skill-creator
Create AiderDesk Agent Skills by writing SKILL.md files, defining frontmatter metadata, structuring references, and organizing skill directories. Use when building a new skill, creating a SKILL.md, planning skill architecture, or writing skill content.
84
78%
Does it follow best practices?
Impact
89%
1.03xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.aider-desk/skills/skill-creator/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 well-crafted skill description that clearly identifies its niche (AiderDesk Agent Skill creation), lists specific concrete actions, and includes an explicit 'Use when' clause with natural trigger terms. It uses proper third-person voice throughout and is concise without being vague. The domain-specific terminology ensures high distinctiveness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'writing SKILL.md files', 'defining frontmatter metadata', 'structuring references', and 'organizing skill directories'. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (create AiderDesk Agent Skills by writing SKILL.md files, defining frontmatter metadata, structuring references, organizing skill directories) and 'when' (explicit 'Use when' clause with four trigger scenarios). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'SKILL.md', 'new skill', 'skill architecture', 'skill content', 'frontmatter metadata', 'skill directories'. These cover the terms a user building skills would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche — specifically about creating AiderDesk Agent Skills and SKILL.md files. The domain-specific terminology (AiderDesk, SKILL.md, frontmatter metadata, skill directories) makes it very unlikely to conflict with other 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 that practices what it preaches regarding progressive disclosure, with a lean body pointing to detailed references. Its main weaknesses are moderate verbosity in explaining concepts (like when to create a skill) and a workflow that lacks explicit validation checkpoints. The example is helpful but could be more complete with frontmatter field documentation.
Suggestions
Remove or significantly trim the 'When to Create a Skill' section — Claude can infer when skills are useful; replace with a one-line trigger if needed.
Add a validation step to the Quick Workflow (e.g., 'Validate YAML with a linter or `yaml.safe_load()` before testing') to create a feedback loop for common errors.
Document all valid/required frontmatter fields (name, description, and any others) with brief constraints (e.g., 'name: lowercase-hyphenated, no spaces') rather than embedding them only in prose.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but includes some unnecessary explanation like 'When to Create a Skill' section which describes general concepts Claude can infer. The progressive disclosure explanation is useful context but slightly verbose for what could be a tighter summary. | 2 / 3 |
Actionability | Provides a concrete SKILL.md example with YAML frontmatter and a directory structure, which is helpful. However, the quick workflow steps are somewhat high-level (e.g., 'Write SKILL.md with YAML frontmatter' lacks specifics on all valid frontmatter fields), and the example is illustrative rather than a fully detailed template covering edge cases. | 2 / 3 |
Workflow Clarity | The 4-step quick workflow provides a clear sequence, and there's a basic troubleshooting note for skill loading failures. However, there's no explicit validation checkpoint between steps (e.g., validate YAML before proceeding) and no feedback loop for iterating on skill content quality. | 2 / 3 |
Progressive Disclosure | Excellent structure with a lean SKILL.md body that clearly references six separate documents in references/ for detailed content. The references are well-signaled with descriptive labels, and the content is appropriately split between overview and detailed materials. | 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.
- Repository
- hotovo/aider-desk
- Commit
e82a91f
- 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.