productivity▌

Use jobs as the unit of work and keep phases explicit.

Expert PostgreSQL optimization, replication setup, and advanced feature implementation. \n \n Covers query analysis with EXPLAIN, index design across B-tree/GIN/GiST/BRIN types, and JSONB storage strategies with containment queries \n Includes streaming and logical replication setup with lag monitoring via pg_stat_replication \n Provides VACUUM tuning, autovacuum configuration, bloat detection, and statistics refresh workflows \n Supports PostgreSQL extensions including PostGIS, pgvector, pg_trg

Strip designs to their essence by removing unnecessary complexity and revealing core functionality. \n \n Analyzes complexity sources across information architecture, visual design, layout, interactions, and content to identify what can be removed or hidden \n Applies ruthless simplification strategies including progressive disclosure, element consolidation, color/typography reduction, and flattened component hierarchies \n Requires the frontend-design skill and its Context Gathering Protocol as

Library-grade Vue composables that accept plain values, refs, or getters as inputs. \n \n Use MaybeRefOrGetter for read-only inputs (computed-friendly) and MaybeRef for writable two-way inputs; normalize with toValue() or toRef() inside reactive effects \n Normalize inputs using toRef() for watcher sources and toValue() for non-reactive resolution to keep behavior predictable across different input types \n Avoid MaybeRefOrGetter when parameters are callbacks, predicates, or comparators to preve

Build AI-powered Node.js/TypeScript applications with Genkit flows, tools, and multi-model support. \n \n Genkit is provider-agnostic; supports Google AI, OpenAI, Anthropic, Ollama, and other LLM providers via plugins \n Define flows with type-safe schemas using Zod, execute generation requests, and compose multi-step AI workflows in TypeScript \n Requires Genkit CLI v1.29.0+; recent major API changes mean you must consult genkit docs:read and common-errors.md for current patterns, not prior kno

Self-contained HTML playgrounds with live preview, interactive controls, and copyable prompt output. \n \n Includes five templates for common playground types: design decisions, data exploration, concept mapping, document critique, and code review \n Every playground features instant live preview, natural-language prompt generation that only mentions non-default choices, and a one-click copy button \n Built as single HTML files with no external dependencies, dark theme by default, and sensible p

Generates GitHub Copilot migration instructions by analyzing code differences between project versions. \n \n Compares two project states (branches, commits, or tags) to extract transformation patterns, API changes, and architectural shifts \n Creates a .github/copilot-migration-instructions.md file with mandatory rules, validated transformations, API correspondences, and obsolete patterns to avoid \n Supports multiple migration types: framework version upgrades, architecture refactoring, techno

USPTO provides specialized APIs for patent and trademark data. Search patents by keywords/inventors/assignees, retrieve examination history via PEDS, track assignments, analyze citations and office actions, access TSDR for trademarks, for IP analysis and prior art searches.

Identifies error-prone APIs, configurations, and designs that enable developer security mistakes. \n \n Evaluates six categories of sharp edges: algorithm selection footguns, dangerous defaults, primitive vs. semantic APIs, configuration cliffs, silent failures, and stringly-typed security \n Provides a four-phase analysis workflow: surface identification, edge case probing, threat modeling against three adversary types (malicious, lazy, confused), and validation \n Includes severity classificat

Automatically capture errors, corrections, and best practices to evolve agent capabilities safely over time. \n \n Records seven types of triggers (failures, user corrections, feature requests, API errors, knowledge gaps, better approaches, task reviews) into structured markdown files with deduplication to avoid low-value entries \n Promotes repeated patterns (≥3 occurrences) from learning logs into permanent capability files (AGENTS.md, TOOLS.md, SOUL.md) or extracts them as independent skills