self-improving-analyticsCaptures data quality issues, metric drift, pipeline failures, misleading visualizations, metric definition mismatches, and data freshness problems to enable continuous analytics improvement. Use when: (1) An ETL/ELT pipeline fails, (2) A metric value shows anomalous behavior, (3) Two teams define the same metric differently, (4) A dashboard shows wrong or misleading data, (5) A data freshness SLA is missed, (6) A schema change breaks downstream consumers.
Install via ClawdBot CLI:
clawdbot install jose-compu/self-improving-analyticsGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/jose-compu/self-improving-analytics.gitAudited Apr 16, 2026 · audit v1.0
Generated Oct 24, 2026
A data engineer is paged when the nightly customer orders ETL fails at 2am. After recovery, they use the skill to log the pipeline name, failing step, error message, and schema diff into DATA_ISSUES.md so the on-call rotation can spot recurrence and promote the fix into a pipeline runbook.
An analytics lead notices weekly active users dropped 18% without a corresponding product change. They log the anomaly with statistical context and category metric_drift, then link a prior definition_mismatch learning, eventually promoting a canonical metric definition to the data dictionary.
Marketing and Finance report different revenue figures because one includes refunds and the other does not. An analytics engineer logs the mismatch under definition_mismatch, tags both teams, and drafts a governance rule requiring data dictionary entries before dashboards ship.
A data platform team misses its 6am freshness SLA for the executive revenue dashboard. They log the SLA threshold and actual delay into DATA_ISSUES.md, then promote a recurring pattern into a dbt source freshness check and document the runbook step.
A producer team renames a column in an upstream events table, silently breaking three downstream dashboards. The analytics team logs the schema diff and affected consumers, then promotes a pre-merge schema contract check as a data quality SLA.
The core skill is free and installable via ClawdHub, while a paid tier offers curated data dictionary schemas, pipeline runbook templates, and SLA policy packs for teams that need governance out of the box.
Data platform and dbt-adjacent vendors embed the skill's logging conventions into their managed offerings, charging customers for automated learning capture, promotion workflows, and cross-dashboard incident correlation.
Analytics consultancies adopt the skill as a standardized incident-learning framework, selling implementation engagements that set up .learnings/ workflows, data quality SLAs, and pipeline runbooks for mid-market data teams.
💬 Integration Tip
Initialize .learnings/ at the workspace root on first use, then wire the opt-in hook to remind agents to log pipeline failures and metric anomalies; promote recurring patterns to data dictionaries or dbt tests instead of letting them accumulate.
Scored Oct 24, 2026
Data analysis and visualization. Query databases, generate reports, automate spreadsheets, and turn raw data into clear, actionable insights. Use when (1) yo...
Data visualization, report generation, SQL queries, and spreadsheet automation. Transform your AI agent into a data-savvy analyst that turns raw data into actionable insights.
Automation skill for DELLIGHT Strategic Intelligence.
Automation skill for DELLIGHT Intelligence Operations.
通过调用 Prana 平台上的远程 agent 完成以下处理:使用7步分析法对中国A股进行全方位财务分析,自动生成包含ROE分解、盈利模式识别、行业对比和投资洞察的HTML报告。支持上海和深圳交易所所有股票。 IMPORTANT: This skill has a mandatory step-by-step p...
基于AI的中文数据分析助手,支持智能图表生成、预测分析、异常检测及一键生成多格式专业报告。