create-agent
Create a new Claude Code agent with proper YAML frontmatter structure. Use when the user wants to add a specialized agent to a plugin. Handles agent file creation with name, description, tools, model selection, and color configuration.
Install with Tessl CLI
npx tessl i github:jpoutrin/product-forge --skill create-agent82
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
85%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 well-crafted skill description that clearly defines its purpose and when to use it. It excels at specificity and completeness with explicit 'Use when' guidance. The main weakness is trigger term coverage, which could benefit from additional natural language variations users might employ when requesting agent creation.
Suggestions
Add more natural trigger term variations such as 'new agent', 'agent template', 'agent config', or 'create agent' to improve discoverability
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Create a new Claude Code agent', 'proper YAML frontmatter structure', 'agent file creation with name, description, tools, model selection, and color configuration'. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Create a new Claude Code agent with proper YAML frontmatter structure', 'Handles agent file creation with name, description, tools, model selection, and color configuration') AND when ('Use when the user wants to add a specialized agent to a plugin') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'agent', 'plugin', 'YAML frontmatter', but missing common variations users might say such as 'new agent', 'add agent', 'agent template', or 'agent config'. The term 'Claude Code agent' is specific but users may just say 'agent'. | 2 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on Claude Code agent creation with YAML frontmatter. The combination of 'agent', 'plugin', and specific configuration elements (tools, model selection, color) creates a distinct trigger profile unlikely to conflict with general coding or documentation skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with clear examples and good organization. The main weaknesses are minor verbosity (table duplicating example content) and missing validation steps in the workflow - there's no guidance on verifying the agent file is correctly formatted or testing that it works before considering the task complete.
Suggestions
Add a validation step to the creation process: 'Verify the agent loads correctly by checking for YAML parsing errors'
Consolidate the frontmatter documentation - either use the table OR the annotated example, not both
Add common error cases (e.g., 'If agent doesn't appear, check: valid YAML syntax, file in correct directory, unique name')
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some redundancy - the table format for frontmatter fields duplicates information that's already shown in the example, and the tool combinations section could be more compact. | 2 / 3 |
Actionability | Provides fully executable examples with complete YAML frontmatter structure, concrete tool lists, and a copy-paste ready example agent. All guidance is specific and immediately usable. | 3 / 3 |
Workflow Clarity | The 5-step creation process is listed but lacks validation checkpoints - no verification that the agent file is valid, no testing step, and no feedback loop for common errors like invalid tool names or missing fields. | 2 / 3 |
Progressive Disclosure | For a skill of this scope, the content is well-organized with clear sections (format, fields, guidelines, tools, process, example). No external references needed and no monolithic walls of text. | 3 / 3 |
Total | 10 / 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.