// Use when the user greets you with hello, hi, hey, good morning, good afternoon, good evening, howdy, or any greeting — including greetings that also mention what they're working on. Responds with a friendly greeting and offers to help.
Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, audit codebase terminology, or mentions "domain model" or "DDD". Also triggers on "audit" with terminology context.
Cognitive load audit of UI code. Use this skill when the user wants to audit, review, or analyze UI components for cognitive load, usability, or UX quality. Triggers on: "ux audit", "cognitive load audit", "audit my form", "review this UI for usability", "check cognitive load", "is this form too complex", "analyze UX of these components", or any request to evaluate UI code against cognitive load principles, usability heuristics, or form design best practices. Also triggers when the user provides UI file paths and asks about complexity, overwhelm, or user confusion.
Multi-phase deep research pipeline that discovers, validates, and synthesizes information from many sources into a comprehensive report. Uses parallel Researcher subagents for maximum coverage and depth. Use this skill whenever the user says "deep research" followed by a topic, when they explicitly invoke it, or when you determine that a question requires thorough, multi-source investigation rather than a quick lookup. This is different from a simple documentation search or a single web query — use this when the user needs a comprehensive understanding of a topic drawn from many sources, cross-validated and synthesized into a structured report. Triggers include: "deep research on X", "research X thoroughly", "I need a full report on X", "dive deep into X", "investigate X comprehensively", or any context where surface-level answers won't cut it and the user (or you) needs authoritative, multi-source coverage of a topic.
Use when the user wants to run the autonomous skill optimization loop. Iteratively improves skills and their agents in the marketplace by modifying SKILL.md and agent files, evaluating changes via head-to-head ELO ranking, and keeping improvements.
Devil's advocate interrogation of a feature or idea. Use this skill whenever the user wants to pressure-test, challenge, refine, or deeply explore a feature, idea, plan, or proposal. Triggers on phrases like "interrogate this", "challenge my idea", "poke holes in this", "help me think this through", "is this a good idea", "what am I missing", or any request to stress-test thinking. Also use when the user describes a feature and seems uncertain or is asking for validation.
| name | example-greeter |
| description | Use when the user greets you with hello, hi, hey, good morning, good afternoon, good evening, howdy, or any greeting — including greetings that also mention what they're working on. Responds with a friendly greeting and offers to help. |
When the user greets you:
Keep the greeting concise (2-3 sentences). Do not be overly enthusiastic or use excessive punctuation.