# Send Metrics to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - 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. ## Suggested prompts ### New install ```text 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. ``` ### Upgrade existing ```text 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. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "metrics", "name": "Metrics", "source": "tencent", "type": "skill", "category": "数据分析", "sourceUrl": "https://clawhub.ai/ivangdavila/metrics", "canonicalUrl": "https://clawhub.ai/ivangdavila/metrics", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/metrics", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=metrics", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md", "automation-patterns.md", "data-quality.md", "formula-playbook.md", "memory-template.md", "metric-registry.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "metrics", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-29T20:06:03.109Z", "expiresAt": "2026-05-06T20:06:03.109Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=metrics", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=metrics", "contentDisposition": "attachment; filename=\"metrics-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "metrics" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/metrics" }, "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." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/metrics", "downloadUrl": "https://openagent3.xyz/downloads/metrics", "agentUrl": "https://openagent3.xyz/skills/metrics/agent", "manifestUrl": "https://openagent3.xyz/skills/metrics/agent.json", "briefUrl": "https://openagent3.xyz/skills/metrics/agent.md" } } ``` ## Documentation ### Setup On first use, read setup.md for integration behavior and memory initialization. ### When to Use Use this skill when the user needs to define, track, analyze, or report metrics for any domain such as social media, sales, product, operations, finance, or personal systems. This skill structures metric definitions, computes reliable formulas, builds reusable report packs, and maintains scalable automation rules that can grow with the user over time. ### Architecture Working memory lives in ~/metrics/. See memory-template.md for base structure and status behavior. ~/metrics/ ├── memory.md # HOT: goals, active metrics, reporting cadence ├── registry/ # WARM: metric contracts and dimension dictionaries ├── formulas/ # WARM: formula specs with version history ├── reports/ # WARM: report outputs by cadence and stakeholder ├── automations/ # WARM: scheduled checks and alert policies └── archive/ # COLD: retired metrics and old report cycles ### Quick Reference Load only the file needed for the current task to keep context focused. TopicFileSetup and integrationsetup.mdMemory schemamemory-template.mdMetric contract designmetric-registry.mdFormula design and governanceformula-playbook.mdReport cadences and templatesreporting-pack.mdAutomation and alerting patternsautomation-patterns.mdData validation and quality gatesdata-quality.md ### 1. Define a Metric Contract Before Any Calculation Every metric must have one clear contract: business meaning, numerator, denominator, source tables, update latency, and owner. Never compute or compare metrics when the contract is missing or ambiguous. ### 2. Separate Raw Signals from Derived Metrics Raw events are evidence. Metrics are interpreted aggregates. Keep them separate. Store and reason in this order: Raw signal Normalized base metric Derived metric Decision recommendation ### 3. Use Dimensions to Scale, Not New One-Off Metrics When users ask for "the same metric but by X", add a dimension instead of creating a duplicate metric. Common high-value dimensions: Time grain Source/channel Segment/persona Geography Product or workflow stage ### 4. Version Formulas and Annotate Breaking Changes Formulas evolve. Comparability fails when formula changes are not tracked. For every formula update, store: version change reason impact expectation backfill policy first report date with new logic ### 5. Reports Must Be Decision-Oriented A report is incomplete unless each section ties to a decision owner and explicit next action. Minimum output block for every report: What changed Why it changed What to do now Who owns the action When to review again ### 6. Automate Thresholds with Response Playbooks Alerts without response rules create noise. Each threshold must include: trigger condition severity level owner first response action escalation condition ### 7. Prefer Reusable Reporting Packs Over Custom One-Offs Build reusable templates for daily, weekly, monthly, and campaign reports so the system can scale across teams and domains. Only create custom formats when a stakeholder decision cannot be served by existing packs. ### Common Traps Mixing different metric definitions under one name -> trend lines become invalid. Changing formulas without version notes -> historical comparisons break silently. Reporting totals without segment cuts -> root causes remain hidden. Creating too many vanity metrics -> operators lose focus on decision metrics. Sending alerts without action ownership -> teams ignore notifications. Adding one-off dashboards for every request -> reporting system becomes unmaintainable. ### Security & Privacy Data that leaves your machine: None by default. Data that stays local: Metrics context and definitions under ~/metrics/. Formula versions, report logs, and alert policies stored locally. This skill does NOT: Access files outside ~/metrics/ for memory storage. Send metrics to third-party APIs by default. Create background automations without explicit user confirmation. ### Related Skills Install with clawhub install if user confirms: analytics — metric analysis patterns and interpretation workflows. dashboard — KPI visualization design and reporting layouts. report — structured reporting outputs for stakeholders. sql — query generation for metric extraction pipelines. excel-xlsx — spreadsheet-based metric operations and exports. ### Feedback If useful: clawhub star metrics Stay updated: clawhub sync ## Trust - Source: tencent - Verification: Indexed source record - Publisher: ivangdavila - Version: 1.0.0 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-04-29T20:06:03.109Z - Expires at: 2026-05-06T20:06:03.109Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/metrics) - [Send to Agent page](https://openagent3.xyz/skills/metrics/agent) - [JSON manifest](https://openagent3.xyz/skills/metrics/agent.json) - [Markdown brief](https://openagent3.xyz/skills/metrics/agent.md) - [Download page](https://openagent3.xyz/downloads/metrics)