CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

create-command

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

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./antigravity/skills/create-command/SKILL.md

The canonical home for this skill is create-command in NeoLabHQ/context-engineering-kit

SKILL.md
Quality
Evals
Security

Quality

Content

71%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, copy-paste-ready examples and a well-sequenced multi-phase workflow including a test step. Its main weaknesses are repetition across sections (conciseness) and a monolithic single-file structure with no progressive disclosure into bundle references.

Suggestions

De-duplicate the frontmatter rules: state the 'frontmatter must be first, description required, argument-hint optional' requirement once and reference it from later sections instead of repeating it in command_frontmatter, generation_patterns, and the checklist.

Move the command-categories catalog and frontmatter-options reference table into a references/ file (e.g. references/command-patterns.md) and link to it from SKILL.md to enable progressive disclosure.

Add an explicit validate-fix-retry feedback loop after generation (e.g., lint the generated frontmatter / run the new command in a dry-run and fix errors before finalizing).

DimensionReasoningScore

Conciseness

Mostly actionable reference material with little explaining of concepts Claude already knows, but frontmatter requirements and MCP-tool guidance are repeated across multiple sections, fitting anchor 3 ('mostly efficient but could be tightened').

3 / 5

Actionability

Provides copy-paste-ready frontmatter examples, bash commands, concrete MCP tool names (e.g. mcp__scopecraft-cmd__task_create), argument syntax ($ARGUMENTS, $1), and a fully worked example command file covering common cases, matching anchor 5.

5 / 5

Workflow Clarity

The interview (Phases 1-5), implementation steps, and creation checklist give a clear sequenced process with checkpoints including a 'Test the Command' step; minor validation gaps (no explicit validate-fix-retry loop on generated output) keep it at anchor 4.

4 / 5

Progressive Disclosure

Content is well-organized into tagged sections and headers but lives entirely in one ~555-line SKILL.md with no bundle files or one-level-deep references to split out detailed material, matching anchor 3.

3 / 5

Total

15

/

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 but omits any explicit trigger/usage guidance, which caps several dimensions at 3. It is specific enough to be distinguishable yet could be sharpened with concrete actions and natural trigger phrases.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers (e.g., 'Use when creating or scaffolding new Claude/slash commands, or when the user asks to set up a project or user command').

Replace quality adjectives ('proper structure, patterns, and MCP tool integration') with concrete actions (e.g., 'scaffolds command frontmatter, picks command category and location, and wires up MCP tools').

Include natural synonyms/variations users actually say ('Claude commands', 'slash commands', 'custom commands', 'project vs user commands').

DimensionReasoningScore

Specificity

Names the domain ('creating new Claude commands') and lists qualities ('proper structure, patterns, and MCP tool integration'), but these are attributes rather than multiple distinct concrete actions, matching anchor 3.

3 / 5

Completeness

Provides a clear 'what' (interactive assistant for creating commands) but no 'when'/trigger guidance, so per the rubric guideline a missing trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

'creating new Claude commands' is a natural phrase a user might say, but no synonyms, variations, or explicit 'Use when...' trigger guidance are present, fitting anchor 3.

3 / 5

Distinctiveness Conflict Risk

Targets a distinct niche (authoring Claude commands with structure/patterns/MCP integration) with low overlap risk; slightly broad phrasing keeps it at anchor 4 rather than 5.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (561 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

NeoLabHQ/context-engineering-kit

Path

antigravity/skills/create-command/SKILL.md

Reviewed

Table of Contents

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.