Analyzes a completed/failed/paused automation's task_results, buckets them by status×reason, separates recoverable cohorts from terminal ones, and produces a win-back plan or a prune/blocklist recommendation. Use when the user wants a post-mortem, failure analysis, win-back, "how is this automation doing", or how to handle silent creators. Affiliate (分销) context. Chinese triggers: 复盘 / 失败分析 / winback / 唤回 / 这条自动化表现如何 / 沉默达人怎么处理.
How to install winback-and-pruning?
crevideo/crevideo-reach/winback-and-pruning
$npx -y skills add crevideo/crevideo-reach --skill winback-and-pruningInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Run `npx skills use "https://github.com/crevideo/crevideo-reach" --skill "crevideo/crevideo-reach/winback-and-pruning"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/crevideo/crevideo-reach" that are relevant to the current task. Run `npx skills add "https://github.com/crevideo/crevideo-reach"` and select the relevant skills, then follow their instructions.
Related
6 picksType
- azure-kustoQuery and analyze data in Azure Data Explorer (Kusto/ADX) using KQL for log analytics, telemetry, and time series analysis.Jul 2026
- analyticsWhen the user wants to set up, improve, or audit analytics tracking and measurement.Jul 2026
- firecrawl-dashboard-reportingPull metrics from analytics dashboards and internal web tools with Firecrawl browser.Jun 2026
- data-storytellingTransform data into compelling narratives using visualization, context, and persuasive structure.Jul 2026
- data-visualizationCreate effective data visualizations with Python (matplotlib, seaborn, plotly).Jul 2026
- extension-oqlMake a canister's data queryable by the Caffeine Data Intelligence agent.Jul 2026
