CtrlK
BlogDocsLog inGet started
Tessl Logo

command-creator

This skill should be used when creating a Claude Code slash command. Use when users ask to "create a command", "make a slash command", "add a command", or want to document a workflow as a reusable command. Essential for creating optimized, agent-executable slash commands with proper structure and best practices.

86

1.83x
Quality

79%

Does it follow best practices?

Impact

99%

1.83x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./codex/command-creator/SKILL.md

The canonical home for this skill is command-creator in jdrhyne/agent-skills

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 well-structured with clear, actionable workflow steps and excellent progressive disclosure to real bundle files. Its main weakness is redundancy across the About, Quick Tips, and Summary sections and the absence of an explicit validation checkpoint for the generated command file.

Suggestions

Remove or condense the 'About Slash Commands' concept explanation and the redundant 'Summary'/'Quick Tips' sections, which restate the six-step workflow and patterns already detailed above.

Add an explicit validation checkpoint in Step 5 or 6 (e.g., confirm the file's frontmatter parses and the command is invocable via /command-name) before reporting completion.

Inline a minimal complete command-file template in the 'Command Structure Overview' so the core artifact is copy-paste ready without loading best-practices.md.

DimensionReasoningScore

Conciseness

The core workflow is efficient, but the "About Slash Commands" section explains a concept Claude already knows, and both the "Quick Tips" and "Summary" sections restate steps and patterns already covered, adding padding that could be trimmed.

3 / 5

Actionability

Provides concrete, executable guidance — specific commands (git rev-parse, mkdir -p), file paths, a frontmatter template example, kebab-case rules with correct/wrong examples, and argument-hint syntax — with minor gaps because the full command-file template lives in a reference rather than inline.

4 / 5

Workflow Clarity

A clear six-step sequence (location → patterns → gather info → generate → create file → test) with explicit substeps and a "report chosen location before proceeding" checkpoint, but no explicit validation that the written command file is well-formed or invokable before declaring done.

4 / 5

Progressive Disclosure

SKILL.md is a clean overview with well-signaled, one-level-deep references (references/patterns.md, examples.md, best-practices.md) — all confirmed to exist — each described with its purpose, making navigation easy.

5 / 5

Total

16

/

20

Passed

Description

87%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 both the skill's purpose and concrete trigger phrases, with strong specificity and low conflict risk. It is slightly held back by overlapping action phrasing and missing a few natural synonyms/extensions.

DimensionReasoningScore

Specificity

Lists several concrete actions — "creating a Claude Code slash command", "document a workflow as a reusable command", "creating optimized, agent-executable slash commands with proper structure and best practices" — though several are restatements of the same core action rather than distinct capabilities, leaving minor coverage gaps.

4 / 5

Completeness

Explicitly answers both what (creating optimized, agent-executable slash commands with structure and best practices) and when ("Use when users ask to ... or want to document a workflow as a reusable command") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural phrases users would say ("create a command", "make a slash command", "add a command") with good synonym coverage, but lacks file-extension or path-style triggers and a few common variations.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (Claude Code slash command creation) with distinct trigger phrases, posing minimal conflict risk with unrelated skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
bap-jorkim/agent-skills-fork-feb-25
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.