Results for “abandonment-rate”

Use this skill when the user asks about CDL driver wellness, retention strategies, what causes driver turnover, common health issues (obesity, hypertension, sleep apnea, mental health), benefits packages, home-time policies, and how to build a culture that keeps drivers. Reference ATA Workforce Development + FMCSA Wellness Initiative.

Investigate retention patterns, cohorts, drivers, warning signs, and intervention options.

Create, apply, and manage AgentRC policies to customize readiness scoring, disable checks, override impact levels, set pass-rate thresholds, and enforce CI gating.

Manages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when deciding whether to maintain or sunset existing code.

Use to find cancellation, downgrade and switching intent in support conversations, and to be honest about how much of your churn support can actually see. Trigger for "which customers are at risk of leaving", "find cancellation intent", "customers asking how to export their data", "top reasons customers asked to close their account", competitor mentions, or building a churn early-warning signal from support data.

Write leave policies covering PTO, sick, and family leave. TRIGGERS - Use when user needs help with leave-policy related tasks.

Runbook skill for failures: cron error, PA failure, cascade, gateway disconnect, semantic DB stale. Walks: detect → classify → diagnose → notify → log. Replaces ad-hoc failure handling. Triggers: "cron failed", "X is broken", "cascade", "incident", "gateway down", "PA failure".

Detect sandbox evasion techniques in malware samples by analyzing timing checks, VM artifact queries, user interaction detection, and sleep inflation patterns from Cuckoo/AnyRun behavioral reports.

Turn churned and downgraded accounts into an early-warning system. Reads the customers who left or shrank, extracts the themes behind why, builds a warning checklist from the real causes, then reads your active book and flags which accounts look like the ones that just churned. Built for B2B retention teams, customizable to your CRM and your customer data. Trigger on "why do customers churn", "what do churned accounts have in common", "build me a churn early-warning list", "which accounts are at risk of churning", "who looks like a recent churner", or any retention post-mortem.

Meta-skill codifying the no-wakeup-polling pattern. Describes the ScheduleWakeup anti-pattern, the fix (--auto merge + detached watcher), and when to still use wakeups. Reduces handoff spam by 80%.

Graceful degradation when primary approach fails. Try alternates in priority order; record which path succeeded for future routing.

Composite skill — one-pass cleanup of stale local branches, dead worktrees, merged branches, and abandoned remote PR branches. Chains `git fetch --prune` → `clean_gone` (kill [gone] branches) → worktree prune + offer-to-remove dead worktrees → list-and-delete branches merged to main and release → delete remote PR branches whose PRs merged >7 days ago. Use instead of running `clean_gone` alone — that only catches half the rot. Daily-friction composite; fires on "clean up branches", "branch hygiene", "stale worktrees", and on session start when local branch count > 30.

Strategic patterns for solving intractable problems through cascading approximation, self-improvement, and heterogeneous evaluation from DeepMind's AlphaGo system

Analyzes Airbnb's design system including color palette, typography, shape language, and component patterns for use in design projects.

Disaster recovery has exactly two quantitative inputs, and every architectural

rate(http_requests_total[5m])

Automates app maintenance by assessing health, prioritizing by staleness and debt, and running targeted fix pipelines that commit directly to main.

Idiomatic Rust patterns, ownership, error handling, traits, concurrency, and best practices for building safe, performant applications.

Alert design and on-call practices — severity, runbooks, SLO burn-rate alerting, escalation. Use when designing alerts, writing runbooks, reducing alert fatigue, setting up escalation policies, implementing SLO-based alerting, or improving on-call processes.

Guides writing idiomatic Rust with ownership, error handling, traits, concurrency, and best practices for safe, performant code.

地道的Rust模式、所有权、错误处理、特质、并发，以及构建安全、高性能应用程序的最佳实践。

A runbook written in a wiki decays silently: the dashboard is renamed, the

Turn "they bought it but nobody uses it" into a plan to fix it. Reads what is unused inside an account, picks the one habit to build next, and writes the enablement plan that gets there. Built for B2B customer success teams, customizable to your product and your onboarding. Trigger on "drive adoption", "which features are unused", "why aren't they using it", "seats sitting idle", "build an enablement plan", or any account-adoption diagnostic.