ultrathink
Display colorful ANSI art of the word "ultrathink". Use when the user says "ultrathink" or invokes /ultrathink.
96
95%
Does it follow best practices?
Impact
100%
1.58xAverage score across 3 eval scenarios
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 for a narrow, single-purpose skill. It excels at completeness and distinctiveness with explicit trigger terms and clear 'Use when' guidance. The only limitation is the inherently simple nature of the skill, which means specificity is adequate but not rich with multiple actions.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names a specific action ('Display colorful ANSI art of the word "ultrathink"') but describes only a single, narrow capability rather than multiple concrete actions. | 2 / 3 |
Completeness | Clearly answers both what ('Display colorful ANSI art of the word "ultrathink"') and when ('Use when the user says "ultrathink" or invokes /ultrathink') with explicit triggers. | 3 / 3 |
Trigger Term Quality | Includes the exact natural keywords users would say: 'ultrathink' and '/ultrathink'. These are precise trigger terms that match user invocation patterns. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with unique trigger terms ('ultrathink', '/ultrathink') that are unlikely to conflict with any other skill. The specific ANSI art output is also unique. | 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 exemplary simple skill that does exactly what it needs to do with maximum efficiency. It provides a complete executable command, clear behavioral constraints ('Do not add any other output'), and wastes no tokens on explanation. The skill perfectly matches its stated purpose.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean - contains only the essential instruction and the executable command. No unnecessary explanation of what ANSI codes are or how bash works. | 3 / 3 |
Actionability | Provides a complete, copy-paste ready bash command that is immediately executable. The instruction is unambiguous: run this command, add no commentary. | 3 / 3 |
Workflow Clarity | This is a simple single-action skill with no multi-step process. The single action is completely unambiguous - run the command and output nothing else. | 3 / 3 |
Progressive Disclosure | For a skill this simple (under 15 lines, single task), no external references or additional structure is needed. The content is appropriately self-contained. | 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.
- Repository
- intellectronica/agent-skills
- Commit
9f7f750
- 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.