CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-development

This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.

89

1.60x
Quality

Does it follow best practices?

Impact

93%

1.60x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

The body is highly actionable with a clear, well-validated workflow, but it is verbose and heavily self-repeating, violating its own lean-SKILL.md guidance. Progressive disclosure is preached more than practiced, with most detail kept inline rather than moved to the single bundled reference.

Suggestions

Consolidate the three repeated treatments of writing style (lines 160, 362, and 490) and merge the overlapping Common Mistakes, Best Practices Summary, and Validation Checklist sections to reduce redundancy and bring the body closer to its stated 1,500-2,000 word target.

Move detailed reference material (the extended good/bad examples, common-mistake walkthroughs, and quick-reference layouts) into references/ files and link to them from SKILL.md to practice the progressive disclosure the skill advocates.

Tighten the two progressive-disclosure sections (lines 77 and 318) into a single concise statement, keeping only the core three-level loading model inline and pointing to references for elaboration.

DimensionReasoningScore

Conciseness

The body is actionable in places but notably verbose and self-repeating: progressive disclosure is explained at line 77 and again at 318, writing style at 160/362/490, and the "Common Mistakes", "Best Practices Summary", and "Validation Checklist" sections restate the same guidance, exceeding the skill's own 1,500-2,000 word target.

2 / 3

Actionability

Provides copy-paste commands (`mkdir -p plugin-name/skills/skill-name/{references,examples,scripts}`, `cc --plugin-dir`), concrete YAML good/bad description examples, and specific directory structures, giving fully executable guidance for an instruction skill.

3 / 3

Workflow Clarity

The Skill Creation Process is sequenced as Steps 1-6 with an explicit Validate-and-Test step containing an 8-item checklist and an Iterate feedback loop, matching the clear-sequence-with-validation anchor.

3 / 3

Progressive Disclosure

The single bundled reference (`references/skill-creator-original.md`) is clearly signaled, but the body itself is a large monolith that keeps writing-style, common-mistakes, and quick-reference content inline despite the skill's own rule that such detail belongs in references/; the many other referenced files (patterns.md, advanced.md, etc.) are illustrative, not present.

2 / 3

Total

10

/

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, third-person description with explicit trigger guidance and concrete phrases users would naturally say. It clearly answers both what the skill does and when to use it, with low conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions such as "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", and "organize skill content", matching the highest anchor.

3 / 3

Completeness

It states what the skill provides ("guidance on skill structure, progressive disclosure, or skill development best practices") and explicitly when to use it via the "This skill should be used when..." clause with concrete triggers.

3 / 3

Trigger Term Quality

The quoted phrases ("create a skill", "write a new skill", "improve skill description") are natural terms a user would actually say, with good coverage of variations.

3 / 3

Distinctiveness Conflict Risk

The triggers are specific to skill/plugin development for Claude Code, forming a clear niche unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (638 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 26 missing, 2 deeper-than-1-level

Warning

Total

13

/

16

Passed

Repository
anthropics/claude-plugins-official
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.