create-command

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

Quality

51%

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

50%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 highly actionable with concrete templates, MCP tool names, and a worked example, but it is noticeably verbose with repeated guidance and lacks explicit validation checkpoints in its workflow. Splitting reference material into bundle files would improve progressive disclosure.

Suggestions

De-duplicate the frontmatter and MCP-tool-vs-CLI guidance, which is repeated across <command_frontmatter>, <generation_patterns>, and the checklist.

Add an explicit validation/verification checkpoint in the workflow (e.g., 'Test the command with a sample invocation; if it errors, fix and re-test before finalizing').

Move the frontmatter options table and full example session into a references/ bundle file, keeping SKILL.md as a lean overview with one-level-deep pointers.

Dimension	Reasoning	Score
Conciseness	The ~560-line body repeats frontmatter guidance, MCP-tool-vs-CLI reminders, and example blocks across multiple sections, and restates slash-command mechanics ($ARGUMENTS, @, ! prefixes) Claude already knows, fitting the 'noticeably verbose with several padded sections' anchor.	2 / 5
Actionability	Provides concrete frontmatter templates, specific MCP tool names (mcp__scopecraft-cmd__task_create), file-reference syntax, and a fully worked example command file, with only minor gaps from project-specific placeholder paths.	4 / 5
Workflow Clarity	A clear sequenced interview process (Phases 1-5) plus implementation steps and a checklist is present, but there are no explicit validation/verification checkpoints or error-recovery feedback loops, matching the anchor for steps listed with validation gaps.	3 / 5
Progressive Disclosure	No bundle files exist and all content is inlined into one monolithic SKILL.md; external doc references are present but not bundled, and content that could be split (frontmatter reference table, full example session) is inline, fitting the 'some structure but could be better organized' anchor.	3 / 5
	Total	12 / 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 clearly states the skill's purpose and carves out a distinct niche, but it lacks an explicit 'Use when...' trigger clause and misses natural synonyms like 'slash command'. It is solid but not exemplary.

Suggestions

Add an explicit trigger clause, e.g. 'Use when creating or scaffolding a new Claude slash command, or when the user asks to make a custom command.'

Include natural synonyms users would say ('slash command', 'custom command') alongside 'Claude commands'.

Replace abstract facets ('proper structure, patterns') with concrete actions such as 'generates frontmatter, picks a command category, and wires up MCP tools'.

Dimension	Reasoning	Score
Specificity	Names the domain ('creating new Claude commands') and lists facets like 'structure, patterns, and MCP tool integration', but these are abstract rather than concrete executable actions, matching the anchor that names domain plus a couple of actions without comprehensive coverage.	3 / 5
Completeness	Provides a clear 'what' (interactive assistant for creating commands with structure/patterns/MCP) but no explicit 'when' / 'Use when...' trigger clause, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Contains relevant keywords ('creating new Claude commands', 'MCP tool integration') but omits common natural variations users would say such as 'slash command' or 'custom command', fitting the anchor for some relevant keywords missing synonyms.	3 / 5
Distinctiveness Conflict Risk	Targets a clear niche (command-creation meta-skill) with distinct triggers and only minor overlap risk with closely related coding/dev skills, matching the 'mostly distinct' anchor.	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 (563 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: 8539779

Reviewed: 4 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.