agent-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.
Install with Tessl CLI
npx tessl i github:dwmkerr/claude-toolkit --skill agent-development56
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
37%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 description is fundamentally incomplete - it only specifies trigger conditions without describing any actual capabilities or actions the skill performs. While the trigger terms are natural and user-friendly, the complete absence of 'what this skill does' makes it impossible for Claude to understand the skill's purpose beyond matching keywords.
Suggestions
Add concrete capability descriptions using third person voice (e.g., 'Generates agent scaffolding code, defines tool schemas, implements agent loops and state management').
Restructure to lead with capabilities before the 'Use when...' clause (e.g., 'Creates autonomous agent implementations with tool definitions and execution loops. Use when...').
Specify the outputs or artifacts produced (e.g., 'Produces agent configuration files, tool definitions, and orchestration code for Claude Code extensions').
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions - it only states when to use the skill but never describes what the skill actually does. 'Create an agent', 'write an agent', 'build an agent' are user requests, not capability descriptions. | 1 / 3 |
Completeness | The description only addresses 'when' (trigger conditions) but completely omits 'what' - there is no explanation of what capabilities this skill provides or what actions it performs. | 1 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'create an agent', 'write an agent', 'build an agent', 'agent capabilities', 'Claude Code'. These are realistic phrases users would use when requesting this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | The term 'agent' provides some specificity, but 'agent capabilities' is vague and could overlap with other agent-related skills. The Claude Code mention helps narrow scope but the overall domain remains somewhat ambiguous. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
52%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is concise and well-formatted but fundamentally incomplete for its stated purpose of helping users 'create an agent.' It covers color conventions and one behavioral note but omits the core workflow: file location, required structure, complete examples, and validation. A user following this skill would know how to color an agent but not how to create one.
Suggestions
Add a complete 'Quick Start' section showing how to create a minimal working agent, including file path, full YAML frontmatter, and basic content structure
Include a step-by-step workflow: 1) Create file in correct location, 2) Add required frontmatter, 3) Write agent instructions, 4) Verify agent appears in list
Provide at least one complete, copy-paste ready agent example that demonstrates all required elements
Add reference links to example agents or templates if they exist elsewhere in the codebase
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, presenting only essential information without explaining concepts Claude already knows. Every section adds specific, non-obvious value about agent development. | 3 / 3 |
Actionability | Provides concrete YAML example for color assignment, but lacks executable code for actually creating an agent. The skill describes agent properties but doesn't show how to create a complete agent file or structure. | 2 / 3 |
Workflow Clarity | No clear workflow for creating an agent from start to finish. Missing steps like: where to create the file, required file structure, validation steps, or how to test the agent works correctly. | 1 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but for a skill about creating agents, it lacks references to examples or templates. The content feels incomplete rather than appropriately split across files. | 2 / 3 |
Total | 8 / 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.