create-command

Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration

Quality

55%

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/customaize-agent/skills/create-command/SKILL.md

Quality

Content

56%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.

The body is well-structured and actionable with strong concrete examples and a clear phased workflow, but it is verbose from repeated frontmatter guidance and inlined general slash-command reference material, and it makes no use of progressive disclosure via separate files. Trimming repetition and splitting reference material out would meaningfully improve it.

Suggestions

Consolidate the frontmatter guidance that currently appears in <command_frontmatter>, <generation_patterns>, and <creation_checklist> into one authoritative section to remove repetition.

Move the general slash-command feature reference (<command_features>: namespacing, $ARGUMENTS, ! prefix, @ refs, frontmatter options table) into a separate reference file and link to it, since Claude already knows these mechanics.

Add an explicit validation feedback loop to the Test step (e.g. 'run the command on a sample scenario; if argument handling or MCP integration fails, fix and re-test').

Dimension	Reasoning	Score
Conciseness	The ~560-line body repeats frontmatter guidance in three places (<command_frontmatter>, <generation_patterns>, <creation_checklist>) and inlines a <command_features> section explaining general slash-command mechanics (namespacing, $ARGUMENTS, ! prefix, @ refs) that Claude already knows, which is noticeable padding.	2 / 5
Actionability	Provides concrete frontmatter examples by command type, named MCP tools (mcp__scopecraft-cmd__task_create), a full worked example_session with a copy-paste generated command, and a final checklist — mostly executable guidance with only minor gaps.	4 / 5
Workflow Clarity	A clear five-phase interview sequence followed by implementation_steps and a creation_checklist gives a well-ordered path; it lacks an explicit validate->fix->retry loop in the Test step, but the operation is not destructive/batch so the cap does not apply.	4 / 5
Progressive Disclosure	No bundle files exist and everything is inlined into one file; the XML-tagged sections provide structure, but reference-grade material (command_features, frontmatter options table) that belongs in a separate file is inline, and the only @ references point at the generated command's targets rather than this skill's own detail docs.	3 / 5
	Total	13 / 20 Passed

Description

53%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.

The description conveys a clear purpose and a distinct niche, but relies on abstract qualifiers ('proper structure, patterns') instead of concrete actions and omits any explicit 'when to use' trigger. Adding a Use-when clause and specific actions would lift it from adequate to strong.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to create, scaffold, or generate a new Claude slash command.'

Replace abstract qualifiers with concrete actions: 'Scaffolds command frontmatter, picks a category pattern, and wires MCP tool integration.'

Include natural synonyms ('slash command', 'custom command', '.claude/commands') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('creating new Claude commands') and a few aspects ('structure, patterns, and MCP tool integration'), but those aspects are abstract rather than concrete actions like 'scaffold frontmatter' or 'wire MCP tools'.	3 / 5
Completeness	It gives a clear 'what' (interactive assistant for command creation) but has no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	'creating new Claude commands' is a phrase a user might naturally say, but there are no synonyms or variations ('slash command', 'custom command', '.claude/commands') to broaden triggering.	3 / 5
Distinctiveness Conflict Risk	'Creating new Claude commands' is a fairly distinct niche with minimal overlap risk against other skills; it would not easily trigger for the wrong skill.	4 / 5
	Total	13 / 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
skill_md_line_count	SKILL.md is long (562 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: NeoLabHQ/context-engineering-kit
Path: plugins/customaize-agent/skills/create-command/SKILL.md
Commit: 23e2428

Reviewed: 18 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.