CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

78

1.85x
Quality

73%

Does it follow best practices?

Impact

100%

1.85x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/toolkit/skills/claude-code-slash-commands/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 a lean, actionable quick reference with a real, well-signaled external doc and a closing checklist. Main gaps are content duplication with the reference file, a dated model ID, and a questionable verification step in the checklist.

Suggestions

Trim the frontmatter-options table and dynamic-content details from SKILL.md, leaving one-line pointers to official-docs.md to remove the near-verbatim duplication.

Replace the dated model example "claude-3-5-haiku-20241022" with a generic placeholder, and swap the "--help style invocation" checklist item for a real verification such as typing / to confirm the command appears in autocomplete.

DimensionReasoningScore

Conciseness

The body is dense reference material (tables, code blocks, a checklist) with no padding explaining concepts Claude already knows. Not 5 because of the dated model string "claude-3-5-haiku-20241022" in the frontmatter example — time-sensitive version info not placed in a deprecated section — and the workaround note that could be trimmed into the reference.

4 / 5

Actionability

Concrete file locations, copy-paste frontmatter blocks, and exact $ARGUMENTS/$1 syntax make the guidance mostly executable. Not 5 because the Bash-execution example is deliberately non-copy-pasteable ("EXCLAMATION`git branch --show-current`" — a justified bug workaround, but still not paste-ready) and the checklist item "Test with /command-name --help style invocation" is not a real slash-command behavior; not 3 because everything else is specific and complete.

4 / 5

Workflow Clarity

The task is simple (create a command file), the single action is unambiguous, and the closing checklist provides validation checkpoints. Not 5 because the checklist's test step is dubious and there is no explicit sequencing of decide-scope → write file → verify; not 3 because the checklist and per-scope location table give adequate checkpoints for this non-destructive task.

4 / 5

Progressive Disclosure

A single, clearly signaled, one-level-deep reference (./references/official-docs.md, verified to exist) with a well-organized overview body. Not 5 because the frontmatter options, arguments, dynamic content, and namespacing sections duplicate near-verbatim content in the reference file, so the split between overview and detail is not clean; not 3 because structure and navigation are otherwise good.

4 / 5

Total

16

/

20

Passed

Description

61%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 has strong, natural trigger phrases and an explicit use-when clause, but it omits an explicit statement of what the skill does and treats a single action through several synonymous phrasings. Adding a capability sentence would lift both specificity and completeness.

Suggestions

Lead with a capability statement in third person (e.g., "Creates custom slash command Markdown files for Claude Code projects, personal scopes, and plugins") before the use-when clause.

Broaden action coverage beyond creation synonyms to include related tasks like editing commands, adding arguments/frontmatter, or namespacing them into subdirectories.

Add one or two more natural trigger variants such as "make a new command" or "custom command" to round out keyword coverage.

DimensionReasoningScore

Specificity

The trigger quotes ("create a command", "write a slash command", "build a plugin command") name the domain clearly, but create/write/build/add are synonyms of a single action rather than distinct capabilities, and coverage of the topic (e.g., editing commands, namespacing, frontmatter) is not comprehensive. Not 4 because it does not list several specific distinct actions; not 2 because the domain is concrete, not generic.

3 / 5

Completeness

The "when" is explicit ("This skill should be used when the user asks to..."), but the "what" is never stated as a capability of the skill — it is only implied through the quoted user asks. Not 4 because a "what" clause (e.g., "Creates custom slash command Markdown files...") is absent; not 2 because the concrete trigger phrases strongly convey the domain and action.

3 / 5

Trigger Term Quality

Phrases like "create a command", "write a slash command", "build a plugin command", and "add custom commands to Claude Code" are natural things a user would say, with good synonym coverage across command/slash command/plugin command/custom command. Not 5 because common variations such as "make a new command" or "custom prompt" are missing.

4 / 5

Distinctiveness Conflict Risk

The niche (Claude Code custom slash commands) is distinct, and "slash command" / "plugin command" / "custom commands to Claude Code" anchor it well. Not 5 because the bare phrase "create a command" could also match shell/CLI command or git alias creation requests; not 3 because the Claude Code qualifiers keep overlap minor.

4 / 5

Total

14

/

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

allowed_tools_field

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

Warning

Total

15

/

16

Passed

Repository

dwmkerr/claude-toolkit

Path

plugins/toolkit/skills/claude-code-slash-commands/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.