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.
89
86%
Does it follow best practices?
Impact
89%
1.03xAverage score across 3 eval scenarios
Passed
No known issues
Quality
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 description that clearly identifies the skill's purpose, lists concrete actions, includes an explicit 'Use when' clause with natural trigger terms, and occupies a distinct niche. It uses proper third-person voice and is concise without being vague. Minor improvement could include mentioning file format details like YAML frontmatter or markdown syntax to further enrich trigger terms.
| 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 triggers: building a new skill, creating a SKILL.md, planning skill architecture, writing skill content). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'new skill', 'SKILL.md', 'skill architecture', 'skill content', 'frontmatter metadata', 'skill directories'. These cover the likely terms a user would use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Targets a very specific niche — AiderDesk Agent Skills and SKILL.md files — which is unlikely to conflict with other skills. The domain-specific terminology (AiderDesk, SKILL.md, frontmatter metadata) makes it clearly distinguishable. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%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, concise skill that practices what it preaches about progressive disclosure. Its main weakness is that the workflow could benefit from a more explicit validation step (e.g., YAML lint check) and the actionability could be improved with a single complete, copy-paste-ready SKILL.md template rather than splitting the example into separate YAML and markdown blocks.
Suggestions
Combine the YAML frontmatter and markdown body into a single complete SKILL.md example block that can be copied as-is, rather than showing them as separate code blocks.
Add an explicit validation step to the Quick Workflow, such as 'Validate YAML: ensure frontmatter parses correctly (no tabs, proper `---` delimiters)' before the verification step.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't over-explain concepts Claude would already know, avoids padding, and every section serves a clear purpose. The progressive disclosure explanation is brief but necessary since it's domain-specific to AiderDesk. | 3 / 3 |
Actionability | The skill provides a concrete SKILL.md example with YAML frontmatter and a directory structure, which is helpful. However, the actual workflow steps are somewhat high-level (e.g., 'Write SKILL.md with YAML frontmatter and body instructions') without fully executable commands or a complete copy-paste-ready template that includes both frontmatter and body in one block. | 2 / 3 |
Workflow Clarity | The Quick Workflow section provides a clear 4-step sequence, and includes a basic troubleshooting tip for when the skill doesn't load. However, there's no explicit validation checkpoint between writing the SKILL.md and verifying it loads — for instance, no step to validate YAML syntax before testing, which would strengthen the feedback loop. | 2 / 3 |
Progressive Disclosure | Excellent use of progressive disclosure — the SKILL.md body is a concise overview with well-signaled, one-level-deep references to six separate documents covering quick-start, writing guide, development process, examples, CLI reference, and architecture. Navigation is clear and appropriately structured. | 3 / 3 |
Total | 10 / 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
9bcd9bb
- 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.