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.
Install with Tessl CLI
npx tessl i github:vercel-labs/agent-browser --skill skill-creatorOverall
score
81%
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/skillEvaluation — 79%
↑ 1.23xAgent success when using this skill
Validation for skill structure
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.
This 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 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' to improve specificity.
Include additional trigger terms users might naturally say: 'SKILL.md', 'write a skill', 'skill file', 'new capability', 'skill template'.
| 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 in the second sentence. | 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 phrases like 'extends Claude's capabilities' and 'specialized knowledge, workflows, or tool integrations' are broad and could overlap with other meta-skills or documentation 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. Its main strength is the clear 6-step workflow with concrete examples and executable commands. The primary weakness is some verbosity in the introductory sections explaining concepts that could be more concise, though the procedural content is appropriately detailed.
Suggestions
Trim the 'About Skills' and 'What Skills Provide' sections - Claude understands these concepts and the description frontmatter already covers when to use the skill
Consider moving the 'Core Principles' section to a references file since it's conceptual guidance rather than procedural instructions
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary explanations (e.g., 'Think of them as onboarding guides', explaining what skills provide) and could be tightened. However, most content is relevant procedural knowledge that Claude wouldn't inherently know about this specific skill system. | 2 / 3 |
Actionability | Provides concrete, executable commands (init_skill.py, package_skill.py with exact syntax), specific file structure examples, and copy-paste ready patterns. The 6-step process is clearly actionable with specific instructions at each stage. | 3 / 3 |
Workflow Clarity | The 6-step skill creation process is clearly sequenced with explicit validation (Step 5 packaging validates automatically). Each step has clear entry/exit criteria, and the workflow includes feedback loops (Step 6: Iterate based on real usage). | 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 appropriately demonstrates the progressive disclosure pattern it teaches. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
88%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 14 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
Total | 14 / 16 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.