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.
83
76%
Does it follow best practices?
Impact
97%
1.27xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skill-creator/SKILL.mdQuality
Discovery
75%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 adequately communicates its purpose and includes explicit 'when to use' guidance, which is a strength. However, it lacks specific concrete actions that would help Claude understand the full scope of what this skill enables, and could benefit from additional natural trigger terms users might employ when seeking help with skill creation.
Suggestions
Add specific concrete actions like 'write YAML frontmatter', 'define trigger conditions', 'structure skill markdown content', 'validate skill format'
Include additional trigger term variations such as 'SKILL.md', 'skill file', 'new capability', 'teach Claude', 'custom workflow'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (creating skills) and mentions some actions ('create a new skill', 'update an existing skill'), but lacks concrete specific actions like 'write YAML frontmatter', 'define trigger conditions', or 'structure skill content'. | 2 / 3 |
Completeness | Clearly answers both what ('Guide for creating effective skills') and when ('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'). | 3 / 3 |
Trigger Term Quality | Includes relevant keywords like 'skill', 'create', 'update', but misses common variations users might say such as 'write a skill', 'new capability', 'skill file', 'SKILL.md', or 'extend Claude'. | 2 / 3 |
Distinctiveness Conflict Risk | Has a clear niche focused specifically on skill creation/modification, with distinct triggers around 'skill' and 'extends Claude's capabilities' that are unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive, well-structured skill with excellent workflow clarity and actionability. The step-by-step process is clearly sequenced with validation checkpoints, and concrete examples are provided throughout. However, the skill is verbose for its purpose—much of the detailed reference material (frontmatter fields, inline vs fork decision matrix) could be moved to reference files to keep SKILL.md leaner.
Suggestions
Move the detailed YAML frontmatter reference table and inline vs fork decision guide to separate reference files (e.g., references/frontmatter_reference.md, references/context_decision_guide.md) and link to them from SKILL.md
Trim explanatory content like 'Think of them as onboarding guides' and 'What Skills Provide' section—Claude understands these concepts
Consider splitting the 'Anatomy of a Skill' section into a separate reference file since it's detailed documentation rather than procedural workflow
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary explanations (e.g., 'Think of them as onboarding guides') and could be tightened in places, but overall provides substantial value. Some sections like 'What Skills Provide' explain concepts Claude likely understands. | 2 / 3 |
Actionability | Provides concrete, executable guidance throughout: specific bash commands for packaging/validation, exact YAML frontmatter examples, clear script invocations like `scripts/init_skill.py <skill-name> --path <output-directory>`, and copy-paste ready code blocks. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with clear sequencing (Steps 1-9), explicit validation checkpoints (Step 6 security review, Step 7 packaging validation), and feedback loops ('If validation fails... fix and run again'). Includes decision guides for critical choices like inline vs fork. | 3 / 3 |
Progressive Disclosure | References external files appropriately (references/sanitization_checklist.md, external Anthropic docs), but the SKILL.md itself is quite long (~400+ lines) with detailed content that could be split into reference files. The inline vs fork decision guide and frontmatter reference could be separate documents. | 2 / 3 |
Total | 10 / 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 |
|---|---|---|
skill_md_line_count | SKILL.md is long (533 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- fernandezbaptiste/claude-code-skills
- Commit
4f0eae8
- 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.