Write, review, or improve UIKit code following best practices for view controller lifecycle, Auto Layout, collection views, navigation, animation, memory management, and modern iOS 18–26 APIs. Use when building new UIKit features, refactoring existing views or view controllers, reviewing code quality, adopting modern UIKit patterns (diffable data sources, compositional layout, cell configuration), or bridging UIKit with SwiftUI. Does not cover SwiftUI-only code.

Resolve pull request feedback by critically assessing each item, fixing source files (not generated files), regenerating derived artifacts, running lint/format, committing, pushing, and replying on the appropriate GitHub thread. Use when the user asks to address PR feedback, respond to reviewer suggestions, fix issues from code review, or resolve GitHub review comments, PR issue comments, or review summaries.

Drafts and refines pull request descriptions with consistent structure: context, motivation, summary of changes, and links to tickets or docs. Use when opening or updating a PR, writing a merge request description, or when the user asks for PR text, release notes from a branch, or a changelog-style summary of work.

Use when the user wants regression hunting after a change. Identify nearby flows, shared code paths, error states, and configuration edges that may have broken even if the main fix works, then run focused checks such as related tests, adjacent commands, or neighboring API paths. Good triggers include "check for regressions", "what else might this have broken", and "test the surrounding area".

Drizzle ORM patterns -- schema definition, type-safe queries, relations, migrations, transactions, upserts, prepared statements, and connection setup. Use when building or reviewing apps with Drizzle ORM, when setting up a new database with Drizzle, when writing queries or migrations, or when configuring Drizzle for production.

Run task evals across multiple Claude models and compare results side-by-side. Use when you want to understand how a skill performs across different models, identify model-specific gaps versus universal tile issues, or validate a skill before publishing it to the registry.

Reference material for writing Rego/OPA policies in a specific domain — Kubernetes admission control, Terraform/CloudFormation infrastructure-as-code validation, HTTP API authorization (request body validation, rate limiting), RBAC/ABAC access control models, metadata annotations, or Regal linter compliance by rule category. Load this when rules.md's general Rego style rules aren't enough and you need worked examples or domain-specific patterns for one of these areas.

Build HIPAA-compliant telemedicine apps with PubNub real-time messaging

Build real-time auction platforms with PubNub bidding and countdowns

Implement real-time presence tracking with PubNub

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

Creates boundary-point validation contracts, defines invariant-based success criteria, and sets up automated verification probes so reliability workflows trigger on objective evidence rather than intuition. Use when designing robust handoff, memory-persistence, or tool-call reliability workflows; when you need to verify handoffs work, check memory persistence, validate tool calls succeeded, or convert vague reliability goals into concrete, testable checks at each boundary point with explicit failure-class mapping (operational vs. critical); or when you want to test your workflow end-to-end, make sure it works, or verify your automation runs correctly using read-back probes and escalation triggers rather than agent confidence.

Interview stakeholders to clarify ambiguous or underspecified requirements before writing code. Use when receiving a new task, feature request, or bug report that lacks clear acceptance criteria. Produces clarified requirements ready for spec authoring. Common triggers: "new feature", "build me", "implement", "add support for", or any task where requirements are vague or incomplete.

Verify that implementation and tests remain synchronized with specs after code changes. Use when code has been generated or modified from specs, after implementation is complete, or when reviewing a PR that touches spec-covered code. Reports mismatched targets, broken test links, and undocumented behavioral changes. Common triggers: "verify the spec", "check spec alignment", "are specs up to date", or after completing implementation work.

Create or update .spec.md files from clarified requirements. Use when requirements have been gathered and confirmed, and specs need to be written or updated before implementation begins. Produces well-structured spec files with frontmatter, requirements, and test links. Common triggers: "write the spec", "update the spec", "create a spec for", or after requirement-gathering completes.

Use when designing, reviewing, or implementing HTTP APIs — error and warning handling, resource state and lifecycle, read-endpoint structure, pagination, and authentication. Triggers on error responses and formats, response envelopes, webhook payloads, how an endpoint should fail; modelling a resource lifecycle (status fields, state machines, webhook event names, enum vs parseable string); structuring read endpoints (screen-shaped/BFF vs canonical resource, aggregation, cursor vs offset pagination); and auth design (security schemes, API keys vs bearer tokens, stepped-up tokens). Apply whenever an API surfaces a failure, state change, view of data, or auth requirement to a client.