15 executable Agent skills distilled from the system prompts of 165 top AI products
kangarooking/system-prompt-skills
Skill Claude CodeCodex
A guide for designing systems where several specialised AI agents share work. It covers dividing responsibilities, passing short task summaries, managing task stages, and checking results.
kangarooking/system-prompt-skills
Skill Claude CodeCodex
A Chinese-language guide for designing systems that show where information comes from, such as document question-answering or search-based answers. It covers inline source markers, keeping citations during rewrites, and making factual claims traceable.
kangarooking/system-prompt-skills
Skill Claude CodeCodex
Design guidance for AI agents that edit code and work with files and Git. Git is a system for tracking code changes and their history.
kangarooking/system-prompt-skills
Skill Claude CodeCodex
Design guidance for managing the limited amount of text an AI can consider at once, called its context window. It covers summaries, delayed loading, persistent memory, and token budgets.
kangarooking/system-prompt-skills
Skill Claude CodeCodex
Design guidance for how an AI should classify requests, choose a workflow, ask clarifying questions, and decide how independently to act.
kangarooking/system-prompt-skills
Skill Claude CodeCodex
Injection defense is a set of rules for stopping untrusted text from taking control of an AI agent. Prompt injection is an attack where content such as a document or webpage contains instructions meant to override the agent’s rules.
kangarooking/system-prompt-skills
Skill Claude CodeCodex
Design guidance for giving an AI a persistent memory system. It covers storing, finding, using, changing, and deleting information such as user preferences and project knowledge.
kangarooking/system-prompt-skills
Skill Claude CodeCodex
Mobile adaptation is a set of response rules for AI used on phones and tablets. It adjusts answer length, structure, and formatting to fit smaller screens.
kangarooking/system-prompt-skills
Skill Claude CodeCodex
A set of rules for controlling an AI assistant’s answer length, format, and writing style.
kangarooking/system-prompt-skills
Skill Claude CodeCodex
Persona design defines an AI’s core identity, role, limits, and relationship with the user. It answers what the AI is and how it should behave in a specific product or context.
kangarooking/system-prompt-skills
Skill Claude CodeCodex
A personality system is a set of switchable style layers for an AI, such as friendly or professional. It keeps the AI’s core role separate from its tone and interaction style.
kangarooking/system-prompt-skills
Skill Claude CodeCodex
A framework for designing multiple safety layers around an AI system, including input checks, permission limits, output filtering, and refusal rules.
kangarooking/system-prompt-skills
Skill Claude CodeCodex
A set of rules for deciding when an AI assistant should search online or in other information sources, and how it should use the results.
kangarooking/system-prompt-skills
Skill Claude CodeCodex
Tool specification defines how an AI discovers, describes, authorizes, and uses external tools. Tools are connected functions or services, such as APIs, browsers, or file operations.
kangarooking/system-prompt-skills
Skill Claude CodeCodex
A set of guidelines for making voice-based assistant conversations brief, natural, and safe. It covers spoken wording, supported languages, response length, and boundaries such as not identifying or imitating speakers.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: