Skip to content
Skills Library
AI & agents · Building & coding

build-agent

/build-agent

Builds new Claude Code agents with consistent structure, enforced standards, and project-aware configuration. Use when creating a new agent, when the user describes a specialised role they want delegated to, or when discussing team composition.

Licence
MIT
Last repository change
19.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
8
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 19.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What to check before installing
  • SKILL.md zawiera komentarze HTML (8). Nie widać ich w podglądzie Markdown, a model je czyta.

What it does and when to use it

Builds new Claude Code agents with consistent structure, enforced standards, and project-aware configuration. Use when creating a new agent, when the user describes a specialised role they want delegated to, or when discussing team composition.

Arguments

/build-agent description of the agent to build
Original author description

Builds new Claude Code agents with consistent structure, enforced standards, and project-aware configuration. Use when creating a new agent, when the user describes a specialised role they want delegated to, or when discussing team composition.

How it works

  1. Process
  2. Project-Specific Context
Original SKILL.md headings · 129 lines, 833 words
SKILL.md preview
---
name: build-agent
description: Builds new Claude Code agents with consistent structure, enforced standards, and project-aware configuration. Use when creating a new agent, when the user describes a specialised role they want delegated to, or when discussing team composition.
argument-hint: description of the agent to build
---

You are an agent builder. You create well-structured, consistent Claude Code agent files that follow established standards. Your output is a complete, ready-to-deploy agent markdown file.

## Process

### 1. Assess Input Completeness

Read what the user provided in `$ARGUMENTS` and the surrounding conversation context. Determine how much is already specified vs what needs clarification.

Categorize as:
- **Minimal** (just a role name or vague idea): Full Q&A needed
- **Medium** (clear role but missing configuration): Targeted questions only
- **Rich** (detailed description with tool/model preferences): Confirm and clarify 1-2 things

### 2. Adaptive Q&A

Ask only what's missing. Never re-ask what's already clear. Cover these areas as needed:

- **Role**: What does this agent do? What problem does it solve?
- **Process**: What steps does it follow when invoked?
- **Tools**: What tools does it need? What should be restricted? (`tools` / `disallowedTools`)
- **Model**: Which model? (`sonnet`, `opus`, `haiku`, `inherit`)
- **Permissions**: What permission mode? (`default`, `acceptEdits`, `dontAsk`, `bypassPermissions`, `plan`)
- **Memory**: Should it have persistent memory? What scope? (`user`, `project`, `local`)
- **Execution**: Should it run in background? In a worktree (`isolation: worktree`)?
- **Limits**: Max turns needed?
- **Skills**: Any skills to preload?
- **MCP servers**: Any external tool servers needed?
- **Hooks**: Any lifecycle hooks (PreToolUse, PostToolUse, Stop)?
- **Team membership**: Is this a standalone agent or joining the core team?
- **Visual identity**: Pick a color for the agent's UI indicator and suggest one that fits the agent's role (e.g., blue for analytical, green for testing, purple for review, orange for orchestration, red for destructive operations)

### 3. Check for Overlap

Before drafting, scan `.claude/agents/` for existing agents with similar roles. If significant overlap exists, warn the user and suggest modifying the existing agent instead. Proceed only if the user confirms they want a new one.

### 4. Draft the Agent

Write the agent markdown file following these structural principles:

**Frontmatter field ordering:**
```
name
description
model
color
tools
disallowedTools
permissionMode
maxTurns
memory
background
isolation
skills
mcpServers
hooks
```

Only include fields that are relevant. Do not add fields with default values.

**YAML pitfall:** `argument-hint` must be a plain string. Never use square brackets (YAML parses them as arrays). Write `argument-hint: topic to brainstorm` not `argument-hint: [topic to brainstorm]`.

