Data & Analytics

Analyze historical downtrend durations and generate interactive HTML histograms showing typical correction lengths by sector and market cap.

High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics

Professional trading charts including candlesticks, equity curves, drawdowns, correlation heatmaps, and return distributions

ML trading signal classifiers using XGBoost and LightGBM with walk-forward validation, SHAP feature importance, and threshold optimization

Portfolio-level performance measurement including return metrics, risk metrics, risk-adjusted ratios, rolling analysis, and HTML reports

Writes golden-dataset items for a profile through two doors. The import door turns a question bank — a CSV, one sheet of an Excel .xlsx workbook, or a table pasted into chat — into items after the parsed rows have been shown and agreed to: a row that already carries a statement is written confirmed, a bare question is written unconfirmed. The save door writes one question, the statement that answered it and the result the person accepted, as a confirmed item. The curation door applies the cha...

Master data manipulation, analysis, and visualization with Pandas, NumPy, and Matplotlib

The pass/fail check that must be clean before an app ships — runs `streamsnow validate-app <slug>` (required files, manifest, schema refs, security, bind predicates, caching, sql-tokens, session fallback, page imports, path leaks, the §11 build-state contract, plus the sql_review audit-trail section, whose coverage severity follows sql_review.coverage in config) and explains how to fix anything that fails. Use when the user says "validate", "is this ready", "check my app", or before /ship-app.

The front door — build a Streamlit-in-Snowflake app from idea to opened PR, or resume one mid-build. Owns the spec, scaffold, page-building, and ship phases, with human checkpoints between them. Start here for any new app, to document an existing one, to add a page, or to set up a machine or repo. Use when the user says "build an app", "new dashboard", "add a page", "spec this out", "set me up", or "pick up where we left off".

Stage, commit, push, and open a PR for one app, gated on a passing validation, then watch CI to a terminal state. Use when the user says "ship it", "open a PR", "deploy <slug>", or after preview and review look good.

Review an app the way a senior reviewer would — parallel reviewers across SQL, data, UI, runtime, and docs — then optionally apply the fixes. Use when the user says "review this app", "audit my dashboard", "fix the findings", "auto-fix until clean", or after validation passes. Flags — --fix applies findings as atomic commits, --auto loops review→fix until clean, --sql writes the paste-and-runnable SQL companions.

Run an app locally against live Snowflake so the user can see it in the browser, wiring up secrets.toml first if missing. Use when the user says "preview my app", "run my app", "let me see it in the browser", or after /start-app scaffolds an app.

Port an external Streamlit app into the repo in two reviewable steps — lift-and-shift into apps/<slug>/, then conform to repo conventions until validation passes. Use when the user says "migrate a streamlit app", "port this dashboard into the repo", "bring an external app in", or "modernize this dashboard".

Turn a user's feedback on a live app into applied fixes — classify each point, update the spec where scope changes, and land one commit per item. Use when the user says "here's feedback on <app>", "users said the numbers look wrong", "the filter is confusing", "polish this dashboard", or pastes review notes/screenshots about an existing app.

Check an app's numbers against the live warehouse — trace every Snowflake object it queries, verify the columns it expects actually exist, and map upstream lineage, using bounded read-only queries. Use when the user says "trace the data", "audit the lineage", "are these numbers right", "lineage for <slug>", or when a review finding hinges on what the live data returns.

Identify, measure, and exclude bot / crawler / AI-agent traffic in PostHog web and product analytics using the traffic classification surface (the isLikelyBot / getTrafficType HogQL functions and the $virt_* virtual properties). Use when the user asks to "exclude bots", "filter out crawlers", "remove bot traffic from my numbers", "how much of my traffic is bots / AI crawlers", "is GPTBot / ChatGPT / Claude hitting my site", "break down traffic by human vs bot", or wants clean human-only count...

Inspects PostHog Web analytics Live tab data — current users online, last-30-minutes pageviews, top pages, referrers, devices, browsers, countries, bot traffic, and the per-minute bot/users charts. Use when the user asks "who is on my site right now?", "what is happening live?", "what bots are crawling me?", asks about the "live tab" / "live dashboard", wants live numbers (last 30 min), or wants help filtering or drilling into the live view. Also covers building product-analytics insights tha...

Change the sync configuration of an existing data warehouse schema — switch sync_type, pick a different incremental_field, set primary_key_columns, choose cdc_table_mode, or change sync_frequency. Use when the user asks "switch my orders table from full refresh to incremental", "this table is syncing too slowly / too frequently", "I need to pick a different incremental column", "set up CDC for this Postgres table", or when diagnosis of a failing sync pointed to an incremental-field or PK misc...

Use when the user asks about revenue, payments, subscriptions, billing, CRM deals, support tickets, ad spend, production database tables, or other data PostHog does not collect natively — or wants to join or correlate PostHog product events with that external business data. Also use when a query fails because a table does not exist or returns no results for expected external data. The data warehouse can import from SaaS tools (Stripe, Hubspot, Zendesk, etc.), ad platforms, production database...

Audit the health of a PostHog project's data warehouse sources and syncs — find every broken or degraded source connection, sync schema, and webhook channel. Use when the user asks "why are my imports failing?", "what's broken with my sources?", "why is my warehouse data stale?", or wants a one-shot triage of source/sync health before deciding where to dig in. Produces a prioritized report grouped by severity, with recommended next steps. For materialized-view health use `auditing-warehouse-v...

Create a recurring AI-generated PostHog report — schedule a free-text prompt to run on a cron, with the LLM-synthesized markdown delivered to email, Slack, or Microsoft Teams on each tick. Use when the user wants a recurring AI summary of X on any cadence (daily, weekly, monthly, yearly) rather than a one-off report. (To attach an AI summary to an existing insight/dashboard subscription instead of a free-text prompt, see `managing-subscriptions` and its `summary_enabled` option.)

Write Streamlit app source code that runs well in a PostHog sandbox — the posthog_apps.query() bridge for reading PostHog data, the packages baked into the sandbox image, caching and session state across Streamlit reruns, layout and chart patterns, and the app.py entry point with any helper modules and data files bundled beside it. Use when authoring or debugging the Python source of a PostHog Streamlit app, when a query inside an app fails, or when asked to "write a streamlit app that shows ...

Create, deploy, and operate Streamlit apps in PostHog via the streamlit-apps MCP tools — create an app, set its source, start and stop its sandbox, poll status, list versions, delete, and share the app with humans via its PostHog URL. Use when asked to "create a streamlit app", "deploy a data app", "ship a dashboard app", "restart/stop my app", "why is my app not running", or "give me a link to the app".

Signals scout for PostHog A/B experiments. Watches running experiments for validity threats — sample ratio mismatch, contamination, exposure stalls, mid-run flag mutations — and lifecycle drift.