Skip to main content
skill CX Codex

06-agent-generate — Claude Code skill: what it does, how to install

06-agent-generate generates agent and subagent scaffolds across the AI coding tools configured in your project from a role prompt.

MIT ★ 571 updated 2026-10-29

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add ai-driven-dev/framework
/plugin install aidd-context@aidd-framework
Open on GitHub

What 06-agent-generate does

The skill captures your role definition and compiles it into canonical agent files adapted for each active AI assistant. Execution runs strictly in three sequential steps: capture-agent defines scope and naming, write-agent renders files per target platform, and validate inspects output integrity.

Each action step executes its own validation block before proceeding to the next. The generation logic depends on contracts in references/agent-authoring.md, path mappings in references/tool-paths.md, and the base scaffold in assets/agent-template.md. This skill only handles agents and roles, explicitly skipping rules, hooks, commands, or regular skills.

What it helps with

  • scaffold specialized subagents across multiple host tools
  • generate agent files with correct frontmatter and directory paths
  • validate generated agent structure against authoring standards

Example prompts for the agent

  • Scaffold an agent for code review: role code-reviewer
  • Generate a database migration subagent across our project tools
  • Create a specialized release manager agent using assets/agent-template.md

How to install 06-agent-generate

1Plugin marketplace

/plugin marketplace add ai-driven-dev/framework
/plugin install aidd-context@aidd-framework

This installs the whole aidd-context plugin with all its skills

2Skills CLI (Vercel)

npx skills add ai-driven-dev/framework --skill 06-agent-generate -a claude-code

3Manually: put the files in place

~/.claude/skills/06-agent-generate/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/06-agent-generate/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about 06-agent-generate

How to install 06-agent-generate in Claude Code?

Register the marketplace with /plugin marketplace add ai-driven-dev/framework, then run /plugin install aidd-context@aidd-framework. You can also install it directly via npx skills add ai-driven-dev/framework --skill 06-agent-generate -a claude-code.

What does 06-agent-generate do?

It translates an intended role into concrete agent files tailored to each AI tool detected in your repository and checks them against project guidelines.

Can I use this skill to create slash commands or hooks?

No, it is strictly scoped to agents, subagents, and specialized roles. It does not generate commands, skills, rules, or hooks.

Source text

SKILL.md · MIT
---
name: 06-agent-generate
description: Generate an agent across the host AI tools a project uses. Use when the user wants to create, scaffold, or refactor an agent, subagent or specialized role. Not for other artifacts like skills, rules, commands, hooks.
argument-hint: role
---

# Agent Generate

Write one canonical agent from intent and render it per confirmed host tool, or once as a plugin source.

## Actions

| #   | Action          | Role                                           | Input        |
| --- | --------------- | ---------------------------------------------- | ------------ |
| 01  | `capture-agent` | Gather the role and propose names              | user request |
| 02  | `write-agent`   | Render the agent per tool and write            | the role     |
| 03  | `validate`      | Check each agent file                          | the files    |

Run the actions in order, `01 → 03`, and run each action's `## Test` before the next.
Before running an action, read its file in `actions/`, not only the table or assets.

## References

- `references/agent-authoring.md`: the contract (frontmatter, body shape, naming, quality).
- `references/tool-paths.md`: per-tool agent path, frontmatter, format conversions, the gate.

## Assets

- `assets/agent-template.md`: agent file scaffold.

© AI-Driven Dev · MIT · ai-driven-dev/framework

Similar skills

All skills for Agent setup: memory, context, orchestration →
nx-generate nrwl nx-generate — a skill that tells the agent how to run Nx generators in a monorepo: pick the right one, dry-run it, then scaffold without breaking repo conventions. CX Codex +1 4,000installs experience-ui-bundle-project-generate forcedotcom experience-ui-bundle-project-generate is a Claude Code skill that scaffolds a Salesforce UI Bundle SFDX starter project from a template in one step. It triggers when starting a fresh React or Angular app, not when modifying an existing one. CX Codex +1 3,200installs conformetry-generate organizzolini The conformetry-generate skill makes the agent scaffold modules, components and services through conformetry instead of writing files by hand. Useful in a workspace that already has a conformetry configuration. CX Codex +1 672installs google-agents-cli-scaffold official Google google-agents-cli-scaffold — a Google skill that drives agents-cli: creates new ADK projects, adds deployment and CI/CD to existing ones. Handy when you need an agent skeleton or want to move a prototype toward production. CX Codex +1 585,900installs convex-quickstart convex convex-quickstart turns a one-sentence idea into a running barebones Next.js + Convex app, with an anonymous dev backend and no publish step. CX Codex +1 139,100installs mcp-apps-builder mcp-use mcp-apps-builder — a skill for Claude Code and other platforms that helps build, debug, and verify TypeScript MCP servers and apps via mcp-use. Triggers when you need to add a tool, resource, prompt, View, or set up OAuth. CX Codex +1 34,100installs

From the same set80

The whole set →
3-cli-process 3-cli-process sets the conventions for a CLI process: how it shuts down, which channel gets which output, and what exit code it returns. CX Codex +1 ★ 571repo stars 02-project-memory 02-project-memory reads codebase architecture and decisions to build project memory and hook it into AI assistants. Useful for initial setups and drift audits. CX Codex +1 ★ 571repo stars 07-epic 07-epic is a Claude Code skill that shapes and reviews product backlog Epics. It checks readiness, resumes saved work, and supports approval before saving. CX Codex +1 ★ 571repo stars 09-defect 09-defect turns an observed product mismatch into a backlog defect: capture, assessment, then a confirmed write. CX Codex +1 ★ 571repo stars 02-challenge 02-challenge is a Claude Code skill that checks completed work against an agreed plan and returns a structured report. Its findings help decide whether to ship, revise, or rework the result. CX Codex +1 ★ 571repo stars 05-spike 05-spike turns one blocking unknown into a bounded spike: frames the question, gathers evidence, writes the outcome. CX Codex +1 ★ 571repo stars 0-contexts 0-contexts enforces one-way imports across bounded contexts and keeps business logic out of the shared kernel in TypeScript projects. CX Codex +1 ★ 571repo stars 1-conventions The 1-conventions rule sets conventions for TypeScript files under src/ and tests/, covering module structure, file names, and test tiers. Use it when adding code or tests to a project. CX Codex +1 ★ 571repo stars

Project sponsors

Companies that keep this analytics open