CtrlK
BlogDocsLog inGet started
Tessl Logo

claude-code-slash-commands

This skill should be used when the user asks to "create a command", "write a slash command", "build a plugin command", or wants to add custom commands to Claude Code.

85

1.85x
Quality

Does it follow best practices?

Impact

100%

1.85x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

57%

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 leans appropriately on a real one-level reference file, but it loses points on conciseness and actionability due to duplicated reference content and a non-executable EXCLAMATION-placeholder workaround, and lacks an explicit validated creation workflow.

Suggestions

Remove the frontmatter/command-location tables that duplicate ./references/official-docs.md and keep only a concise summary plus the link, so the body earns every token.

Replace the EXCLAMATION-placeholder bash-execution example with a directly executable example (or a fenced snippet that shows the real `!` prefix) so guidance is copy-paste ready.

Add a short explicit creation workflow with a validation step (e.g. create the file, then verify it appears via `/help` or invoke `/command --help`) so the checklist becomes a true feedback loop.

DimensionReasoningScore

Conciseness

Mostly efficient with tables and code examples, but the frontmatter and command-location material duplicates the referenced official-docs.md, and the EXCLAMATION-placeholder workaround adds noise rather than earning every token.

2 / 3

Actionability

Provides concrete locations, frontmatter options, and code blocks, but the Bash-execution example uses a non-executable `EXCLAMATION` placeholder requiring manual substitution rather than copy-paste-ready commands.

2 / 3

Workflow Clarity

Sections are well organized and a checklist gives a light sequence, but there is no explicit step-by-step creation workflow with validation checkpoints for confirming a command works before finishing.

2 / 3

Progressive Disclosure

Clear overview in the body with a single, well-signaled one-level reference to ./references/official-docs.md (a real file), keeping detailed reference material out of the main skill.

3 / 3

Total

9

/

12

Passed

Description

100%

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 is concise, specific, and follows the recommended pattern of stating capabilities plus an explicit 'Use when...' style trigger. It covers multiple natural phrasings users would actually say and is clearly distinct from other skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions a user would request — "create a command", "write a slash command", "build a plugin command", and "add custom commands to Claude Code" — rather than vague language.

3 / 3

Completeness

Explicitly states both what the skill does (custom slash commands) and when to use it via a clear "should be used when the user asks to..." trigger clause.

3 / 3

Trigger Term Quality

Uses natural phrasings users would actually say ("create a command", "write a slash command", "build a plugin command", "add custom commands to Claude Code") with good coverage of variations.

3 / 3

Distinctiveness Conflict Risk

Tied to a clear niche — Claude Code slash/plugin commands — with distinct triggers unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
dwmkerr/claude-toolkit
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.