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.
84
76%
Does it follow best practices?
Impact
96%
1.31xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/skill-creator/SKILL.mdQuality
Discovery
67%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 explains its purpose and includes explicit trigger guidance, which is a strength. However, it lacks concrete specific actions that would help Claude understand exactly what this skill teaches, and the trigger terms could be more comprehensive to capture natural user language variations.
Suggestions
Add specific concrete actions like 'write YAML frontmatter', 'define description fields', 'structure skill content sections', or 'set up trigger conditions'
Expand trigger terms to include variations users might naturally say: 'write a skill', 'skill file', 'SKILL.md', 'teach Claude', 'new capability'
| 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'), with explicit trigger guidance using 'This skill should be used when...' clause. | 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 | Reasonably specific to skill creation, but 'extends Claude's capabilities with specialized knowledge, workflows, or tool integrations' is broad and could overlap with documentation or configuration skills. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, comprehensive skill that effectively teaches skill creation through clear workflows and concrete examples. Its main weakness is some verbosity in explaining concepts (like what skills are) that Claude already understands. The progressive disclosure patterns and actionable commands make this highly usable.
Suggestions
Trim the 'About Skills' and 'What Skills Provide' sections significantly - Claude understands these concepts and this adds ~200 tokens of unnecessary context
Remove or condense metaphorical explanations like 'narrow bridge with cliffs' in favor of direct guidance
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary explanation (e.g., explaining what skills are to Claude, the 'narrow bridge with cliffs' metaphor) but is mostly efficient. Some sections like 'What to Not Include' could be more concise. | 2 / 3 |
Actionability | Provides concrete, executable commands (init_skill.py, package_skill.py with exact syntax), specific directory structures, and copy-paste ready examples. The step-by-step process is fully actionable. | 3 / 3 |
Workflow Clarity | Clear 6-step sequential process with explicit validation built into Step 5 (packaging validates automatically). Each step has clear entry/exit criteria and the workflow includes feedback loops in Step 6 for iteration. | 3 / 3 |
Progressive Disclosure | Excellent structure with clear navigation to external references (references/workflows.md, references/output-patterns.md). Content is well-organized with headers, and the skill demonstrates the very patterns it teaches. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
38245b8
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.