Trigger: new skills, agent instructions, documenting AI usage patterns. Create LLM-first skills with valid frontmatter.
64
75%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./internal/assets/skills/skill-creator/SKILL.mdQuality
Discovery
50%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 conveys a recognizable domain (skill creation for LLMs) and includes some trigger terms, but lacks the specificity of multiple concrete actions and an explicit 'Use when...' clause. The trigger terms are a mix of useful and vague, and the description could be more distinctive by specifying file formats, structure details, or clearer use-case boundaries.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to create a new skill file, write a SKILL.md, or define agent instructions with YAML frontmatter.'
List more concrete actions beyond 'create', such as 'validate frontmatter fields, structure skill content with examples, define trigger conditions'.
Include more natural user terms like 'SKILL.md', 'skill file', 'teach Claude', 'custom skill', 'YAML metadata' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain ('LLM-first skills') and a specific action ('Create LLM-first skills with valid frontmatter'), but doesn't list multiple concrete actions beyond creation. The phrase 'documenting AI usage patterns' adds some specificity but is vague. | 2 / 3 |
Completeness | The 'what' is partially addressed ('Create LLM-first skills with valid frontmatter') and the 'when' is implied through the 'Trigger:' prefix listing trigger scenarios, but there is no explicit 'Use when...' clause with clear guidance on when Claude should select this skill. | 2 / 3 |
Trigger Term Quality | Includes some relevant terms like 'new skills', 'agent instructions', 'frontmatter', but misses common variations users might say such as 'skill file', 'SKILL.md', 'teach Claude', 'custom instructions', or 'prompt template'. The term 'documenting AI usage patterns' is not a natural user phrase. | 2 / 3 |
Distinctiveness Conflict Risk | The concept of 'LLM-first skills with valid frontmatter' is fairly niche, but 'agent instructions' and 'documenting AI usage patterns' are broad enough to potentially overlap with other documentation or AI-related skills. | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality meta-skill that effectively teaches how to create LLM-first skills. It is concise, actionable, and well-structured with clear decision gates, concrete examples (including good/bad comparisons), and a logical workflow. The progressive disclosure pattern of deferring to the style guide with inline fallback rules is particularly well-executed.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient. It uses imperative instructions throughout, avoids explaining concepts Claude already knows (like what a skill is in general terms), and every section serves a clear purpose. The decision table and inline fallback rules are compact and information-dense. | 3 / 3 |
Actionability | Provides concrete directory structures, exact frontmatter YAML templates, good/bad examples for description formatting, a clear ordered execution sequence, and specific file paths. The guidance is copy-paste ready and leaves no ambiguity about what to produce. | 3 / 3 |
Workflow Clarity | The 6 execution steps are clearly sequenced with a logical flow: check for existing guide → confirm no duplicate → create file structure → write frontmatter → write sections → register. The decision gates table provides clear routing for different content types, and the activation contract defines when to proceed vs. not. | 3 / 3 |
Progressive Disclosure | Content is well-structured with clear sections that serve distinct purposes. The decision gates table explicitly directs supporting content to `assets/` and `references/` directories. The skill references `docs/skill-style-guide.md` as the normative source with a clear fallback pattern, keeping the main body as an actionable overview. | 3 / 3 |
Total | 12 / 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.
3bfa934
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.