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

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/plugin-dev/skills/agent-development/SKILL.md

Quality

Content

63%Weight 40%Scale 1-5

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

A thorough, actionable authoring guide with real bundle support and an explicit validation step, weakened by redundant restatements of the same guidance and several dangling references to files that do not exist in the bundle.

Suggestions

Collapse the repeated frontmatter/best-practices guidance into one canonical section; replace the summary table and duplicate DO/DON'T lists with a single pointer.

Remove or create the missing bundle paths — examples/agent-creation-prompt.md, examples/complete-agent-examples.md, and scripts/test-agent-trigger.sh are referenced but absent.

Move the large inline system-prompt and format templates into the existing references/*.md files and link to them, so SKILL.md stays a lean overview.

Dimension	Reasoning	Score
Conciseness	Mostly useful but noticeably padded: the frontmatter field guidance is repeated across the detailed section, a summary table, two DO/DON'T lists, and the Implementation Workflow, and the Overview bullet list restates points elaborated below. Not a 2 because the templates genuinely earn their place.	3 / 5
Actionability	Provides copy-paste-ready agent file templates, concrete good/bad name examples, an explicit JSON return schema for AI-assisted generation, and a real validation script; the "then convert to agent file format" hand-wave and placeholder-only blocks keep it just below a 5.	4 / 5
Workflow Clarity	The 9-step Implementation Workflow is clearly sequenced with a validation checkpoint (step 7, `validate-agent.sh`) and a testing checkpoint (step 8); not a 5 because step 8's "Test triggering with real scenarios" lacks an explicit validate-fix-retry feedback loop.	4 / 5
Progressive Disclosure	Structure exists with a Reference Files section pointing to the three real references/*.md files and scripts/validate-agent.sh, but the body also references non-existent paths (examples/agent-creation-prompt.md, examples/complete-agent-examples.md, scripts/test-agent-trigger.sh) and inlines ~395 lines of template content that overlaps the reference files — a mix of clear signaling and broken/deep-duplication gaps.	3 / 5
	Total	14 / 20 Passed

Description

86%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, trigger-rich description that uses third person and answers both what and when with natural user phrasings. Its only weakness is that the capability statement leans on "needs guidance on" rather than naming crisp deliverables.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("create an agent", "add an agent", "write a subagent") plus specific subtopics (frontmatter, tools, colors, system prompts), giving broad coverage of the agent-development domain with only minor gaps.	4 / 5
Completeness	Explicitly answers "when" ("This skill should be used when the user asks to...") with concrete triggers, and answers "what" via "needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices"; the "what" is framed as guidance rather than a crisp capability statement, so it stops just short of a 5.	4 / 5
Trigger Term Quality	Comprehensive natural phrasing users would actually say — "create an agent", "add an agent", "write a subagent", "agent frontmatter", "agent tools", "agent colors", "autonomous agent" — including synonyms (agent/subagent) and varied intent phrasings.	5 / 5
Distinctiveness Conflict Risk	Clear niche — Claude Code plugin agent authoring — with agent-specific trigger terms that are unlikely to fire for unrelated skills; minimal conflict risk.	5 / 5
	Total	18 / 20 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
Path: plugins/plugin-dev/skills/agent-development/SKILL.md
Commit: 8864c9d

Reviewed: about 18 hours 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.