Reads a site feature specification file and converts it into a structured, actionable development task list saved to the project memory bank. Use when you need to break down requirements into developer tasks, plan project work from a PRD or spec, convert feature specifications into tickets with acceptance criteria, or create a task breakdown from site-setup documentation. Produces per-task acceptance criteria, file references, and technical stack notes drawn exclusively from the specification — no scope creep or unspecified features added.

Analyzes, redesigns, and automates business workflows to eliminate bottlenecks and improve efficiency. Creates process flow diagrams, identifies root-cause inefficiencies, writes standard operating procedures (SOPs), designs automation sequences, and produces implementation roadmaps with ROI estimates. Use when the user asks to map a business process, audit a workflow for inefficiencies, identify bottlenecks or handoff failures, create SOPs or checklists, design automation for repetitive tasks, apply Lean or Six Sigma techniques, or build a phased process improvement plan.

Develops brand guidelines, audits content for brand consistency, creates brand voice documentation, defines visual identity standards (colors, typography, logo usage), and produces brand strategy deliverables including positioning statements and messaging frameworks. Use when the user asks about brand guidelines, brand voice, logo usage, style guides, brand audits, naming, maintaining brand consistency across materials, or building a brand identity system from scratch.

Reviews web application UI using Playwright screenshot captures to identify visual bugs, broken interactive elements, layout regressions, and specification mismatches. Produces structured evidence-based QA reports with screenshot references, pass/fail verdicts, and prioritised fix lists. Use when asked to QA a web page, find UI bugs, run visual testing, check screenshot evidence, validate an implementation against a spec, review responsive layout, or verify interactive elements like accordions, forms, and navigation menus.

Sends HTTP requests to REST and GraphQL API endpoints, validates response codes, headers, and payloads, measures response times against SLA thresholds, generates structured test suites, and produces test reports covering functional, security, and performance scenarios. Use when the user asks about testing APIs, validating endpoints, checking HTTP status codes or response bodies, load testing, stress testing, debugging REST or GraphQL services, testing authentication flows, checking rate limiting, detecting SQL injection or OWASP API vulnerabilities, or integrating API tests into CI/CD pipelines.

Sends HTTP requests to REST and GraphQL API endpoints, validates response codes, headers, and payloads, measures response times against SLA thresholds, generates structured test suites, and produces test reports covering functional, security, and performance scenarios. Use when the user asks about testing APIs, validating endpoints, checking HTTP status codes or response bodies, load testing, stress testing, debugging REST or GraphQL services, testing authentication flows, checking rate limiting, detecting SQL injection or OWASP API vulnerabilities, or integrating API tests into CI/CD pipelines.

Expert user experience researcher that creates usability test plans, designs surveys, conducts user interview analysis, builds data-backed personas, maps user journeys, and synthesizes research findings into prioritized, actionable design recommendations. Use when the user asks about usability testing, user interviews, UX audits, survey design, persona creation, user journey mapping, A/B testing analysis, heatmap interpretation, accessibility research, or translating research data (interview notes, survey results, behavioral analytics) into design decisions. Distinct from general product management or analytics skills by focusing specifically on user behavior research methodology, participant recruitment, study design, and insight communication.

Designs and tracks scientific experiments, A/B tests, and feature rollouts for product and engineering teams. Defines experiment hypotheses, calculates required sample sizes, tracks variant performance metrics, analyzes statistical significance, and delivers ship/no-ship recommendations. Use when the user asks about designing A/B tests or split tests, setting up control vs. treatment groups, tracking experiment results, calculating statistical significance or confidence intervals, managing feature flag rollouts, or deciding whether to ship a feature based on experiment data.

Collects, categorizes, and synthesizes user feedback from multiple channels into actionable product insights. Performs sentiment scoring, theme tagging, NPS/CSAT analysis, feature request ranking, priority matrix generation, and Voice of Customer reporting. Use when the user asks to analyze customer feedback, survey responses, NPS scores, CSAT data, feature requests, app reviews, support tickets, social media mentions, or any Voice of Customer data; or when they need to prioritize a product roadmap from user input, identify top pain points from feedback, understand why users are churning, or produce an executive feedback report.