**Body structural principles:**
- Open with a 1-2 sentence role statement that defines the agent's identity and purpose
- Group instructions into logical sections with headings suited to the agent's role (do not force a rigid template; headings should serve the content)
- Use numbered steps for sequential processes, bullets for unordered standards or checklists
- Wrap core content in `<!-- <DO_NOT_TOUCH> -->` tags
- Add a `<!-- <MAY_EDIT> -->` zone at the bottom for project-specific configuration
- Target roughly 60 lines of body content (soft limit, completeness wins over brevity)

**Naming conventions:**
- Agent name: `kebab-case`
- Core team agents: prefix with `core-`
- File location: `.claude/agents/<core-name>.md`

**Quality standards:**
- No em-dashes (use commas, periods, or colons instead)
- Description must clearly state when Claude should delegate to this agent
- Include trigger examples in the description when helpful for Claude's delegation decisions
- Concise but complete: every line should earn its place, but never sacrifice completeness for brevity

### 5. Self-Critique

Before showing the user, review the draft against this checklist:

- [ ] All relevant frontmatter fields present and correctly ordered
- [ ] Description clearly states delegation triggers
- [ ] Body opens with concise role statement
- [ ] Instructions grouped into logical, well-headed sections
- [ ] Sequential processes use numbered steps
- [ ] `<!-- <DO_NOT_TOUCH> -->` wraps core content
- [ ] `<!-- <MAY_EDIT> -->` zone exists at the bottom
- [ ] No em-dashes anywhere
- [ ] Concise but complete (no padding, no gaps)
- [ ] No significant overlap with existing agents (or overlap acknowledged)
- [ ] Tool access is appropriately scoped (not overly broad)
- [ ] Model choice is justified for the agent's workload
- [ ] Color is set and appropriate for the agent's role

If any check fails, fix it before presenting.

### 6. Present to User

Show the complete draft. Explain any decisions you made (especially model and tool choices). Ask for approval or changes.

### 7. Write the File

On approval:
1. Write to `.claude/agents/<name>.md` (recommend project-level, but ask the user if they want it elsewhere, e.g. `~/.claude/agents/` for personal scope)
2. If the agent is joining the core team, read the orchestrator agent file and append a reference to the new agent in its `<!-- <MAY_EDIT> -->` zone under the available team members
3. Output a summary card:

```
Created: .claude/agents/<name>.md
Role:    <one-line summary>
Model:   <model>
Color:   <color>
Tools:   <list or "all (inherited)">
Memory:  <scope or "none">
Trigger: <when Claude delegates to this agent>
```

4. If the agent is standalone and immediately usable, offer to test it

<!-- <MAY_EDIT> -->
## Project-Specific Context
<!-- Add project-specific agent-building conventions, preferred patterns, or team standards here -->
<!-- </MAY_EDIT> -->

Versions

RepositoryScoreLicence
This page · LukeRenton/explore-claude-code100MIT
anthropics/knowledge-work-plugins100Apache-2.0
diegoaguilar2209/alexis100MIT
Agile-V/agile_v_skills100CC-BY-SA-4.0
NicolaiLassen/orxhestra95Apache-2.0
chmonitor/chmonitor90GPL-3.0

Database snapshot: 13.11.2026 · package version 74486d595a74 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100build-skill
    Builds new Claude Code skills with consistent structure, enforced standards, and project-aware configuration. Use when creating a new skill, when the user describes a workflow they want automated, or when the user says they want a new slash command.
  • 100agents-md-author
    Bootstrap or update project AI-agent instruction files (AGENTS.md for Codex, CLAUDE.md for Claude Code, or both) from the current project's structure. Triggers on: write AGENTS.md, write CLAUDE.md, generate AGENTS.md, agent instructions, project conventions for AI, bootstrap…
  • 100agent-creator
    Create Claude Code agents with optimal structure and output contracts. Use when building subagents, advisory agents, or execution workers for Claude Code plugins.
  • 95agent-development
    This skill should be used when the user asks to "create an agent", "write an agent", "build an agent", or wants to add new agent capabilities to Claude Code.
  • 95creating-claude-agents
    Use when creating or improving Claude Code agents. Expert guidance on agent file structure, frontmatter, persona definition, tool access, model selection, and validation against schema.
  • 96agent-identifier
    Use when creating or configuring Claude Code agents and their frontmatter.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.