Team Builder
Browse markdown agent personas and compose an ad-hoc parallel team (e.g., Security + SEO + Architecture) before dispatching work.
Overview
Team Builder is an agent skill most often used in Build (also Ship, Grow) that provides an interactive menu to browse markdown agent personas and compose parallel multi-domain teams before dispatch.
Install
npx skills add https://github.com/affaan-m/everything-claude-code --skill team-builderWhat is this skill?
- Interactive menu to browse available agent markdown personas before you commit to a lineup
- Compose ad-hoc cross-domain teams (e.g., Security + SEO + Architecture) from one picker
- Supports flat `agents/*.md` and domain subfolders with domain inferred from directory or shared filename prefixes
- Uses first `# heading` as agent name and first paragraph as description for discovery
- Prefix-based domain detection requires 2+ files sharing a prefix; multi-word domains should use subdirectory layout
- Flat layout treats a filename prefix as a domain only when 2+ files share that prefix
- Agent name and description are taken from the first `# heading` and first paragraph in each markdown file
Adoption & trust: 4k installs on skills.sh; 210k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have dozens of agent persona files but no fast way to see what exists or assemble the right specialists for a cross-cutting task.
Who is it for?
Builders curating markdown agent libraries in Claude Code-style setups who run multi-specialist workflows regularly.
Skip if: Single-agent sessions with no persona library, or teams that need runtime agent generation instead of picking from existing files.
When should I use this skill?
You have multiple agent persona markdown files and want to pick, browse, or compose an ad-hoc parallel team across domains.
What do I get? / Deliverables
You select a purposeful multi-agent lineup from your catalog—flat or subdirectory layout—with domains inferred automatically, ready for parallel dispatch on the current task.
- Selected agent team composition for the current task
- Browsable inventory of available agents grouped by inferred domain
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Agent-tooling is the canonical shelf: the skill is meta-orchestration over a library of agent markdown files, not delivering a single product feature itself. Picking and composing agent personas is tooling for how your coding agent runs work, matching build/agent-tooling rather than a single frontend or backend deliverable.
Where it fits
Open the menu to combine engineering and marketing personas before implementing a feature plus its positioning copy.
Browse domains to see which planning or architecture agents exist before splitting a roadmap into parallel workstreams.
Dispatch Security and Architecture agents together for a pre-merge review pass.
Staff SEO and content-strategy personas for a coordinated launch article and metadata pass.
How it compares
Use instead of manually @-mentioning random agent files without a structured browse-and-compose step.
Common Questions / FAQ
Who is team-builder for?
Team Builder is for indie developers and small teams who maintain multiple agent persona markdown files and want an interactive way to pick and combine them.
When should I use team-builder?
Use it in Build when staffing agent-tooling for a feature; in Ship when you want Security plus Review personas before merge; and in Grow when combining content and SEO agents for a launch slice—whenever you need to browse or compose a team first.
Is team-builder safe to install?
It orchestrates which local persona prompts run next; review the Security Audits panel on this Prism page and audit agent markdown for risky instructions before dispatch.
SKILL.md
READMESKILL.md - Team Builder
# Team Builder Interactive menu for browsing and composing agent teams on demand. Works with flat or domain-subdirectory agent collections. ## When to Use - You have multiple agent personas (markdown files) and want to pick which ones to use for a task - You want to compose an ad-hoc team from different domains (e.g., Security + SEO + Architecture) - You want to browse what agents are available before deciding ## Prerequisites Agent files must be markdown files containing a persona prompt (identity, rules, workflow, deliverables). The first `# Heading` is used as the agent name and the first paragraph as the description. Both flat and subdirectory layouts are supported: **Subdirectory layout** — domain is inferred from the folder name: ``` agents/ ├── engineering/ │ ├── security-engineer.md │ └── software-architect.md ├── marketing/ │ └── seo-specialist.md └── sales/ └── discovery-coach.md ``` **Flat layout** — domain inferred from shared filename prefixes. A prefix counts as a domain when 2+ files share it. Files with unique prefixes go to "General". Note: the algorithm splits at the first `-`, so multi-word domains (e.g., `product-management`) should use the subdirectory layout instead: ``` agents/ ├── engineering-security-engineer.md ├── engineering-software-architect.md ├── marketing-seo-specialist.md ├── marketing-content-strategist.md ├── sales-discovery-coach.md └── sales-outbound-strategist.md ``` ## Configuration Agents are discovered via two methods, merged and deduplicated by agent name: 1. **`claude agents` command** (primary) — run `claude agents` to get all agents known to the CLI, including user agents, plugin agents (e.g. `everything-claude-code:architect`), and built-in agents. This automatically covers ECC marketplace installs without any path configuration. 2. **File glob** (fallback, for reading agent content) — agent markdown files are read from: - `./agents/**/*.md` + `./agents/*.md` — project-local agents - `~/.claude/agents/**/*.md` + `~/.claude/agents/*.md` — global user agents Earlier sources take precedence when names collide: user agents > plugin agents > built-in agents. A custom path can be used instead if the user specifies one. ## How It Works ### Step 1: Discover Available Agents Run `claude agents` to get the full agent list. Parse each line: - **Plugin agents** are prefixed with `plugin-name:` (e.g., `everything-claude-code:security-reviewer`). Use the part after `:` as the agent name and the plugin name as the domain. - **User agents** have no prefix. Read the corresponding markdown file from `~/.claude/agents/` or `./agents/` to extract the name and description. - **Built-in agents** (e.g., `Explore`, `Plan`) are skipped unless the user explicitly asks to include them. For user agents loaded from markdown files: - **Subdirectory layout:** extract the domain from the parent folder name - **Flat layout:** collect all filename prefixes (text before the first `-`). A prefix qualifies as a domain only if it appears in 2 or more filenames (e.g., `engineering-security-engineer.md` and `engineering-software-architect.md` both start with `engineering` → Engineering domain). Files with unique prefixes (e.g., `code-reviewer.md`, `tdd-guide.md`) are grouped under "General" - Extract the agent name from the first `# Heading`. If no heading is found, derive the name from the filename (strip `.md`, replace hyphens with spaces, title-case) - Extract a one-line summary from the first paragraph after the heading If no agents are found after running `claude agents` and probing file locations, inform the user: "No agents found. Run `claude agents` to verify your setup." Then stop. ### Step 2: Present Domain Menu ``` Available agent domains: 1. Engineering — Software Architect, Security Engineer 2. Marketing — SEO Specialist 3. Sales — Discovery Co