUrl": "https://openagent3.xyz/skills/insight-engine/agent.md" } }