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.

87

1.85x
Quality

81%

Does it follow best practices?

Impact

100%

1.85x

Average score across 3 eval scenarios

SecuritybySnyk

Failed to scan

The risk profile of this skill

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 content is well-structured and actionable, with a clean overview that delegates depth to one real reference file. It is efficient and mostly executable, held back only slightly by a non-copy-paste Bash workaround example and the absence of an explicit post-creation verification loop.

Suggestions

Make the Bash-execution example directly copy-pasteable by working around bug #12762 differently (e.g., placing the ! in a separate code span or noting the substitution more prominently) so users do not have to manually edit the snippet.

Add an explicit verification step to the checklist, such as 'Run /command-name to confirm it executes and the frontmatter/arguments behave as expected', to create a clear post-creation feedback loop.

Trim the redundant restatement of the bug #12762 workaround in the Dynamic Content section since it is already covered by the inline comments and the reference doc.

DimensionReasoningScore

Conciseness

The body is largely efficient — tables and short code blocks deliver the key facts without explaining basic concepts Claude already knows — but includes a few minor padded sections (e.g., the redundant Dynamic Content note restating the bug workaround) that could be trimmed.

4 / 5

Actionability

It provides mostly executable guidance: concrete file locations, frontmatter field tables, and copy-ready code snippets for arguments and file references, but the Bash-execution example requires manual substitution ("Replace EXCLAMATION with the exclamation mark character") rather than being directly copy-paste ready.

4 / 5

Workflow Clarity

A clear checklist and well-sequenced sections (structure → basic command → frontmatter → arguments → dynamic content) guide authoring, and the final checklist acts as a validation checkpoint; however it lacks an explicit test/verify feedback loop for confirming the command works after creation, a minor validation gap.

4 / 5

Progressive Disclosure

The SKILL.md is a concise overview with a single, clearly signaled one-level-deep reference to ./references/official-docs.md, which is a real file; content is appropriately split between the overview and the detailed reference, matching the top anchor.

5 / 5

Total

17

/

20

Passed

Description

83%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 is strong: it explicitly states both what the skill does and when to use it, with multiple natural trigger phrases and a clear, distinct niche. Minor gaps in concrete capability enumeration and synonym coverage keep specificity and trigger quality just below full marks.

DimensionReasoningScore

Specificity

The description names the domain (creating custom commands for Claude Code) and several concrete triggering actions like "create a command", "write a slash command", "build a plugin command", though it does not enumerate the full set of concrete capabilities (e.g., namespacing, frontmatter, dynamic content), leaving minor gaps.

4 / 5

Completeness

It explicitly answers both what the skill does (creating custom commands for Claude Code) and when to use it ("when the user asks to ... or wants to add custom commands to Claude Code") with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

It includes several natural phrases a user would say ("create a command", "write a slash command", "build a plugin command", "add custom commands"), with good keyword coverage, though it misses some synonyms like "prompt" or "shortcuts".

4 / 5

Distinctiveness Conflict Risk

It targets a clear niche — Claude Code slash command/plugin command authoring — with distinct triggers unlikely to collide with other skills, fitting the top anchor.

5 / 5

Total

18

/

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.

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.