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.
67
53%
Does it follow best practices?
Impact
93%
1.60xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/plugin-dev/skills/skill-development/SKILL.mdQuality
Discovery
72%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 trigger term coverage and occupies a clear niche, but it lacks an explicit statement of what the skill actually does (its concrete capabilities and outputs). It reads more like a list of trigger conditions than a balanced description of capabilities plus usage guidance. Restructuring to lead with concrete actions would significantly improve it.
Suggestions
Add an explicit 'what it does' section before the trigger terms, e.g., 'Guides creation of well-structured SKILL.md files including YAML frontmatter, description fields, and progressive disclosure patterns for Claude Code plugins.'
Separate the capability description from the trigger clause — start with concrete actions (generates, validates, organizes) then follow with 'Use when...' for clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (skill creation for Claude Code plugins) and mentions some actions like 'create a skill', 'improve skill description', 'organize skill content', but it doesn't list concrete specific capabilities beyond these quoted trigger phrases. It references concepts like 'progressive disclosure' and 'skill development best practices' but doesn't explain what concrete actions the skill performs. | 2 / 3 |
Completeness | The description has a 'Use when' clause (it starts with 'This skill should be used when...'), but the 'what does this do' part is weak — it mostly lists trigger scenarios rather than clearly describing the skill's capabilities or outputs. The 'what' is only implied through the trigger terms rather than explicitly stated. | 2 / 3 |
Trigger Term Quality | The description includes multiple natural trigger phrases users would actually say: 'create a skill', 'add a skill to plugin', 'write a new skill', 'improve skill description', 'organize skill content'. These are realistic user utterances and cover several variations of the core intent. | 3 / 3 |
Distinctiveness Conflict Risk | The description targets a very specific niche — creating and improving skills for Claude Code plugins. The trigger terms like 'skill', 'plugin', 'progressive disclosure', and 'skill structure' are distinctive and unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is deeply ironic—it teaches progressive disclosure and conciseness while being a verbose, monolithic document that violates nearly every principle it advocates. The core workflow (Steps 1-6) is solid and well-structured, but it's buried in repetitive explanations of writing style, trigger phrases, and progressive disclosure that are each stated 3+ times. The skill would benefit enormously from practicing what it preaches: moving detailed examples, common mistakes, and style guides into references/ files.
Suggestions
Practice what the skill preaches: move 'Common Mistakes to Avoid', 'Writing Style Requirements', and 'Progressive Disclosure in Practice' sections to references/ files, reducing SKILL.md to the target 1,500-2,000 words
Eliminate redundancy: trigger phrase guidance appears in Steps 1, 4, 5, Common Mistakes, and Best Practices Summary—consolidate to one authoritative location
Remove the 'About Skills' section entirely or reduce to 2-3 sentences—Claude doesn't need to be told what skills are when it's being instructed on how to create them
Add explicit error recovery to the validation step: 'If description lacks trigger phrases → add specific user queries. If SKILL.md exceeds 3,000 words → identify sections to extract to references/'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~3,500+ words, with extensive repetition of the same concepts (writing style requirements are stated at least 3 times, progressive disclosure explained multiple times, trigger phrase guidance repeated in multiple sections). It explains concepts Claude already knows (what skills are, what PDFs are conceptually) and includes redundant 'Common Mistakes' that simply restate rules already covered. The 'About Skills' section is largely unnecessary preamble. | 1 / 3 |
Actionability | The skill provides some concrete guidance like directory structure commands and YAML frontmatter examples, but much of the content is meta-guidance about writing style and organization rather than executable steps. The examples are illustrative but not truly copy-paste ready for creating a specific skill—they're more like style guides than actionable templates. | 2 / 3 |
Workflow Clarity | The 6-step creation process (Steps 1-6) provides a clear sequence, and Step 5 includes a validation checklist. However, the validation step lacks explicit feedback loops—it's a checklist without clear 'if X fails, do Y' recovery paths. The workflow is also buried within massive amounts of surrounding content, making it harder to follow. | 2 / 3 |
Progressive Disclosure | The skill references `references/skill-creator-original.md` and other skill directories as examples, showing some progressive disclosure. However, the SKILL.md itself is a monolithic wall of text that violates its own advice of keeping SKILL.md to 1,500-2,000 words. Much of the detailed content (writing style examples, common mistakes, progressive disclosure details) should be in references/ files per the skill's own guidance. | 2 / 3 |
Total | 7 / 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.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
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 |
Total | 9 / 11 Passed | |
48aa435
Table of Contents
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.