agent-factory
Claude Code agent generation system that creates custom agents and sub-agents with enhanced YAML frontmatter, tool access patterns, and MCP integration support following proven production patterns
Install with Tessl CLI
npx tessl i github:alirezarezvani/claude-code-skill-factory --skill agent-factory57
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
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description identifies a specific domain (agent generation) but relies heavily on technical jargon without explaining concrete user benefits. The critical missing element is any 'Use when...' guidance, making it difficult for Claude to know when to select this skill. The description would benefit from clearer action verbs and natural trigger terms.
Suggestions
Add an explicit 'Use when...' clause with natural trigger phrases like 'when the user wants to create a new agent', 'build a sub-agent', 'set up agent workflows', or 'configure agent tools'.
Replace or supplement technical jargon with user-facing language: instead of 'YAML frontmatter' say 'agent configuration'; instead of 'MCP integration' explain 'connecting agents to external tools and services'.
List 2-3 concrete actions users would request, such as 'scaffold new agents, configure tool permissions, set up agent hierarchies'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (agent generation) and some actions (creates custom agents and sub-agents), but the specific capabilities are buried in technical jargon like 'enhanced YAML frontmatter', 'tool access patterns', and 'MCP integration support' without explaining what concrete actions these enable. | 2 / 3 |
Completeness | Describes what it does (creates agents with various features) but completely lacks a 'Use when...' clause or any explicit trigger guidance. There is no indication of when Claude should select this skill over others. | 1 / 3 |
Trigger Term Quality | Contains some relevant keywords like 'agent', 'sub-agents', 'Claude Code', but uses technical jargon ('YAML frontmatter', 'MCP integration') that users are unlikely to naturally say. Missing common variations like 'create agent', 'build agent', 'agent template'. | 2 / 3 |
Distinctiveness Conflict Risk | The focus on 'Claude Code agent generation' is somewhat specific, but 'agent' is a broad term that could overlap with other automation or workflow skills. The technical terms help narrow scope but aren't distinctive enough for clear selection. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides comprehensive documentation for an agent factory system with good workflow clarity and safety guidelines. However, it's verbose with explanatory content Claude doesn't need (field categories, color meanings), and the core actionability depends on an external template rather than providing inline generation capability. The content would benefit from trimming categorical explanations and either inlining the generation logic or being more concise as a pointer to the template.
Suggestions
Remove or drastically condense the Field Categories, Color Coding, and Expertise Levels sections - these are self-explanatory from examples
Either inline the core generation logic from AGENTS_FACTORY_PROMPT.md or reduce this skill to a concise pointer with one complete example
Move MCP Tool Integration and Safety & Performance sections to separate reference files, keeping only essential safety rules inline
Replace the 'What This Skill Does' and 'Capabilities' sections with a single concrete example showing input → output
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains useful information but is verbose in places. Sections like 'What This Skill Does' and 'Capabilities' list could be condensed. The extensive categorization tables (Field Categories, Color Coding, Expertise Levels) add bulk that Claude could infer from examples. | 2 / 3 |
Actionability | Provides concrete YAML examples and file structures, but the actual agent generation relies on an external template file (AGENTS_FACTORY_PROMPT.md) rather than providing executable generation logic inline. The 'Example Invocation' shows input but the actual generation mechanism is delegated elsewhere. | 2 / 3 |
Workflow Clarity | Clear numbered steps in Quick Start section, explicit workflow examples for Feature Development/Bug Fix/Code Review, and safety guidelines with specific thresholds. The execution rules clearly distinguish safe vs unsafe patterns with validation checkpoints. | 3 / 3 |
Progressive Disclosure | References external template file appropriately, but the main document itself is quite long with content that could be split (e.g., MCP tool details, safety monitoring could be separate files). The structure is good but the skill is monolithic for its complexity. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- 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.