sub-agent-patterns
Comprehensive guide to sub-agents in Claude Code: built-in agents (Explore, Plan, general-purpose), custom agent creation, configuration, and delegation patterns. Use when: creating custom sub-agents, delegating bulk operations, parallel research, understanding built-in agents, or configuring agent tools/models.
Install with Tessl CLI
npx tessl i github:jezweb/claude-skills --skill sub-agent-patterns87
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly defines its scope around Claude Code sub-agents with specific capabilities and explicit usage triggers. It uses proper third-person voice, lists concrete actions, and includes natural keywords users would employ when working with agent delegation. The 'Use when:' clause provides clear guidance for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'built-in agents (Explore, Plan, general-purpose)', 'custom agent creation', 'configuration', and 'delegation patterns'. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (comprehensive guide to sub-agents covering built-in agents, custom creation, configuration, delegation patterns) AND when (explicit 'Use when:' clause with specific triggers like creating custom sub-agents, delegating bulk operations, parallel research). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'sub-agents', 'custom sub-agents', 'delegating', 'bulk operations', 'parallel research', 'built-in agents', 'agent tools/models'. Good coverage of terms a user working with Claude Code agents would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on 'sub-agents in Claude Code' with distinct triggers like 'Explore', 'Plan', 'delegation patterns', and 'agent tools/models'. Unlikely to conflict with general coding or documentation skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive, highly actionable skill document that excels at providing concrete, executable guidance for sub-agent creation and delegation. The workflow clarity is strong with explicit validation steps and error recovery patterns. The main weakness is length - at ~700 lines, it could benefit from splitting detailed reference material (tool lists, example agents, prompt templates) into separate files while keeping the core concepts in the main skill.
Suggestions
Split the 'Available Tools Reference' table and 'Example Custom Sub-Agents' sections into separate reference files (e.g., TOOLS.md, EXAMPLES.md) to reduce main file length
Consolidate the model selection guidance which appears in multiple places (Model Selection Strategy section, Quick Reference, Best Practices) into a single authoritative location
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | While the content is generally well-organized and avoids explaining basic concepts Claude knows, it's quite lengthy (~700 lines) with some redundancy. The 'Why Use Sub-Agents' section and multiple model selection explanations could be tightened. However, most content earns its place with actionable guidance. | 2 / 3 |
Actionability | Excellent actionability with complete YAML configurations, executable code examples, specific tool lists, and copy-paste ready templates. The prompt templates section provides fully usable patterns, and configuration fields are clearly documented with exact values. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit validation checkpoints. The delegation workflow pattern shows a 5-step process with clear stages. The 'Avoiding Bash Approval Spam' section includes explicit before/after patterns. Error handling section provides clear recovery steps. | 3 / 3 |
Progressive Disclosure | Content is well-structured with clear sections and a quick reference at the end. However, this is a monolithic document that could benefit from splitting detailed sections (prompt templates, example agents, tool reference) into separate files. References to external docs are present but the main file is quite long. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
75%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 12 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (1089 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 12 / 16 Passed | |
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.