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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured and largely actionable, but is verbose with redundant best-practice lists, relies on placeholder examples, and references bundle files that are missing. Tightening prose and fixing broken references would materially improve it.

Suggestions

Trim conceptual exposition and the duplicated DO/DON'T and summary-table sections; assume Claude knows what agents and frontmatter are and keep only the skill-specific guidance.

Replace placeholder system-prompt templates ("You are [role]...") with at least one fully worked, copy-paste-ready agent example, or move complete examples into the missing examples/ files and link them.

Fix broken references: create the referenced examples/ directory and test-agent-trigger.sh, or remove those pointers; add an explicit validate→fix→revalidate feedback loop to the workflow.

Dimension	Reasoning	Score
Conciseness	The body restates concepts Claude already knows ("Agents are autonomous subprocesses...") and repeats guidance across multiple DO/DON'T lists and a summary table, so it is mostly efficient but padded and could be tightened rather than the lean anchor.	2 / 3
Actionability	It provides concrete frontmatter formats, validation rules, and a real validate script, but core system-prompt examples are template placeholders ("You are [role]...") and the referenced test script and examples directory are missing, leaving guidance incomplete.	2 / 3
Workflow Clarity	The 'Implementation Workflow' lists a sequenced 9-step process with a validation step, but validation is a single 'run the script' step with no explicit validate→fix→retry feedback loop, and the referenced test trigger script does not exist.	2 / 3
Progressive Disclosure	It signals one-level-deep references to real files in references/ and scripts/validate-agent.sh, but also points to a non-existent examples/ directory and test-agent-trigger.sh, and keeps large amounts of content inline that could live in references.	2 / 3
	Total	8 / 12 Passed

Description

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.

The description is specific, trigger-rich, and clearly answers both what the skill does and when to use it, with low conflict risk. It is a strong, well-targeted description.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple concrete capabilities and topics — "create an agent", "write a subagent", "agent frontmatter", "agent colors", "autonomous agent" — rather than vague language, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It answers both 'what' (agent development guidance for Claude Code plugins) and 'when' with an explicit trigger clause ("This skill should be used when the user asks to..."), satisfying the both-what-and-when anchor.	3 / 3
Trigger Term Quality	Phrases like "create an agent", "add an agent", "write a subagent", and "agent colors" are exactly what a user would naturally say, giving good coverage of natural trigger terms.	3 / 3
Distinctiveness Conflict Risk	The niche — agent development for Claude Code plugins — is distinct with specific triggers unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: anthropics/claude-plugins-official
Commit: 30a213f

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.