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.
Install with Tessl CLI
npx tessl i github:anthropics/claude-plugins-official --skill skill-developmentOverall
score
71%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
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.
This description excels at trigger term coverage and distinctiveness, making it easy for Claude to know when to select it. However, it's structured backwards - it focuses heavily on 'when to use' while leaving 'what it does' vague. The description would benefit from leading with concrete capabilities before the trigger conditions.
Suggestions
Add specific capabilities at the beginning, e.g., 'Guides creation of SKILL.md files with proper YAML frontmatter, structured content sections, and example patterns.'
Restructure to lead with 'what' before 'when': describe concrete outputs (skill files, descriptions, content organization) before listing trigger phrases.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (skill development for Claude Code plugins) and mentions some actions like 'create', 'add', 'write', 'improve', 'organize', but doesn't list concrete specific capabilities - it's more about when to use rather than what it actually does. | 2 / 3 |
Completeness | The 'when' is very well covered with explicit trigger phrases, but the 'what' is weak - it mentions 'guidance on skill structure, progressive disclosure, or skill development best practices' but doesn't clearly describe what concrete actions or outputs the skill provides. | 2 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'create a skill', 'add a skill to plugin', 'write a new skill', 'improve skill description', 'organize skill content', plus domain terms like 'progressive disclosure' and 'skill development best practices'. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche focused on Claude Code plugin skill development - the combination of 'skill', 'plugin', and 'Claude Code' creates a distinct trigger space unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
63%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides excellent actionable guidance with clear workflows and validation steps, but severely violates its own principles of conciseness and progressive disclosure. At 4,500+ words with significant repetition, it contradicts its own recommendation to keep SKILL.md under 2,000 words. The irony of a skill-development skill that doesn't follow skill-development best practices undermines its effectiveness.
Suggestions
Move 'Common Mistakes to Avoid', 'Writing Style Requirements', and 'Validation Checklist' sections to references/ files, reducing SKILL.md to ~1,500-2,000 words as the skill itself recommends
Consolidate redundant content - writing style guidance appears in Steps 4, 'Writing Style Requirements', 'Common Mistakes', and 'Best Practices Summary' sections
Remove explanatory content Claude already knows (e.g., 'Skills are modular, self-contained packages...', basic directory structure explanations) and focus on procedural instructions
Add a 'Quick Reference' section at the top with the essential workflow, moving detailed explanations to references/
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~4,500+ words, with significant redundancy. It explains concepts Claude already knows (what skills are, basic directory structures), repeats the same guidance multiple times (writing style requirements appear in at least 3 sections), and includes excessive examples of good/bad patterns that could be consolidated. | 1 / 3 |
Actionability | The skill provides concrete, executable guidance with specific bash commands for creating skill structures, exact YAML frontmatter examples, clear code blocks for correct/incorrect patterns, and step-by-step workflows. The instructions are copy-paste ready. | 3 / 3 |
Workflow Clarity | The 6-step skill creation process is clearly sequenced with explicit validation checkpoints (Step 5 has a detailed validation checklist). Each step has clear entry/exit criteria, and the workflow includes iteration guidance for error recovery. | 3 / 3 |
Progressive Disclosure | While the skill references a `references/skill-creator-original.md` file and mentions studying other skills, the SKILL.md itself is a monolithic document that violates its own advice about keeping content under 2,000 words. Much of the detailed content (common mistakes, validation checklist, writing style requirements) should be in references/ files. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
82%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 | |
- 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.