Turn a raw product, app, bot or feature idea into one evidence-backed build blueprint (researched stack, epics, Given/When/Then criteria, tests) that coding agents build one epic per session.
Expert TypeScript engineering with advanced patterns, architectural design, performance optimization, testing strategies, and production-grade code quality. Use when building scalable TypeScript applications, implementing complex type systems, optimizing performance, designing maintainable architectures, or when the user asks for TypeScript engineering excellence, advanced patterns, or professional-grade code practices.
Reconcile accounts by comparing GL balances to subledgers, bank statements, or third-party data. Use when performing bank reconciliations, GL-to-subledger recs, intercompany reconciliations, or identifying and categorizing reconciling items.
Design and execute a social engineering penetration test including phishing, vishing, smishing, and physical pretexting campaigns to measure human security resilience and identify training gaps.
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
When the user wants to reduce churn, build cancellation flows, set up save offers, recover failed payments, or implement retention strategies. Also use when the user mentions 'churn,' 'cancel flow,' 'offboarding,' 'save offer,' 'dunning,' 'failed payment recovery,' 'win-back,' 'retention,' 'exit survey,' 'pause subscription,' 'involuntary churn,' 'people keep canceling,' 'churn rate is too high,' 'how do I keep users,' or 'customers are leaving.' Use this whenever someone is losing subscribers or wants to build systems to prevent it. For post-cancel win-back email sequences, see email-sequence. For in-app upgrade paywalls, see paywall-upgrade-cro.
Find and compare restaurants, bars, cafes, sights, museums, parks, tours, adventure parks and other things to do using Google Maps and the web through Bladebro. Use for what to do, where to eat/drink, attractions, nightlife, activities, or nearby recommendations.
Create a 3×3 animated GIF sticker pack from a character reference image plus nine reactions or a theme. Use for nine-grid motion sticker, 九宫格动态表情包, or transparent sticker-pack requests; do not use for ordinary image edits, single stickers, or generic GIF conversion.
Run ship-safe security and quality audit on the current project. Executes npx ship-safe audit . and reports findings by severity. Use before shipping any feature or PR.
Generate professional reports — sprint retrospectives, financial summaries, analytics dashboards, and incident postmortems — from structured data with templates, charts, and multi-format output. Use when the user requests report generation or provides relevant inputs for this workflow.
User-facing wrapper for the Superfield merge workflow. Use when the user explicitly asks to perform the repository's deterministic merge flow for the current selected PR.
Programmatic Clerk sign-in for e2e testing. Use when the application authenticates with Clerk and you need to sign in test users (including multi-user scenarios) without interacting with the Clerk UI. Note this only works for applications built with Replit's Clerk Authentication support.
Use when working with Bitbucket Pipelines in Azure/Microsoft environments, or when comparing Bitbucket vs GitHub Actions vs Azure DevOps for CI/CD. Triggers on any Bitbucket Pipelines question, especially regarding Azure authentication, OIDC, deployment environments, or pricing.
Ruby on Rails framework patterns for Rails 7.1+ and 8.x apps. Covers the directory contract, skinny controllers with service objects, form objects, query objects, idiomatic ActiveRecord, background jobs, ViewComponent, Hotwire, and the Rails 8 Solid stack. Use when building or reviewing Rails apps, controllers, models, services, jobs, or views.
Analyze a repository's portfolio trust-signal quality for 2026 hiring and
write a recommendations report you can act on. Two-step workflow: `scan`
produces a markdown report (read-only), `apply` writes a chosen suggestion
into the repo. Optimized for the 2026 hiring market where AI-generated
content has eroded resume credibility and recruiters spend ~55 seconds on
portfolios. Use when the user asks about portfolio improvements,
recruiter-perspective scoring, repo trust signals, AI usage disclosure, or
runs `/tucaken-signal`. Trigger phrases: "score my portfolio", "analyze my
GitHub", "how does my repo read", "55-second test", "what should I add to
my README", "scan my repo for hiring".