Use when creating custom agents for Claude Code, configuring specialized AI assistants, or when the user asks about agent creation, configuration, or delegating tasks to workers. Covers both file-based agents and teams delegation.
SkillScore95Maintained
Automatic
◆AI Engineer pack
Last verified 8/19/2026
What it changes
Passed 19 of 20 test cases with the skill, and 7 of 20 without it.
Without skill36%
With skill95%
Checks it passed that the model alone missed
sets model to opus in frontmatter
specifies permissionMode as bypassPermissions
specifies the storage path as ~/.claude/agents/
and 15 more in the full report
13 fixed8 passed either way1 still failing0 broke
Pass-rate lift
+59 pp
Tokens
+124%
Agent turns
0%
Response time
-55%
Model gemini-3.6-flashMeasured 8/19/2026v121 of 22 cases passed with skill · 20 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 11
Prompt
We need a frontmatter header for a standard feature-building worker that can read files, write files, edit files, inspect directories, search patterns, and run command-line commands. Show the frontmatter tools key line.
What was checked, without and with the skill
Checked
Without skill
With skill
lists tools as Read, Write, Edit, Bash, Glob, Grep
Missed
Passed
case-10 · gemini-3.6-flash · 8/19/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md480 linessingle file
Create Worker
This skill provides comprehensive guidance for creating and configuring workers in Claude Code.
Understanding Workers
Workers are specialized AI assistants that Claude Code can delegate tasks to. Each worker:
Operates in its own context window (preserving main conversation context)
Has a specific purpose and expertise area
Can be configured with specific tools and permissions
Includes a custom system prompt guiding its behavior
When to Create Workers
Create a worker when:
Tasks require specialized expertise that benefits from focused instructions
Context preservation is important (workers don't pollute main context)
The same specialized workflow is needed repeatedly
Different tool permissions are needed for different tasks
Parallel execution of independent tasks is desired
Choose skills instead when:
The capability extends your knowledge without needing separate context
No specialized agent persona is needed
Tool restrictions are sufficient without full agent isolation
Choose slash commands when:
Users need explicit control over when to invoke functionality
The workflow should be user-initiated, not model-initiated
Two Approaches to Workers
Approach 1: File-Based Agents
Persistent worker definitions stored as Markdown files.