agent-development
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
Install with Tessl CLI
npx tessl i github:anthropics/claude-plugins-official --skill agent-developmentOverall
score
83%
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
72%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 excels at trigger term coverage and distinctiveness, making it easy for Claude to identify when to use this skill. However, it's structured backwards - it leads with 'when' triggers but lacks clear explanation of what concrete actions or outputs the skill provides. The description would benefit from stating specific capabilities before listing trigger conditions.
Suggestions
Add specific capability statements at the beginning (e.g., 'Generates agent configuration files, writes system prompts, and creates frontmatter for Claude Code plugin agents').
Restructure to follow the 'what then when' pattern: lead with concrete actions, then follow with 'Use when...' clause.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (agent development for Claude Code plugins) and mentions some actions like guidance on 'agent structure, system prompts, triggering conditions', but doesn't list concrete specific actions the skill performs (e.g., 'generates agent frontmatter', 'creates system prompts'). | 2 / 3 |
Completeness | The description focuses heavily on 'when' (trigger conditions) but is weak on 'what' - it says the skill provides 'guidance' but doesn't clearly explain what concrete outputs or actions the skill produces. The 'what' is only implied through the trigger terms. | 2 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'create an agent', 'add an agent', 'write a subagent', 'agent frontmatter', 'agent tools', 'autonomous agent'. These are realistic phrases users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting Claude Code plugin agent development. The explicit mention of 'Claude Code plugins', 'subagent', and 'agent frontmatter' creates clear boundaries that are unlikely to conflict with general coding or documentation skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, comprehensive skill for agent development with excellent actionability and clear workflows. The content provides concrete, executable examples and well-structured guidance. Minor improvements could be made by reducing redundancy in the DO/DON'T sections and tightening some explanatory text.
Suggestions
Consolidate the two DO/DON'T lists (in System Prompt Design and Best Practices sections) into a single reference to reduce redundancy
Consider moving the detailed Frontmatter Fields section to a reference file, keeping only essential information in the main skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some redundancy (e.g., best practices repeated in multiple sections, DO/DON'T lists appearing twice). Some sections like the model options explanation could be tightened, though overall it avoids explaining concepts Claude already knows. | 2 / 3 |
Actionability | Provides fully executable examples with complete YAML frontmatter and markdown body templates. The agent file structure, validation rules, and creation methods are concrete and copy-paste ready with specific patterns and formats. | 3 / 3 |
Workflow Clarity | The Implementation Workflow section provides a clear 9-step sequence. Testing sections include explicit validation steps (validate-agent.sh, test-agent-trigger.sh). Both AI-assisted and manual creation methods have clear step-by-step processes. | 3 / 3 |
Progressive Disclosure | Well-organized with clear overview leading to detailed sections. References to external files (references/, examples/, scripts/) are one level deep and clearly signaled. The Quick Reference section provides a scannable summary while detailed content is appropriately sectioned. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
91%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 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.