Upsolve-Labs

Ship a feature branch: write docs, bump version, create PR with screenshots and evidence. Links Linear tickets if available. Use when ready to merge.

Functional verification against the plan. Manually confirms every planned path works, takes screenshots, saves API examples as evidence for the PR. Use after /execute.

Build a plan to spec using Red/Green TDD. Writes tests first, confirms they fail, then implements. Supports --ticket mode for scoped execution with dependency checks and file-level scope guardrails. Use after /plan to implement a feature or fix.

Plan a feature or bug fix with deep engineering analysis. Explores the codebase, compares implementation alternatives, maps error paths, and produces test coverage diagrams — all before any code is written. Emits structured YAML tickets with dependency DAG and self-contained agent briefs. Optionally materializes to Linear and TODOS.md. Use when starting new work, breaking down a feature, or before any code changes. Strongly recommended as the first step before /execute.

Full sprint flow: /plan -> /execute -> /validate -> /review -> /ship-pr. Always runs /plan (which auto-detects small follow-ups via fast-path). Loops review/execute until clean. End result is a pushed PR.

Analyzes git state, TODOs, and project context to recommend which upstack skill to run next. Use when starting a session or unsure what to do.

Independent exploratory QA. Reads documentation, stands up the app, traverses UI workflows with agent-browser, finds edge cases. Use anytime to test app quality.

Senior engineer code review. Compares the current branch against its base branch for bugs, security risks, and code quality issues. Best run in a clean conversation.

Recommends which data skill to run next. Use when starting a new analysis session or unsure where to begin. Asks what you are trying to accomplish and recommends the right skill with reasoning. Trigger phrases: "where should I start?", "what skill should I use?", "advisor", "help me figure out what to run", "I don't know where to begin".

Period-over-period or cohort comparison. Use to understand what changed between two time periods, groups, or experiments. Breaks down the delta by key dimensions to find where the difference comes from. Trigger phrases: "last week vs prior week", "before vs after launch", "compare these two groups", "A/B results", "what changed?", "why is X different?".

Dataset discovery and schema mapping. Use when starting fresh with data, exploring what's available, or mapping a new data source. Opens an Upsolve thread, surfaces available tables and schemas, profiles row counts and key columns, and outputs a structured data map. Strongly recommended as the first step before any analysis. Trigger phrases: "what data do I have?", "show me my tables", "explore this dataset", "what's available?", "I'm new to this data".

Funnel drop-off analysis. Define conversion steps and get conversion rates, absolute drop-off counts, and segment breakdowns at each stage. Use for product analytics, marketing funnels, checkout flows, or any sequential user journey. Trigger phrases: "funnel analysis", "where are users dropping off?", "conversion rate", "show me the funnel", "why aren't users converting?".

Anomaly root cause analysis. Use when a metric looks wrong or surprising. Runs a structured 4-phase investigation over a single Upsolve thread: confirm → narrow → hypothesize → validate. Findings use numbered codes (1A CONFIRMED, 1B CANDIDATE, 2A RULED_OUT). Trigger phrases: "revenue dropped", "metric is spiking", "why did X change?", "something looks wrong", "root cause", "debug this metric".

KPI deep dive report. Given a metric name, produces a structured brief: current value, WoW and MoM trend, top contributing segments, and notable outliers. Outputs a shareable summary for Slack, docs, or stakeholder updates. Trigger phrases: "summarize this metric", "metric brief", "what's happening with X", "give me a KPI summary", "how is [metric] doing?", "weekly metric update".

Data pipeline health check. Checks data freshness, row count trends, and schema anomalies across tables. Outputs a health dashboard with OK/WARN/FAIL per table. Use for daily pipeline monitoring, SLA checks, or debugging stale data. Trigger phrases: "check pipeline health", "is my data fresh?", "data SLA", "pipeline monitoring", "are my tables up to date?", "something seems stale".

Data quality audit for a table or dataset. Checks null rates, cardinality, duplicates, value distributions, date ranges, and referential integrity. Outputs a quality scorecard with OK/WARN/FAIL ratings per dimension. Run before building models, pipelines, or reports on top of a dataset. Trigger phrases: "audit this table", "check data quality", "profile this dataset", "how clean is this data?", "is this table safe to use?".