Designs and documents UI component libraries, design token systems, color palettes, typography scales, spacing systems, and responsive layout frameworks. Produces design specifications, style guides, and developer-ready handoff documentation. Use when a user needs to create a design system, build a component library, define a color palette or typography scale, design UI mockups or wireframes, establish a visual style guide, set up CSS tokens or theming (including dark mode), specify accessible interface components (WCAG AA), or produce layout compositions for web or mobile interfaces.

Orchestrates complete multi-agent development pipelines from specification to production-ready implementation. Coordinates specialist agents (PM, ArchitectUX, Developer, QA) in a structured sequence, enforcing task-by-task Dev↔QA validation loops with automatic retry logic and quality gates. Use when the user asks to run the full development pipeline, execute the end-to-end workflow, coordinate multiple agents on a project, automate build-to-QA cycles, or manage a project from spec to delivery.

Reviews code changes, validates test coverage, checks deployment criteria, and gates production approvals based on evidence from automated screenshots, test results, and specification compliance checks. Defaults to "NEEDS WORK" unless comprehensive evidence supports readiness. Use when a user asks to approve a PR, run a release readiness check, validate deployment criteria, perform a QA gate review, check if code is production-ready, or assess integration test results.

Creates and manages project artifacts including project charters, Gantt-style timelines, RACI matrices, risk registers, and stakeholder communication plans. Tracks milestones, deadlines, resource allocation, and budget variance across cross-functional teams. Generates status reports, facilitates change control, and produces lessons-learned documentation. Use when a user needs to plan a new project, build a project plan or roadmap, track milestone progress, write a status update, conduct a risk assessment, allocate resources across teams, coordinate cross-functional delivery, or align stakeholders on scope, timeline, or budget changes.

Filters consolidated sales data by territory, matches reports to assigned representatives, and sends personalized HTML report emails via SMTP — with full audit logging of every delivery attempt. Use when the user needs to send or schedule sales reports to reps, distribute territory-based reports, automate report delivery to a sales team, email territory data to assigned representatives, or review report distribution history. Covers daily/weekly scheduled sends, manual on-demand distribution, and querying the distribution audit trail.

Designs identity, authentication, and trust verification systems for autonomous AI agents in multi-agent environments. Capabilities include cryptographic credential issuance and rotation, mutual agent authentication, capability-based authorization policies, delegation chain verification, zero-trust peer verification protocols, append-only tamper-evident audit logging, and trust scoring based on verifiable outcomes. Use when designing agent authentication, agent-to-agent trust, agent credentials, digital signatures for agents, zero-trust agent networks, agent certificate management, identity federation across frameworks, or audit trails for autonomous agent actions. Especially relevant when agents execute high-stakes operations such as financial transactions, infrastructure deployment, or API calls to external systems.

Creates structured software and platform evaluation reports with weighted scoring matrices, TCO analysis, and adoption recommendations. Use when asked to compare tools, recommend software, evaluate platforms, choose between apps, or answer questions like "which tool should I use", "best software for X", "tool comparison", "software recommendation", "pros and cons of [tool]", or "help me pick between [A] and [B]". Produces comparison matrices, financial analyses, risk assessments, and phased implementation plans for business tool decisions.

Create a Google Meet meeting space and share the join link.

Create a Google Classroom course and invite students.

Review who attended a Google Meet conference and for how long.

Multi-path parallel product analysis with cross-model test-time compute scaling. Spawns parallel agents (Claude Code agent teams + Codex CLI) to explore product from multiple perspectives, then synthesizes findings into actionable optimization plans. Can invoke competitors-analysis for competitive benchmarking. Use when "product audit", "self-review", "发布前审查", "产品分析", "analyze our product", "UX audit", or "信息架构审计".