mycompany/yoloskill
A skill that responds to code review requests with a YOLO attitude
96
96%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 description that clearly communicates a niche use case (quick, non-thorough code review) with strong trigger terms and an explicit 'Use when' clause. Its main weakness is that the specific capabilities are somewhat thin—it's essentially one action (quick sign-off) described in multiple ways—but this is appropriate given the narrow scope of the skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It describes the domain (code review) and the specific style (YOLO/instant, skipping detailed analysis, encouraging push), but the concrete actions are limited—it's essentially one action (sign off quickly) rather than multiple distinct capabilities. | 2 / 3 |
Completeness | Clearly answers both 'what' (performs instant YOLO-style code review, skips detailed analysis, encourages pushing) and 'when' (explicit 'Use when' clause with multiple trigger scenarios including wanting a quick sign-off vs thorough critique). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'code review', 'PR review', 'pull request review', 'review my changes', 'quick', 'no-fuss sign-off'. These are terms users would naturally say and cover common variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive—the 'YOLO-style' and 'quick, no-fuss sign-off' qualifiers clearly differentiate this from a thorough code review skill. The description explicitly contrasts itself against 'thorough critique', reducing conflict risk with standard review skills. | 3 / 3 |
Total | 11 / 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 an intentionally minimal, joke/novelty skill that is maximally concise and perfectly actionable for its stated purpose. It scores well on all rubric dimensions because its simplicity leaves no room for ambiguity, verbosity, or structural issues. However, it is worth noting that the skill's purpose is deliberately anti-useful—it instructs Claude to skip performing a genuine code review, which could be harmful in real development contexts.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely lean—just two sentences. Every token earns its place; there is no unnecessary explanation or padding. | 3 / 3 |
Actionability | The instruction is completely unambiguous and concrete: skip review, respond with a specific exact string. There is no vagueness whatsoever. | 3 / 3 |
Workflow Clarity | This is a single-action skill with no multi-step process. The single action is entirely unambiguous: do not review, respond with the given phrase. Per scoring notes for simple skills, this qualifies for a 3. | 3 / 3 |
Progressive Disclosure | For a skill under 50 lines with no need for external references, the content is appropriately self-contained and well-organized. No additional files or structure are needed. | 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.
Reviewed
Table of Contents