skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
62
42%
Does it follow best practices?
Impact
99%
1.17xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/skill-creator/SKILL.mdQuality
Discovery
57%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 successfully communicates when to use the skill with an explicit 'Use when' clause, but falls short on specificity of what concrete actions it performs. The 'what' portion is vague ('guide for creating effective skills') without detailing specific actions like generating frontmatter, structuring markdown, or validating skill format. Trigger terms are adequate but could include more natural variations.
Suggestions
Replace the vague 'Guide for creating effective skills' with specific actions like 'Generates SKILL.md files with proper YAML frontmatter, writes structured markdown instructions, and validates skill format'.
Add more natural trigger term variations such as 'SKILL.md', 'skill file', 'write a skill', 'skill template', or 'custom workflow'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description says 'creating effective skills' and 'extends Claude's capabilities with specialized knowledge, workflows, or tool integrations' but doesn't list concrete actions like 'generates YAML frontmatter, writes markdown instructions, validates skill structure.' The language is abstract and vague about what it actually does. | 1 / 3 |
Completeness | It answers both 'what' (guide for creating effective skills) and 'when' ('should be used when users want to create a new skill or update an existing skill'). The 'when' clause is explicit with clear trigger conditions. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'create a new skill', 'update an existing skill', and 'skill' which users would naturally say. However, it misses variations like 'SKILL.md', 'skill file', 'write a skill', 'skill template', or 'custom instruction'. | 2 / 3 |
Distinctiveness Conflict Risk | The term 'skill' is somewhat specific to this domain, but 'extends Claude's capabilities with specialized knowledge, workflows, or tool integrations' is broad enough to potentially overlap with other meta-skills or configuration-related skills. The niche is identifiable but not sharply delineated. | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill suffers primarily from excessive verbosity—it spends significant tokens explaining concepts Claude already understands (what skills are, what directories do, what progressive disclosure means) rather than focusing on actionable, non-obvious guidance. The workflow is reasonably structured but lacks concrete examples of good SKILL.md output and validation checkpoints. Ironically, the skill about creating skills violates its own progressive disclosure principle by inlining all content rather than splitting detailed reference material into separate files.
Suggestions
Move the 'About Skills' section (anatomy, resource types, progressive disclosure explanation) into a references/ file and keep only a brief summary in SKILL.md—this would practice the progressive disclosure the skill itself advocates.
Add a concrete example of a well-written SKILL.md (input scenario → output SKILL.md content) to make Step 4 more actionable rather than abstract.
Remove explanations of concepts Claude already knows, such as what PDF libraries do, what scripts/references/assets directories contain, and the general concept of modular design.
Add an explicit validation checkpoint after Step 4 (e.g., a checklist to verify SKILL.md quality before packaging) to strengthen the workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is very verbose, explaining concepts Claude already knows (what skills are, what scripts/references/assets are, the concept of progressive disclosure). Sections like 'What Skills Provide' and 'About Skills' are largely unnecessary background. The entire 'Anatomy of a Skill' section explains directory structures and file purposes at length when Claude already understands these concepts. | 1 / 3 |
Actionability | The skill provides some concrete guidance (init_skill.py and package_skill.py commands are executable), but much of the content is descriptive rather than instructive. The actual editing guidance in Step 4 is abstract ('answer the following questions') rather than providing concrete templates or examples of good SKILL.md content. | 2 / 3 |
Workflow Clarity | The 6-step process is clearly sequenced and logically ordered, with some guidance on when to skip steps. However, there are no validation checkpoints between steps (e.g., no check after Step 4 to verify SKILL.md quality before packaging), and the feedback loop in Step 6 is vague. The packaging step does include validation, which is good. | 2 / 3 |
Progressive Disclosure | The skill is a monolithic wall of text with no references to external files. Detailed explanations of skill anatomy, resource types, and the progressive disclosure principle itself could be moved to reference files. The content that should be a concise overview is instead an exhaustive inline guide spanning many sections. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- davepoon/buildwithclaude
- Commit
7cc63f3
- 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.