Scaffolds new Agent Skills with SKILL.md frontmatter, folder structure, and bundled resources. USE FOR: create a skill, scaffold skill, new skill template, add agent capability. DO NOT USE FOR: Azure infrastructure, Bicep/Terraform code, architecture decisions.
83
78%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.github/skills/make-skill-template/SKILL.mdQuality
Discovery
100%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 is a strong skill description that clearly communicates its purpose, includes natural trigger terms, and explicitly defines both positive and negative use cases. The DO NOT USE FOR clause is a particularly effective addition that helps disambiguate this skill from infrastructure-related skills. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: scaffolding new Agent Skills, creating SKILL.md frontmatter, setting up folder structure, and bundling resources. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (scaffolds new Agent Skills with frontmatter, folder structure, bundled resources) and 'when' (explicit USE FOR and DO NOT USE FOR clauses with specific trigger scenarios). | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'create a skill', 'scaffold skill', 'new skill template', 'add agent capability'. These are realistic phrases a user would type when needing this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct niche focused specifically on Agent Skill scaffolding. The explicit DO NOT USE FOR clause listing Azure infrastructure, Bicep/Terraform, and architecture decisions further reduces conflict risk with related but different skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
57%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 meta-skill with excellent progressive disclosure and reference organization. Its main weaknesses are that the core creation workflow is delegated to a reference file rather than being actionable inline, and some sections (Prerequisites, When to Use) add little value for Claude. The skill would benefit from inlining the key frontmatter rules and creation steps rather than requiring a reference file load for the primary use case.
Suggestions
Inline the essential frontmatter field requirements and description best practices from 'references/step-by-step-guide.md' directly into the skill body, keeping only advanced details in the reference file.
Remove or significantly trim the 'Prerequisites' and 'When to Use This Skill' sections — the former lists vague requirements and the latter duplicates frontmatter description triggers.
Integrate validation checkpoints directly into the Quick Start workflow steps (e.g., after step 3, add 'Validate: npm run skill:validate' before proceeding to step 4).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary sections like 'Prerequisites' (listing things like 'understanding of what the skill should accomplish' is not actionable) and 'When to Use This Skill' which largely duplicates what should be in the frontmatter description. The troubleshooting table and validation checklist add value but could be tighter. | 2 / 3 |
Actionability | The Quick Start section provides concrete steps, and the folder structure example is helpful. However, the core creation process is delegated to a reference file ('references/step-by-step-guide.md') rather than being directly actionable in the skill body. The validation command `npm run skill:validate` is concrete but the main workflow lacks executable detail inline. | 2 / 3 |
Workflow Clarity | The Quick Start provides a clear 5-step sequence for duplicating the template, and the 4-step creation process is referenced but not detailed inline. There are no explicit validation checkpoints within the workflow steps themselves — the validation checklist is separate rather than integrated into the workflow as feedback loops. | 2 / 3 |
Progressive Disclosure | Excellent use of progressive disclosure with a clear Reference Index table explaining when to load each reference file. References are one level deep, clearly signaled, and the main body provides a concise overview without inlining all the detailed content. The 'Load these on demand — do NOT read all at once' instruction is a smart touch. | 3 / 3 |
Total | 9 / 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.
ec7b8ff
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.