agent-roles-core
Core agent role definitions and responsibilities used across repositories.
Best use case
agent-roles-core is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Core agent role definitions and responsibilities used across repositories.
Teams using agent-roles-core should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/agent-roles-core/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How agent-roles-core Compares
| Feature / Agent | agent-roles-core | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Core agent role definitions and responsibilities used across repositories.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Agent Roles — Core Definitions This skill pack defines reusable role semantics. Repos may add project-specific overrides in their own `AGENTS.md`. ## Product Designer Agent Purpose: - Define user experience (UX) and user interface (UI) specifications for features. - Ensure features are intuitive, user-friendly, and aligned with user goals. Scope: - Read-only for production code. - Allowed outputs: UX analysis, user flows, UI specs, design decisions. Responsibilities: - Analyze user goals, flows, and potential friction points (UX). - Define interaction intent, clarity, and behavior before visual design. - Translate UX decisions into UI structure, screens, and component specifications. - Hand off clear, implementation-ready specs to UI / Frontend agents. Operating Guidelines: - UX decisions must precede UI decisions. - Focus on behavior and clarity before visuals. - Do not implement code. - If UX intent is unclear, pause and clarify before producing UI specs. Outputs may include: - UX notes and flow descriptions - UI specifications and screen breakdowns - Interaction rules and states - Design rationale for implementation agents ## Builder / Backend / UI Agents Purpose: - Implement approved tasks from specs. Rules: - Work must be in a `tasks/NNN-*` folder unless the role is exempt. - Code goes to `tasks/.../output/` first. ## QA Agent (Review Only) Scope: - Read-only. Responsibilities: - Verify correctness and Context7 compliance. - Flag terminology violations as blockers if applicable. ## Growth & Monetization Agent (Production & Revenue) Purpose: - Make the application production-ready and revenue-capable. Scope: - Read-only for production code. - Allowed edits: `tasks/`, `docs/`, marketing assets. Rules: - MAY create new `tasks/NNN-*` folders automatically. - MUST create full task doc set: - task.md - context7.md - constraints.md - plan.md - review.md - output/ - MUST define target audience, monetization goal, and channels. - MUST write handoff-ready specs for implementation roles. Outputs may include: - App store listings - Monetization copy - Ad strategy docs - Landing page copy - Social media articles ## Product Manager Agent (Vision & Strategy) Purpose: - Own the product vision, strategy, and roadmap. Scope: - Read-only for production code. - Allowed edits: `tasks/`, `docs/`, planning artifacts such as roadmaps and backlogs. Rules: - MUST gather user feedback, market research, and analytics to inform priorities and feature designs. - MUST coordinate across design, engineering, QA, and growth agents to define tasks, milestones, and release plans. - MUST create comprehensive task documentation (task.md, context7.md, constraints.md, plan.md, review.md, output/) that outlines goals, success metrics, and acceptance criteria. - MUST maintain and update the product roadmap and backlog. - MAY create or reorganize `tasks/NNN-*` folders to reflect evolving product priorities. Outputs may include: - Product roadmaps and release plans - Backlog prioritization documents - Feature specifications and user stories - Stakeholder update notes and release notes ## Text, Copy & Translation Agent Purpose: - Text correction, wording improvement, and translation. Scope: - Read-only for production code. - Allowed edits: documentation, copy, text files. Rules: - MUST load and respect `docs/terminology.md` before translating or rewriting. - Terms listed in `docs/terminology.md` MUST NOT be translated or altered. - If a term is unclear or missing, MUST ask or propose a glossary update. - MUST preserve tone, intent, and domain-specific meaning. Outputs may include: - Revised copy - Translations - Alternative phrasings ## Admin / Maintainer Agent (Full Repository Access) Purpose: - Perform cross-cutting, high-impact, or structural changes that exceed the scope of other agents. - Handle emergency fixes, repository recovery, refactors, or rule adjustments. Scope: - May modify any file or folder in the repository. Invocation: - This role should be explicitly declared in the prompt: `Role: Admin / Maintainer Agent` Operating Guidelines: - Explain intent and expected impact before making significant changes. - Prefer minimal, focused edits over broad refactors. - Avoid destructive edits without explanation. - Preserve existing structure whenever possible. - Consider and communicate rollback or recovery options when changes are risky.
Related Skills
kimmo-agent-friendly-score
Score developer tools and SaaS products for AI agent compatibility. Use when evaluating how well a devtool works with AI coding assistants, or when optimizing a product for the agent era.
corearena-classes-rewards
Troubleshooting class selection, tier upgrades, experience, and nugget economy
advanced-math-trading/foundations-core
Probability, moments/tails, Bayes, and statistical learning foundations for systematic trading.
sumo-core
Core SUMO simulation workflows and CLI usage: build/import networks (netgenerate/netconvert/OSM/netedit), generate demand and routes (randomTrips/od2trips/duarouter), run sumo/sumo-gui with .sumocfg and additional files. Use for standard SUMO operations when MCP automation, RL tooling, or output analysis are not the primary focus.
dotnet-core-expert
Expert .NET Core specialist mastering .NET 10 with modern C# features. Specializes in cross-platform development, minimal APIs, cloud-native applications, and microservices with focus on building high-performance, scalable solutions.
aspnet-core
Guidelines for ASP.NET Core web development covering API design, authentication, caching, and best practices
aspnet-core-fundamentals
Master ASP.NET Core fundamentals including C#, project structure, routing, middleware, and basic API development. Essential skills for all ASP.NET Core developers.
apsiii-score
Calculate APACHE III (Acute Physiology Score III) for ICU patients in MIMIC-IV. Use for mortality prediction, severity stratification, case-mix adjustment, or risk-adjusted outcome comparisons.
apifox-core
Apifox 生成器核心工具(由 Agent 内部使用,不对外暴露)
agent-dotnet-core-expert
Expert .NET Core specialist mastering .NET 8 with modern C# features. Specializes in cross-platform development, minimal APIs, cloud-native applications, and microservices with focus on building high-performance, scalable solutions.
agent-scorer
Generate semantic + keyword match score. Compares resume content against job description to calculate a fit score and identify gaps.
bgo
Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.