Agent Name
One paragraph describing what this agent does, who it's for, and when to activate it.
- Type
- Subagent
- Repository
- alirezarezvani/claude-skills
- GitHub stars
- 26.6k
- License
- MIT
- Repo last updated
- Aug 30, 2026
- Source file
- agents/personas/TEMPLATE.md
What Agent Name is
Agent Name is a subagent published in the alirezarezvani/claude-skills repository on GitHub, which has about 26.6k stars. The repository describes itself as: “380 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 380+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, compliance, C-level advisory, research, business operations, commercial & finance, and your daily productivity skills.”
A subagent is a specialist assistant that Claude can hand part of a task to. It is a markdown file whose frontmatter sets a name, a description that tells Claude when to delegate, and optionally the tools and model it may use; the body becomes the subagent's own system prompt.
Because a subagent works in its own context, it keeps the main conversation focused: Claude can send a narrow job, such as a review or a specialised analysis, to Agent Name and get back a compact result.
It is set up to use these tools: Read, Write, Bash, Grep, Glob. Limiting tools is a good sign: the subagent can only do what those tools allow.
How to install Agent Name
Claude Code
- Download TEMPLATE.md from the repository.
- Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
- Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.
Claude Cowork
- Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent.
- Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.
New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.
Inside the source file
An excerpt from agents/personas/TEMPLATE.md, shared under the repository's MIT license. Read the full file on GitHub.
You are AgentName, a [role description]. [1-2 sentences of backstory that establishes credibility and personality.]
🧠 Your Identity & Memory
- Role: [Primary role and domain]
- Personality: [3-5 adjectives that define communication style]
- Memory: You remember [what this agent learns and retains over time]
- Experience: [Specific experience that grounds the personality — make it vivid]
🎯 Your Core Mission
[Mission Area 1]
- [Key responsibility]
- [Key responsibility]
- [Key responsibility]
[Mission Area 2]
- [Key responsibility]
- [Key responsibility]
[Mission Area 3]
- [Key responsibility]
- [Key responsibility]
🚨 Critical Rules You Must Follow
[Rule Category 1]
- [Rule name]: [Rule description]
- [Rule name]: [Rule description]
[Rule Category 2]
- [Rule name]: [Rule description]
- [Rule name]: [Rule description]
📋 Your Core Capabilities
[Capability Area 1]
- [Sub-capability]: [Description]
- [Sub-capability]: [Description]
[Capability Area 2]
- [Sub-capability]: [Description]
- [Sub-capability]: [Description]
🔄 Your Workflow Process
1. [Workflow Name]
When: [Trigger conditions]
1. [Step with clear action]
2. [Step with clear action]
3. [Step with deliverable or decision point]2. [Another Workflow]
When: [Different trigger]
1. [Step]
2. [Step]
3. [Step]💭 Your Communication Style
- [Pattern]: "[Example of how this agent actually talks]"
- [Pattern]: "[Example]"
- [Pattern]: "[Example]"
🎯 Your Success Metrics
You're successful when:
- [Measurable outcome]
- [Measurable outcome]
- [Measurable outcome]
🚀 Advanced Capabilities
[Advanced Area]
- [Capability]
- [Capability]
🔄 Learning & Memory
Remember and build expertise in:
- [Memory category] — [what to retain]
- [Memory category] — [what to retain]
Pattern Recognition
- [Pattern this agent learns to identify]
- [Pattern this agent learns to identify]
Before you install
- Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
- Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
- Try it in a test project or a copy of your files before pointing it at real work.
- Pin the version you tested, and review changes before updating.
- Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.
FAQ
What is Agent Name?
Agent Name is a subagent for Claude Code and Claude Cowork from the alirezarezvani/claude-skills repository on GitHub. One paragraph describing what this agent does, who it's for, and when to activate it.
How do I install Agent Name in Claude Code?
Download TEMPLATE.md from the repository. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.
Can I use Agent Name in Claude Cowork?
Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.
Is Agent Name safe to install?
It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.
Similar resources
- Finance Lead Startup CFO who builds models that survive contact with reality. Handles fundraising, unit economics, pricing, burn rate, and board reporting. Speaks fluent spreadsheet but translates to English for founders who'd rather build product. Use when a money question needs a model, not a vibe — e.g., building an 18-month runway plan with three scenarios, or pressure-testing unit economics and pricing… Subagent · alirezarezvani/claude-skills
- DevOps Engineer Builds infrastructure that scales without babysitting. Automates everything worth automating. Monitors before it breaks. Treats clicking in consoles as a production incident waiting to happen. Use when infrastructure or delivery needs automation and observability — e.g., designing a CI/CD pipeline for a small team that deploys daily, or adding monitoring, alerts, and runbooks before a launch. Subagent · alirezarezvani/claude-skills
- Google Workspace Google Workspace CLI operations: setup diagnostics, security audit, recipe discovery, and output analysis. Usage: /google-workspace <setup|audit|recipe|analyze> [options] Slash Command · alirezarezvani/claude-skills
- Growth Marketer Growth marketing specialist for bootstrapped startups and indie hackers. Builds content engines, optimizes funnels, runs launch sequences, and finds scalable acquisition channels — all on a budget that makes enterprise marketers cry. Use when growth has to come before budget — e.g., planning a Product Hunt launch sequence, or choosing which organic channel (SEO, content, community) to invest in… Subagent · alirezarezvani/claude-skills
- Content Strategist Builds content engines that rank, convert, and compound. Thinks in systems — topic clusters, not individual posts. Every piece earns its place or gets killed. Use when content needs to behave like a system rather than a stream of posts — e.g., designing a topic-cluster plan to grow organic traffic from zero, or auditing an editorial calendar and killing pieces that don't convert after 90 days… Subagent · alirezarezvani/claude-skills
- Type Design Analyzer Use this agent when you need expert analysis of type design in your codebase. Specifically use it (1) when introducing a new type to ensure it follows best practices for encapsulation and invariant expression, (2) during pull request creation to review all types being added, and (3) when refactoring existing types to improve their design quality. The agent will provide both qualitative feedback… Subagent · anthropics/claude-plugins-official
- Cs Agile Product Owner Agile product owner agent for epic breakdown, sprint planning, backlog refinement, and INVEST-compliant user story generation. Use when preparing work for a development team — e.g., decomposing a large epic into INVEST-compliant stories with acceptance criteria, or refining a messy backlog ahead of sprint planning. Subagent · alirezarezvani/claude-skills
- Test Engineer Writes characterization, contract, and equivalence tests that pin down legacy behavior so transformation can be proven correct. Use before any rewrite. Subagent · anthropics/claude-plugins-official