Name: skill-developer
Rating: 72 (1 reviews)
Author: diet103

skill-developer

Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns, file paths, content patterns), enforcement levels (block, suggest, warn), hook mechanisms (UserPromptSubmit, PreToolUse), session tracking, and the 500-line rule.

Quality

88%

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

The canonical home for this skill is skill-developer in diet103/claude-code-infrastructure-showcase

Quality

Content

77%Weight 40%Scale 1-3

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

The body is actionable with strong templates, test commands, and a well-sequenced creation workflow, but it loses conciseness to a duplicative summary section and its progressive-disclosure references are dead links pointing to files that are not bundled.

Suggestions

Remove or merge the "Quick Reference Summary" section, which duplicates the Quick Start steps, trigger types, enforcement levels, skip conditions, and best-practices already detailed earlier in the document.

Ship the six referenced reference files (TRIGGER_TYPES.md, SKILL_RULES_REFERENCE.md, HOOK_MECHANISMS.md, TROUBLESHOOTING.md, PATTERNS_LIBRARY.md, ADVANCED.md) in a references/ directory so the progressive-disclosure links resolve, or inline the essential parts and drop the dangling links.

Trim status-fluff lines like "Skill Status: COMPLETE" and "Next: Create more skills" that consume tokens without adding actionable guidance.

Dimension	Reasoning	Score
Conciseness	The guidance is specific to this custom system rather than re-explaining known concepts, but a large "Quick Reference Summary" section restates trigger types, enforcement levels, skip conditions, and best practices already covered above, adding redundancy. It is mostly efficient but could be tightened by removing the duplicate summary block.	2 / 3
Actionability	Provides copy-paste-ready SKILL.md and skill-rules.json templates, executable test commands (e.g. `echo '{...}' \| npx tsx .claude/hooks/skill-activation-prompt.ts`), and concrete env-var/markers, giving Claude exact actions rather than vague direction.	3 / 3
Workflow Clarity	The "Quick Start: Creating a New Skill" is a clear 5-step sequence with explicit validation checkpoints (test UserPromptSubmit, test PreToolUse, `jq . skill-rules.json`) and a refine-from-testing feedback loop, supported by a thorough testing checklist.	3 / 3
Progressive Disclosure	References are clearly signaled and one level deep (TRIGGER_TYPES.md, SKILL_RULES_REFERENCE.md, etc.), but no bundle files exist and none of the six referenced .md files are present, so the navigation points to missing material. Structure is good but references do not resolve to actual files.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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, third-person description that states concrete capabilities, provides an explicit Use-when trigger clause, and uses distinctive domain terms. It is comprehensive without resorting to vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("Create and manage Claude Code skills", "modifying skill-rules.json", "debugging skill activation", "implementing progressive disclosure") plus a detailed catalog of covered topics, going well beyond a single domain mention.	3 / 3
Completeness	Explicitly answers both what ("Create and manage Claude Code skills following Anthropic best practices") and when ("Use when creating new skills, modifying skill-rules.json...") with an explicit trigger clause.	3 / 3
Trigger Term Quality	Covers natural terms a user would actually say — "creating new skills", "skill-rules.json", "hooks", "trigger patterns", "YAML frontmatter", "500-line rule" — with good variation rather than only technical jargon.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (Claude Code skill authoring) anchored by distinctive tokens like skill-rules.json and UserPromptSubmit/PreToolUse hooks, making conflicts with other skills unlikely.	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
relative_links	Relative link issues: 9 missing	Warning

	Total	15 / 16 Passed

Repository: diet103/claude-code-infrastructure-showcase
Path: .agents/skills/skill-developer/SKILL.md
Commit: 07f75ce

Reviewed: ~14 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.