89 boosters for "persona" — open source, verified from GitHub, ready to install
Study Abroad Advisor is a comprehensive planning assistant that guides Chinese students through the entire study abroad process—from school selection and application strategy to visa preparation and overseas adaptation across 7 major destinations. It solves a high-demand, high-stakes problem for a specific demographic with actionable, data-driven guidance.
Outbound Strategist helps sales teams design signal-based, multi-channel prospecting sequences with precision targeting and research-driven personalization. Sales leaders and revenue teams benefit from a framework that prioritizes reply rates and qualified pipeline over volume-based outreach.
ZK Steward is an AI agent that helps users build interconnected, validated knowledge bases by adopting Niklas Luhmann's Zettelkasten methodology, switching between expert perspectives (Luhmann, Feynman, Munger, Ogilvy) based on task requirements. It's ideal for researchers, knowledge workers, and teams managing complex information who need systematic note-linking and cross-domain decision support.
A LinkedIn content strategy agent that helps professionals build thought leadership and personal brands by creating high-engagement posts tailored to LinkedIn's algorithm. Ideal for founders, job seekers, developers, and anyone looking to attract inbound opportunities through strategic content.
Delight is a skill booster that helps developers add joyful, personality-driven touches to interfaces—transforming functional designs into memorable user experiences. It benefits product teams, UX-focused developers, and anyone building customer-facing applications.
This file explains the Knowledge Base feature and how it's implemented. The knowledge base helps users store and manage information that can be used to help draft responses to emails. It acts as a personal database of information that can be referenced when composing replies. Users can create, edit,
Agents are the agentic logic layer of OpenJarvis. They determine how a query is processed -- whether it goes directly to a model, through a tool-calling loop, via ReAct reasoning, CodeAct code execution, recursive decomposition, or an external agent runtime. All agents implement the ABC and are reg
当用户对已有前任 Skill 说以下内容时，进入进化模式： 本 Skill 运行在 Claude Code 环境，使用以下工具： 本 Skill 在生成和运行过程中严格遵守以下规则：
MIRIX is a Multi-Agent Personal Assistant with an Advanced Memory System. It features a six-agent memory architecture (Core, Episodic, Semantic, Procedural, Resource, Knowledge Vault) with screen activity tracking and privacy-first design. 1. Follow PEP 8 strictly 3. Documentation
TinyClaw enables developers to run multiple specialized AI agents simultaneously with isolated workspaces and independent configurations, allowing for task-specific agent teams that can be routed via simple @agent_id syntax. This is valuable for projects requiring diverse AI capabilities (coding, writing, analysis) working in parallel without state interference.
This wiki is maintained entirely by your coding agent. No API key or Python scripts needed — just open this repo in Codex, OpenCode, or any agent that reads this file, and talk to it. Describe what you want in plain English: Or use shorthand triggers:
1. Create directory structure: 2. Write with required fields (see below) 3. Create with agent identity
"name": "edmunds-claude-code", "description": "Edmund's personal Claude Code setup with 14 productivity commands and 11 specialized AI agents for modern web development", "path": ".claude/commands/new-task.md",
"name": "claude-blog", "description": "AI-powered blog skill suite with 30 sub-skills and 5 agents. FLOW framework integration (Find/Optimize/Win, 30 evidence-led prompts), semantic topic-cluster planning + execution, multilingual publishing (translate/localize/locale-audit), Google API integration
Analyzes ANY input to find, improve, or create the right skill. Start with least privilege (, , , , ). Only add higher-risk tools when explicitly required:
根据用户第一条消息的语言，全程使用同一语言。 向用户询问蒸馏对象的角色，读取对应模板： 根据角色模板中的伦理要求，在收集材料前告知用户。不同角色的伦理侧重：
Use this skill only for explicit or requests. is the only supported entrypoint.
1. Initialize predictive-persona-performance operational context 2. Execute primary protocol actions 3. Validate results and generate output
Safe referencing of real people — their wisdom, skills, and contributions — without impersonation. K-lines, not cosplay. LLMs can impersonate anyone. This is: A Hero-Story card activates a conceptual cluster associated with a person:
"name": "claude-buddy", "description": "Permanent coding companion for Claude Code \u2014 survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.", "repository": "https://github.com/1270011/claude-buddy",
1. — CCPA/CPRA 15개 공개 의무·7대 권리·SPI 11종·주법 비교 기본 규칙 + 다음 조건부 블록 추가:
A prompt booster that teaches AI assistants (in Windsurf) how to help developers build static HTML websites using the Static generator framework. Ideal for developers creating blogs, landing pages, and personal sites who want AI-assisted development.
Activate when the user says any of: If the user provides a name as an argument (e.g. ), skip Q1 in intake and use it directly as the slug. Enter evolution mode when:
This project is an MCP server that's built using Node.js and the TypeScript SDK for MCP. When working on this project, make sure to refer to the type definitions for the MCP TypeScript SDK: https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/refs/heads/main/src/types.ts.
