Skill Relationships
Skill → Skill usage relationships, with cross-layer references. Same color blocks indicate the same skill form.
Skill Composition
Each skill is designed for a specific kind of caller — some only fire when you name them, others load automatically when the model judges them relevant. The split below summarises both modes at a glance.
These skills only fire when you call them by name. The agent will not load them on its own — they stay inert until invoked.
These skills are loaded automatically by the agent when it judges the context relevant. You usually don't need to call them yourself.
Skill List
Helps users discover and install agent skills from the open ecosystem via the Skills CLI. It parses natural-language requests, runs `npx skills find` to search, presents options with install commands, and can install globally. Value: quickly extends agent capabilities with community skills.
A lightweight brainstorming skill for fast decision-making before creative or architectural work. It uses a 4-step flow (discover, propose, converge, capture) to align on direction with the user via batched questions and trade-off analysis. Value: avoids premature coding and delivers an approved, actionable direction quickly.
A streamlined brainstorming skill invoked before creative or architectural work to align on direction fast. It uses a 4-step flow (Discover, Propose, Converge, Capture) with batched questions and YAGNI principles. Value: quick, good decisions without process overhead, preventing premature implementation.
A skill providing various XSS payload examples (HTML, SVG, JS URI, etc.) for security testing. Method: list injection snippets. Value: quick reference to verify XSS defenses.
A test skill containing various XSS payload examples for security testing. It provides common and bypass XSS vectors to validate filtering. Value: quick reference for XSS detection checks.
test3 is a placeholder Agent Skill with no described functionality, methods, or deliverables. It provides no procedures, tools, or outputs and currently holds no practical value for users or agents.
