wingman-chat

Audit an HTML/UI Studio build for accessibility — contrast, semantic HTML, keyboard/focus, motion, forms — and fix what's found. Use only when the user explicitly requests an accessibility review or a polish-pass.

Scan a Studio HTML/UI build for generic AI-template visual tropes and fix them. Use only when the user explicitly asks whether it looks AI-generated, asks to remove the slop, or requests a polish-pass.

Create generative / algorithmic art — flow fields, particle systems, noise-driven compositions — rendered to an image with code. Use when the user wants art made with code, generative art, or parametric visuals.

Design a software/system architecture diagram (C4 context/container, or a sequence diagram) from the conversation and workspace material, delivered as a Mermaid `.mmd` diagram that renders natively in the panel. Trigger with "draw the architecture", "create a C4 diagram", "diagram the system", "show a sequence diagram", or whenever the user wants a technical system visualized.

Build a self-contained interactive HTML dashboard with ECharts, filters, KPIs, and tables. Use for executive overviews, operational monitoring, or analytical workspaces where several coordinated views need to respond to the same data.

Create beautiful static visual art — posters, design pieces, cover art — as .png or .pdf, driven by a design philosophy. Use when the user asks for a poster, a piece of art, a design, or any static, design-forward visual. Create original work, never copying existing artists.

Create rigorous static or interactive data visualizations from real data. Use Python with matplotlib/seaborn for publication-ready PNG/SVG, or the JavaScript executor's embedded ECharts browser bundle for a self-contained interactive HTML chart.

Extract a design system from a brand guide, codebase, screenshots, or finished artifact. Use when the user explicitly asks for tokens, a component inventory/library, or to turn an existing visual language into a reusable system.

Create or edit a Word (.docx) deliverable such as a report, memo, letter, proposal, or template. Use when the user explicitly wants a Word file or asks to modify an existing .docx; not for a report that should remain in chat.

Build a distinctive, intentional web page, UI, or interactive prototype as an HTML artifact — aesthetic direction, typography, interaction wiring, and variations that don't read as templated defaults. Use whenever you're designing a landing page, web UI, clickable prototype, or HTML artifact and want it to look deliberately designed rather than generic.

Check an HTML/UI Studio build's visual hierarchy and spacing/type rhythm, then fix what's off. Use only when the user explicitly requests this review, says the hierarchy/spacing feels off, or requests a polish-pass.

Apply a named visual style to a generated image — photography, product rendering, flat/isometric illustration, marketing/brand graphics, or artistic/playful treatments. Fold the closest brief-compatible fragment into the create_image/render prompt while preserving explicit user constraints.

Generate a single poster-style infographic image (.png) that visualizes the key facts and numbers from the conversation and workspace material. Trigger with "make an infographic", "create a visual summary", "turn this into a one-pager graphic", or whenever the user wants a single shareable visual.

Check an HTML/UI Studio build's hover, active, focus, disabled, and loading states, then fix what's missing. Use only when the user explicitly requests an interaction-state review or a polish-pass.

Build a hierarchical mind map of the concepts in the conversation and workspace material, delivered as a Mermaid diagram (.mmd) that renders natively in the side panel. Trigger with "make a mind map", "map out these concepts", "give me a concept map", or whenever the user wants the structure of a topic visualized.

Create or manipulate a PDF deliverable — designed reports/one-pagers, merge/split/rotate, extraction to another file, watermarks, or form filling. Do not trigger merely because the user asks a question about an attached PDF.

Turn the conversation and workspace material into a spoken podcast-style audio file (.wav), single- or multi-voice. Trigger with "make a podcast", "create an audio overview", "turn this into a podcast", "narrate this", or whenever the user wants an audio version of the material.

Run a final review of accessibility, AI-template tropes, hierarchy/rhythm, and interaction states, then fix what's found. Use only when the user explicitly asks to polish the build, run final checks, or make it ready to ship.

Create or edit PowerPoint presentations (.pptx) — pitch decks, slide decks, presentations. Trigger on "deck", "slides", "presentation", ".pptx", or any request to build/modify slides. Produces an editable .pptx the user can open in PowerPoint/Keynote/Google Slides.

Design a process / workflow diagram (swimlane / BPMN-style flow) from the conversation and workspace material, delivered as a Mermaid `.mmd` diagram that renders natively in the panel. Trigger with "map this process", "draw the workflow", "create a swimlane diagram", "model this as BPMN", or whenever the user wants a business/operational process visualized.

