Results for “drop-off-analysis”

Analyze conversion funnel drop-offs and identify biggest leak points with impact-ranked recommendations

Maps the end-to-end customer experience from awareness to advocacy — touchpoints, emotions, friction points, and improvement opportunities per stage. Use when identifying drop-off points, improving onboarding, or understanding the full user lifecycle. Triggers on: customer journey, user journey, journey map, touchpoints, onboarding experience, funnel analysis, churn points, aha moment, drop-off, user lifecycle.

Operations, debugging, and optimization for DAG workflows. Performs root cause analysis on failures, profiles execution performance, aggregates results from parallel branches, bridges context between nodes, and learns patterns from execution history. Activate on "DAG failed", "why did it fail", "root cause", "performance profile", "aggregate results", "merge branches", "execution patterns", "optimize DAG". NOT for planning DAGs (use dag-planner), executing DAGs (use dag-runtime), or validating outputs (use dag-quality).

Analyze closed deals and lost opportunities for patterns

当分析个人或他人成就差异的根本原因，并寻求提升路径时

Econometrics skill for Regression Discontinuity Design (RDD). Activates when the user asks about: "regression discontinuity", "RDD", "RD design", "sharp RDD", "fuzzy RDD", "running variable", "forcing variable", "cutoff", "bandwidth selection", "local linear regression", "McCrary test", "density test", "RDROBUST", "continuity assumption", "donut hole RDD", "geographic RDD", "断点回归", "回归不连续", "运行变量", "截断值", "带宽选择", "精确断点", "模糊断点", "密度检验", "局部线性回归"

Econometrics skill for Difference-in-Differences (DID) analysis. Activates when the user asks about: "difference in differences", "DID", "DiD", "diff-in-diff", "parallel trends", "treatment group", "control group", "pre-treatment", "post-treatment", "policy evaluation", "natural experiment", "staggered DID", "event study regression", "two-way fixed effects DID", "callaway santanna", "sun and abraham", "双重差分", "倍差法", "平行趋势", "处理组", "对照组", "政策评估", "事件研究", "交错DID", "渐进处理"

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

Analyzes a completed phase diff for high-confidence behavior-preserving simplifications and applies only explicitly approved proposals, reducing duplication, dead code, needless complexity, or avoidable inefficiency.

Generates detailed, technology-agnostic implementation blueprints by analyzing project architecture, technology stacks, and data flow patterns.

Analyzes .NET project code coverage and CRAP (Change Risk Anti-Patterns) scores to identify risk hotspots, methods blocking coverage gains, and prioritize where to add tests.

Extract structured knowledge from source material. Comprehensive extraction is the default — every insight that serves the domain gets extracted. For domain-relevant sources, skip rate must be below 10%. Zero extraction from a domain-relevant source is a BUG. Triggers on "/reduce", "/reduce [file]", "extract insights", "mine this", "process this".

上市公司财报/季报/年报/业绩的深度因果分析，覆盖A股、港股、美股和中概股。用于解读财报表现、亮点/风险、收入利润等指标变动、超预期或低于预期原因，以及针对毛利率、现金流、费用率等具体变量的归因问题。不用于纯股价、估值、评级、目标价、非财报新闻或未锚定具体公司报告期的宏观行业讨论。

Dropdown Implementation

Onboarding and activation optimization for Nick's products. Use when improving first-run experience, reducing drop-off, guiding users to value faster, or cleaning up empty states, setup friction, and early confusion.

Diagnoses whether a user's current approach is trading short-term speed for long-term pain, and recommends slower methods that build compoundable assets through friction.

Brain Dump Journaling

分析故事文本，提炼主要情节点并分析戏剧功能。适用于分析小说、剧本大纲、故事梗概等文本，识别关键转折点和情感节点

Debugging is the scientific method under time pressure.

Transforms scattered competitor data into a decision-ready product strategy report with positioning maps, feature matrices, pricing analysis, and opportunity windows.

Transforms A/B test and product experiment data into actionable readouts with hypothesis, metrics, interpretation, and decision.

Reduction is a trade, not an improvement.

EL2N: Deep Learning on a Data Diet

Generates a post-release blameless retrospective from project signals — synthesizing DORA-like metrics, WorkItem outcomes, session timeline, and drift deltas into a structured Artifact + LogEntry. Use at the end of a release cycle when asked to run a retro, "post-release review", "retrospective", or "post-mortem".

Expected error decomposes into bias, variance, and irreducible noise.

Build a USASpending relationship snapshot for the incumbent and buying agency on a pursuit row. Use when user needs award flows and rel counts before battlecard or teaming work — deterministic from DuckDB bulk.

Use to find the activation blockers visible in support contacts from new customers, before they show up in retention numbers months later. Trigger for "why aren't new customers activating", "what do new customers contact us about", onboarding drop-off, time-to-value analysis, first-90-days support experience, or a retention problem that traces back to activation.