claude-code-skill-development

This skill should be used when the user asks to "create a skill", "write a skill", "build a skill", or wants to add new capabilities to Claude Code. Use when developing SKILL.md files, organizing skill content, or improving existing skills. Do NOT use for plugin development, hook creation, agent creation, or slash command creation — those have dedicated skills.

Quality

85%

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

Quality

Content

78%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 well-structured, mostly lean instructional skill that delegates detail to six real reference files and ends with a useful checklist. Main improvement is trimming restatements of concepts Claude already knows and embedding explicit validation checkpoints inside the build workflow.

Suggestions

Trim optional-field explanations that restate known concepts (e.g., the inline gloss of context: fork and metadata) to keep only what is non-obvious about skill authoring.

Add an explicit mid-workflow validation checkpoint (e.g., 'After writing the description, verify it passes the triggering test') rather than relying solely on the terminal checklist.

Align the 'Writing Effective Descriptions' good example with the skill's own domain (it currently uses a hook example, slightly muddying the guidance).

Dimension	Reasoning	Score
Conciseness	Efficient and well-organized directive prose, but a few optional-field descriptions (e.g., restating what context: fork or metadata do) restate concepts Claude already knows and could be trimmed.	4 / 5
Actionability	Provides concrete templates (use-case block, directory tree, YAML frontmatter, troubleshooting table, checklist) with specific rules; examples are instructional templates rather than copy-paste code, which is appropriate for this instruction-only skill but leaves minor gaps.	4 / 5
Workflow Clarity	Clear end-to-end sequence (define use cases -> pick category -> structure -> frontmatter -> test -> troubleshoot -> checklist) with a terminal checklist gate, though embedded validation checkpoints within the build flow are implicit rather than explicit.	4 / 5
Progressive Disclosure	SKILL.md is a concise (~152 line) overview with six well-signaled, one-level-deep references, all verified to exist as real bundled files, each accompanied by a one-line description for easy navigation.	5 / 5
	Total	17 / 20 Passed

Description

92%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, well-structured description that clearly states capabilities, provides concrete natural trigger phrases, and distinguishes itself from adjacent skills via explicit negative triggers. Minor room only in trigger synonym breadth.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('create a skill', 'write a skill', 'build a skill', 'developing SKILL.md files, organizing skill content, improving existing skills') with comprehensive coverage of the skill-authoring domain.	5 / 5
Completeness	Explicitly answers both WHAT (develop/organize/improve SKILL.md files, add capabilities) and WHEN ('Use when...', 'Do NOT use for...') with concrete trigger phrases and negative boundary guidance.	5 / 5
Trigger Term Quality	Includes natural phrases users say (create/write/build a skill, add new capabilities) with synonyms, but is missing a few common variations or file-extension cues that would push it to comprehensive.	4 / 5
Distinctiveness Conflict Risk	Clear niche (SKILL.md authoring) with explicit 'Do NOT use for plugin development, hook creation, agent creation, or slash command creation' boundary, sharply minimizing overlap with related skills.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
relative_links	Relative link issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: dwmkerr/claude-toolkit
Path: plugins/toolkit/skills/skill-development/SKILL.md
Commit: 4316684

Reviewed: 8 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.