Create or apply a cohesive visual theme for a deck, document, report, or HTML artifact. Use only when the user asks for a theme, reusable visual direction, palette/type system, or wants an existing artifact re-themed.

Create a general explanatory visual — a mechanism drawing, simple flow/chart, or interactive explainer — as .mmd/.svg/.png/.html. Use when no specialized process, architecture, mind-map, or rigorous data-visualization skill fits better.

Create or edit spreadsheets (.xlsx) — data tables, financial models, budgets, trackers, cleaned/restructured tabular data. Trigger when a spreadsheet is the primary output, the user references an .xlsx/.csv by name, or asks for a model/budget/table as Excel. Not when the deliverable is a Word doc, PDF, or report.

Package an escalation for engineering, product, or leadership with full context. Use when a bug needs engineering attention beyond normal support, multiple customers report the same issue, a customer is threatening to churn, or an issue has sat unresolved past its SLA.

Multi-source research on a customer question or topic with source attribution. Use when a customer asks something you need to look up, investigating whether a bug has been reported before, checking what was previously told to a specific account, or gathering background before drafting a response.

Draft a professional customer-facing response tailored to the situation and relationship. Use when answering a product question, responding to an escalation or outage, delivering bad news like a delay or won't-fix, declining a feature request, or replying to a billing issue.

Draft a knowledge base article from a resolved issue or common question. Use when a ticket resolution is worth documenting for self-service, the same question keeps coming up, a workaround needs to be published, or a known issue should be communicated to customers.

Triage and prioritize a support ticket or customer issue. Use when a new ticket comes in and needs categorization, assigning P1-P4 priority, deciding which team should handle it, or checking whether it's a duplicate or known issue before routing.

Answer data questions -- from quick lookups to full analyses. Use when looking up a single metric, investigating what's driving a trend or drop, comparing segments over time, or preparing a formal data report for stakeholders.

Profile and explore a dataset to understand its shape, quality, and patterns. Use when encountering a new table or file, checking null rates and column distributions, spotting data quality issues like duplicates or suspicious values, or deciding which dimensions and metrics to analyze.

Write correct, performant SQL across all major data warehouse dialects (Snowflake, BigQuery, Databricks, PostgreSQL, etc.). Use when translating a natural-language data need into SQL, writing or optimizing queries, translating between dialects, or building complex analytical queries with CTEs, window functions, or aggregations.

Apply statistical methods including descriptive stats, trend analysis, outlier detection, and hypothesis testing. Use when analyzing distributions, testing for significance, detecting anomalies, computing correlations, or interpreting statistical results.

QA an analysis before sharing -- methodology, accuracy, and bias checks. Use when reviewing an analysis before a stakeholder presentation, spot-checking calculations and aggregation logic, verifying a SQL query's results look right, or assessing whether conclusions are actually supported by the data.

Generate developer handoff specs from a design. Use when a design is ready for engineering and needs a spec sheet covering layout, design tokens, component props, interaction states, responsive breakpoints, edge cases, and animation details.

Synthesize user research into themes, insights, and recommendations. Use when you have interview transcripts, survey results, usability test notes, support tickets, or NPS responses that need to be distilled into patterns, user segments, and prioritized next steps.

Plan, conduct, and synthesize user research. Trigger with "user research plan", "interview guide", "usability test", "survey design", "research questions", or when the user needs help with any aspect of understanding their users through research.

Write or review UX copy — microcopy, error messages, empty states, CTAs. Trigger with "write copy for", "what should this button say?", "review this error message", or when naming a CTA, wording a confirmation dialog, filling an empty state, or writing onboarding text.

Create or evaluate an architecture decision record (ADR). Use when choosing between technologies (e.g., Kafka vs SQS), documenting a design decision with trade-offs and consequences, reviewing a system design proposal, or designing a new component from requirements and constraints.

Review code changes for security, performance, and correctness. Trigger with a PR URL or diff, "review this before I merge", "is this code safe?", or when checking a change for N+1 queries, injection risks, missing edge cases, or error handling gaps.

Structured debugging session — reproduce, isolate, diagnose, and fix. Trigger with an error message or stack trace, "this works in staging but not prod", "something broke after the deploy", or when behavior diverges from expected and the cause isn't obvious.