CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-creator

Scaffold a new Claude Code skill with SKILL.md, frontmatter, and bundled resources. Use when creating a custom skill, standardizing skill structure across a team, or packaging a skill for distribution.

80

2.27x
Quality

Does it follow best practices?

Impact

100%

2.27x

Average score across 1 eval scenario

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable skill body with clear workflow and good use of bundled scripts for detail. The main weakness is redundancy — repeated tips and a template inlined that already lives in init_skill.py — which costs conciseness without adding capability.

Suggestions

Remove the duplicated 'under 5000 words' guidance — it appears in both 'Validate the Skill' and 'Tips'; state it once.

Replace the inlined 'Generated SKILL.md Template' block with a pointer to init_skill.py (which already embeds the canonical template), so the template lives in one place.

Trim the 'Tips' section to items not already covered by Workflow/Validate to avoid restating the same guidance.

DimensionReasoningScore

Conciseness

Mostly efficient and free of concept explanations Claude already knows, but repeats itself — the 5000-word limit appears in both Validate and Tips, and the inlined 'Generated SKILL.md Template' duplicates the template already embedded in init_skill.py.

2 / 3

Actionability

Provides copy-paste-ready commands (init_skill.py and package_skill.py invocations), concrete example prompts, and a numbered validation checklist — fully executable guidance.

3 / 3

Workflow Clarity

Clear four-step sequence (Create, Template, Validate, Package) with an explicit validation checklist (frontmatter, content, structure, test) and a worked example that repeats the validate-and-test checkpoint.

3 / 3

Progressive Disclosure

SKILL.md is an overview that delegates heavy logic to the two real referenced scripts (init_skill.py, package_skill.py); no nested reference chains and bundle paths resolve to actual files.

3 / 3

Total

11

/

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.

A strong description: third-person voice, explicit 'Use when' clause, multiple concrete capabilities, and natural trigger terms that clearly bound its niche. No over-claims or padding.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Scaffold a new Claude Code skill with SKILL.md, frontmatter, and bundled resources' — naming the specific artifacts produced rather than vague activity.

3 / 3

Completeness

Clearly states what it does (scaffold skills with SKILL.md/frontmatter/bundled resources) and when to use it via an explicit 'Use when' clause with three distinct triggers.

3 / 3

Trigger Term Quality

Natural user phrasings like 'creating a custom skill', 'standardizing skill structure across a team', and 'packaging a skill for distribution' cover the realistic ways a user would request this.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (skill authoring/packaging) with triggers unlikely to overlap with content-focused skills, so conflict risk is low.

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
FlorianBruniaux/claude-code-ultimate-guide
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.